KONGU ENGINEERING COLLEGE

(Autonomous Institution Affiliated to Anna University, Chennai)

PERUNDURAI ERODE – 638 060
TAMILNADU INDIA

REGULATIONS, CURRICULUM & SYLLABI - 2020

(CHOICE BASED CREDIT SYSTEM &
OUTCOME BASED EDUCATION)
(For the students admitted during 2020 - 2021 and onwards)

BACHELOR OF TECHNOLOGY DEGREE

IN
ARTIFICAL INTELLIGENCE AND DATA SCIENCE
 Kongu Engineering College, Perundurai, Erode – 638060, India

INDEX

Page
[Link]. CONTENTS
No.

1 VISION AND MISSION OF THE INSTITUTE 3

2 QUALITY POLICY 3

3 VISION AND MISSION OF THE DEPARTMENT 3

4 PROGRAM EDUCATIONAL OBJECTIVES (PEOs) 3

5 PROGRAM OUTCOMES (POs) 4

6 PROGRAM SPECIFIC OUTCOMES (PSOs) 5

7 REGULATIONS 2020 6

8 CURRICULUM BREAKDOWN STRUCTURE 23

9 CATEGORISATION OF COURSES 23

10 SCHEDULING OF COURSES 31

11 MAPPING OF COURSES WITH PROGRAM OUTCOMES 32

CURRICULUM OF [Link] – ARTIFICIAL INTELLIGENCE AND DATA

12 39
SCIENCE

13 DETAILED SYLLABUS 46

[Link] Artificial Intelligence and Data Science - R2020 Page 2

 Kongu Engineering College, Perundurai, Erode – 638060, India

KONGU ENGINEERING COLLEGE

PERUNDURAI ERODE – 638 060
(Autonomous)

INSTITUTE VISION
To be a centre of excellence for development and dissemination of knowledge in Applied Sciences,
Technology, Engineering and Management for the Nation and beyond.

INSTITUTE MISSION
We are committed to value based Education, Research and Consultancy in Engineering and Management
and to bring out technically competent, ethically strong and quality professionals to keep our Nation
ahead in the competitive knowledge intensive world.

QUALITY POLICY
We are committed to

 Provide value based quality education for the development of students as competent and
responsible citizens.
 Contribute to the nation and beyond through research and development
 Continuously improve our services

DEPARTMENT OF COMPUTER SCIENCE ENGINEERING

VISION
To be a centre of excellence for nurturing competent computer professionals of high caliber and quality
for catering to the ever-changing needs of the industry and society.

MISSION
Department of Computer Science Engineering is committed to:
MS1: Develop innovative, competent and ethically strong computer engineers to meet global
challenges.
MS2: Foster consultancy and basic as well as applied research activities to solve real world problems.
MS3: Endeavour for constant upgradation of technical expertise to cater to the needs of the industry
and society.

PROGRAM EDUCATIONAL OBJECTIVES (PEOs)

Graduate of Computer Science Engineering programme will:
PEO1: Utilize the fundamental knowledge of basic sciences and engineering to succeed in their
professional career.
PEO2: Analyze, design, develop and verify computer-based solutions to real world problems.
PEO3: Exhibit soft skills, ethical code of conduct and ability for life-long learning.

[Link] Artificial Intelligence and Data Science - R2020 Page 3

 Kongu Engineering College, Perundurai, Erode – 638060, India

MAPPING OF MISSION STATEMENTS (MS) WITH PEOs

MS\PEO PEO1 PEO2 PEO3

MS1 2 2 3
MS2 3 3 2
MS3 3 2 3
1 – Slight, 2 – Moderate, 3 – Substantial

PROGRAM OUTCOMES (POs)

Graduates of Computer Science Engineering will:
PO1 Engineering knowledge: Apply the knowledge of mathematics, science, engineering
fundamentals, and an engineering specialization to the solution of complex engineering problems.
PO2 Problem analysis: Identify, formulate, review research literature, and analyze complex
engineering problems reaching substantiated conclusions using first principles of mathematics,
natural sciences, and engineering sciences.
PO3 Design/development of solutions: Design solutions for complex engineering problems and
design system components or processes that meet the specified needs with appropriate
consideration for the public health and safety, and the cultural, societal, and environmental
considerations.
PO4 Conduct investigations of complex problems: Use research-based knowledge and research
methods including design of experiments, analysis and interpretation of data, and synthesis of the
information to provide valid conclusions.
PO5 Modern tool usage: Create, select, and apply appropriate techniques, resources, and modern
engineering and IT tools including prediction and modeling to complex engineering activities
with an understanding of the limitations.
PO6 The engineer and society: Apply reasoning informed by the contextual knowledge to assess
societal, health, safety, legal and cultural issues and the consequent responsibilities relevant to the
professional engineering practice.
PO7 Environment and sustainability: Understand the impact of the professional engineering
solutions in societal and environmental contexts, and demonstrate the knowledge of, and need for
sustainable development.
PO8 Ethics: Apply ethical principles and commit to professional ethics and responsibilities and norms
of the engineering practice.
PO9 Individual and team work: Function effectively as an individual, and as a member or leader in
diverse teams, and in multidisciplinary settings.
PO10 Communication: Communicate effectively on complex engineering activities with the
engineering community and with society at large, such as, being able to comprehend and write
effective reports and design documentation, make effective presentations, and give and receive
clear instructions.
PO11 Project management and finance: Demonstrate knowledge and understanding of the
engineering and management principles and apply these to one’s own work, as a member and
leader in a team, to manage projects and in multidisciplinary environments.
PO12 Life-long learning: Recognize the need for, and have the preparation and ability to engage in
independent and life-long learning in the broadest context of technological change.

[Link] Artificial Intelligence and Data Science - R2020 Page 4

 Kongu Engineering College, Perundurai, Erode – 638060, India

PROGRAM SPECIFIC OUTCOMES (PSOs)

Graduates of Computer Science Engineering will:

PSO1 Foundations of Computer Science: Ability to use the mathematical and computing knowledge
to propose viable ideas and solutions to solve real world problems.

PSO2 Software design and Development: Ability to develop computer based systems using
engineering skills, knowledge of software design process, programming languages and tools.

MAPPING OF PEOs WITH POs AND PSOs

PEO\ PO PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2

PEO1 3 2 - - - - 2 - - - 1 2 3 1

PEO2 - 3 3 3 2 - 1 - - - 2 2 1 3

PEO3 - - - - - 3 - 3 3 3 - 3 1 1
1 – Slight, 2 – Moderate, 3 – Substantial

[Link] Artificial Intelligence and Data Science - R2020 Page 5

 Kongu Engineering College, Perundurai, Erode – 638060, India
KONGU ENGINEERING COLLEGE, PERUNDURAI, ERODE – 638060

(Autonomous)

REGULATIONS 2020

CHOICE BASED CREDIT SYSTEM AND OUTCOME BASED EDUCATION

BACHELOR OF ENGINEERING (BE) / BACHELOR OF TECHNOLOGY (BTech) DEGREE

PROGRAMMES

These regulations are applicable to all candidates admitted into BE/BTech Degree programmes from the
academic year 2020 – 2021 onwards.

1. DEFINITIONS AND NOMENCLATU

RE

In these Regulations, unless otherwise specified:

i. “University” means ANNA UNIVERSITY, Chennai.

ii. “College” means KONGU ENGINEERING COLLEGE.

iii. “Programme” means Bachelor of Engineering (BE) / Bachelor of Technology (BTech)

Degree programme

iv. “Branch” means specialization or discipline of BE/BTech Degree programme, like Civil
Engineering, Information Technology, etc.

v. “Course” means a Theory / Theory cum Practical / Practical course that is normally
studied in a semester like Mathematics, Physics etc.

vi. “Credit” means a numerical value allocated to each course to describe the candidate’s
workload required per week.

vii. “Grade” means the letter grade assigned to each course based on the marks range
specified.

viii. “Grade point” means a numerical value (0 to 10) allocated based on the grade assigned
to each course.

ix. “Principal” means Chairman, Academic Council of the College.

x. “Controller of Examinations” means authorized person who is responsible for all

examination related activities of the College.

xi. “Head of the Department” means Head of the Department concerned of the College.

2. PROGRAMMES AND BRANCHES OF STUDY

[Link] Artificial Intelligence and Data Science - R2020 Page 6

 Kongu Engineering College, Perundurai, Erode – 638060, India
The following programmes and branches of study approved by Anna University, Chennai and
All India Council for Technical Education, New Delhi are offered by the College.
Programme Branch

Civil Engineering
Mechanical Engineering
Electronics and Communication Engineering
Computer Science and Engineering
BE Electrical and Electronics Engineering
Electronics and Instrumentation Engineering
Mechatronics Engineering
Automobile Engineering
Computer Science and Design
Chemical Engineering
Information Technology
BTech Food Technology
Artificial Intelligence and Data Science
Artificial Intelligence and Machine Learning

3. ADMISSION REQUIREMENTS
3.1 First Semester Admission
The candidates seeking admission to the first semester of the eight semester BE / BTech
Degree Programme:
Should have passed the Higher Secondary Examination (10 + 2) in the academic stream
with Mathematics, Physics and Chemistry as three of the four subjects of study under
Part-III subjects of the study conducted by the Government of Tamil Nadu or any
examination of any other University or authority accepted by the Anna University,
Chennai as equivalent thereto.
(OR)
Should have passed the Higher Secondary Examination of Vocational stream
(Vocational groups in Engineering / Technology) as prescribed by the Government of
Tamil Nadu.
They should also satisfy other eligibility conditions as prescribed by the Anna
University, Chennai and Directorate of Technical Education, Chennai from time to time.

3.2 Lateral Entry Admission

The candidates who hold a Diploma in Engineering / Technology awarded by the State
Board of Technical Education, Tamilnadu or its equivalent are eligible to apply for
Lateral entry admission to the third semester of BE / BTech in relevant branches of
[Link] Artificial Intelligence and Data Science - R2020 Page 7
 Kongu Engineering College, Perundurai, Erode – 638060, India
study.
(OR)
The candidates who hold a BSc degree (10+2+3 stream) with mathematics as one of the
subjects at the BSc level from a recognised University are eligible to apply for Lateral
entry admission to the third semester of BE / BTech. Such candidates shall undergo two
additional Engineering course(s) in the third and fourth semesters as prescribed by the
College.
They should satisfy other eligibility conditions prescribed by the Anna University,
Chennai and Directorate of Technical Education, Chennai from time to time.
4. STRUCTURE OF PROGRAMMES
4.1 Categorisation of Courses
The BE / BTech programme shall have a curriculum with syllabi comprising of theory,
theory cum practical, practical courses in each semester, professional skills training,
project work, internship, etc. that have been approved by the respective Board of Studies
and Academic Council of the College. All the programmes have well defined Programme
Outcomes (PO), Programme Specific Outcomes (PSO) and Programme Educational
Objectives (PEOs) as per Outcome Based Education (OBE). The content of each course
is designed based on the Course Outcomes (CO). The courses shall be categorized as
follows:
i. Humanities and Social Sciences (HS) including Management Courses
ii. Basic Science (BS) Courses
iii. Engineering Science (ES) Courses
iv. Professional Core (PC) Courses
v. Professional Elective (PE) Courses
vi. Open Elective (OE) Courses
vii. Employability Enhancement Courses (EC) like Project work, Professional Skills,
Comprehensive Test & Viva, Entrepreneurships/Start ups and Internship in
Industry or elsewhere
viii. Audit Courses (AC)
ix. Mandatory Courses (MC) like Student Induction Program and Environmental
Science.
x. Honours Degree Courses (HC)
4.2 Credit Assignment and Honours Degree
4.2.1. Credit Assignment
Each course is assigned certain number of credits as follows:
Contact period per week Credits
1 Lecture / Tutorial Period 1
2 Practical Periods 1
2 Project Work Periods 1
40 Training / Internship Periods 1
The minimum number of credits to complete the BE/BTech programme is 169.
[Link] Artificial Intelligence and Data Science - R2020 Page 8
 Kongu Engineering College, Perundurai, Erode – 638060, India

4.2.2. Honours Degree

If a candidate earns 18 to 20 additional credits in an emerging area, then he/she can be
awarded with Honours degree mentioning that emerging area as his/her specialization.
The respective board of studies shall recommend the specializations for honours degree
and appropriate additional courses to be studied by the candidate which shall get
approval from Academic Council of the institution. A candidate shall have not less than
8.0 CGPA and no history of arrears during the entire programme to opt for the honours
degree.
Various specializations for various branches recommended by the respective boards of
studies are given below:
S. Specializations for Honours To be offered as Honours, Only for the
No. degree in emerging areas following branches mentioned against the
specialization
1. Construction Technology Civil Engineering
2. Robotics Mechanical Engineering
3. Electric Vehicles Mechanical Engineering
4. Artificial Intelligence and Mechatronics Engineering
Machine Learning
5. Electric Vehicles Automobile Engineering
6. Artificial Intelligence and Electronics and Communication
Machine Learning Engineering
7. Electric Vehicles Electrical and Electronics Engineering
8. Control Systems and Sensors Electronics and Instrumentation
Technology Engineering
9. Cyber Security Computer Science and Engineering
10. Data Science Computer Science and Engineering
11. Cyber Security Information Technology
12. Data Science Information Technology
13. Waste Technology Chemical Engineering
14. Food Processing and Food Technology
Management
The courses specified under Honours degree in the emerging area may include theory,
theory cum practical, practical, project work, etc. under the particular specialization. A
candidate can choose and study these specified courses from fourth semester onwards
and he/she shall successfully complete the courses within the stipulated time vide
clause 5. Total number of credits earned in each semester may vary from candidate to
candidate based on the courses chosen. The registration, assessment & evaluation pattern
and classification of grades of these courses shall be the same as that of the courses in the
regular curriculum of the programme of the candidate vide clause 6, clause 7 and
clause 15 respectively. A candidate can earn Honours degree in only one specialization
during the entire duration of the programme.

[Link] Artificial Intelligence and Data Science - R2020 Page 9

 Kongu Engineering College, Perundurai, Erode – 638060, India
4.3 Employability Enhancement Courses
A candidate shall be offered with the employability enhancement courses like project
work, internship, professional skills training, comprehensive test & viva, internship and
entrepreneurships/start ups during the programme to gain/exhibit the knowledge/skills.
4.3.1 Professional Skills Training/ Entrepreneurships/Start Ups
A candidate may be offered with appropriate training courses imparting
programming skills, communication skills, problem solving skills, aptitude skills
etc. It is offered in two phases as phase I in fifth semester and phase II in sixth
semester including vacation periods and each phase can carry two credits.
(or)
A candidate may be allowed to go for training at research organizations or
industries for a required number of hours in sixth semester vacation period. Such
candidate can earn two credits for this training course in place of Professional
Skills Training course II in sixth semester. He/She shall attend Professional Skills
Training Phase I in fifth semester and can earn two credits.
(or)
A candidate may be allowed to set up a start up and working part-time for the start
ups by applying his/her innovations and can become a student entrepreneur
during BE/BTech programme. Candidates can set up their start up from fifth
semester onwards either inside or outside of the college. Such student entrepreneurs
may earn a maximum of 2 credits per semester for two semesters each in place of
either Professional Skills Training I or Professional Skills Training II. The area in
which the candidate wants to initiate a start up may be interdisciplinary or
multidisciplinary. The progress of the startup shall be evaluated by a panel of
members constituted by the Principal through periodic reviews.
4.3.2 Comprehensive Test & Viva
The overall knowledge of the candidate in various courses he/she studied shall be
evaluated by (i) conducting comprehensive tests with multiple choice questions
generally with pattern similar to GATE and/or (ii) viva-voce examination
conducted by a panel of experts assigned by the Head of the department. The
members can examine the knowledge of the candidate by asking questions from
various domains and the marks will be assigned based on their answers. This
course shall carry two credits.
4.3.3 Internships
The curriculum enables a candidate to go for full time projects through internship
during a part of seventh semester and/or entire final semester and can earn credits
vide clause 7.6 and clause 7.11.
A candidate is permitted to go for full time projects through internship in seventh
semester with the following condition: The candidate shall complete a part of the
seventh semester courses with a total credit of about 50% of the total credits of
seventh semester including Project Work I Phase II in the first two months from the
commencement of the seventh semester under fast track mode. The balance credits
required to complete the seventh semester shall be earned by the candidate through
either approved Value Added Courses /Online courses / Self Study Courses or
Add/Drop courses as per clause 4.4 and clause 4.5 respectively.
A candidate is permitted to go for full time projects through internship during
eighth semester. Such candidate shall earn the minimum number of credits required
to complete eighth semester other than project through either approved Value
Added Courses /Online courses / Self Study Courses or Add/Drop courses as per

[Link] Artificial Intelligence and Data Science - R2020 Page 10

 Kongu Engineering College, Perundurai, Erode – 638060, India
clause 4.4 and clause 4.5 respectively.
Assessment procedure is to be followed as specified in the guidelines approved by
the Academic Council.
4.4 Value Added Courses / Online Courses / Self Study Courses
The candidates may optionally undergo Value Added Courses / Online Courses /
Self Study Courses as elective courses.

4.4.1 Value Added Courses: Value Added courses each with One / Two credits shall
be offered by the college with the prior approval from respective Board of
Studies. A candidate can earn a maximum of six credits through value added
courses during the entire duration of the programme.
4.4.2 Online Courses: Candidates may be permitted to earn credits for online courses,
offered by NPTEL / SWAYAM / a University / Other Agencies, approved by
respective Board of Studies.

4.4.3 Self Study Courses: The Department may offer an elective course as a self study
course. The syllabus of the course shall be approved by the respective Board of
Studies. However, mode of assessment for a self study course will be the same as
that used for other courses. The candidates shall study such courses on their own
under the guidance of member of the faculty following due approval procedure.
Self study course is limited to one per semester.

4.4.4 The elective courses in the final year may be exempted if a candidate earns the
required credits vide clause 4.4.1, 4.4.2 and 4.4.3 by registering the required
number of courses in advance.
4.4.5 A candidate can earn a maximum of 30 credits through all value added courses,
online courses and self study courses.

4.5 Flexibility to Add or Drop Courses

4.5.1 A candidate has to earn the total number of credits specified in the curriculum of
the respective programme of study in order to be eligible to obtain the degree.
However, if the candidate wishes, then the candidate is permitted to earn more
than the total number of credits prescribed in the curriculum of the candidate’s
programme.
4.5.2 From the first to eighth semesters the candidates have the option of registering for
additional elective/Honours courses or dropping of already registered additional
elective/Honours courses within two weeks from the start of the semester. Add /
Drop is only an option given to the candidates. Total number of credits of such
courses during the entire programme of study cannot exceed eight.
4.6 Maximum number of credits the candidate can enroll in a particular semester cannot
exceed 30 credits.

4.7 The blend of different courses shall be so designed that the candidate at the end of the
programme would have been trained not only in his / her relevant professional field but
also would have developed to become a socially conscious human being.

[Link] Artificial Intelligence and Data Science - R2020 Page 11

 Kongu Engineering College, Perundurai, Erode – 638060, India

4.8 The medium of instruction, examinations and project report shall be English.

5. DURATION OF THE PROGRAMME

5.1 A candidate is normally expected to complete the BE / BTech Degree programme in

8 consecutive semesters/4 Years (6 semesters/3 Years for lateral entry candidate), but in
any case not more than 14 semesters/7 Years (12 semesters/6 Years for lateral entry
candidate).

5.2 Each semester shall consist of a minimum of 90 working days including continuous
assessment test period. The Head of the Department shall ensure that every teacher
imparts instruction as per the number of periods specified in the syllabus for the course
being taught.

5.3 The total duration for completion of the programme reckoned from the commencement
of the first semester to which the candidate was admitted shall not exceed the maximum
duration specified in clause 5.1 irrespective of the period of break of study (vide
clause 11) or prevention (vide clause 9) in order that the candidate may be eligible for the
award of the degree (vide clause 16). Extension beyond the prescribed period shall not be
permitted.
6. COURSE REGISTRATION FOR THE EXAMINATION

6.1 Registration for the end semester examination is mandatory for courses in the current
semester as well as for the arrear courses failing which the candidate will not be
permitted to move on to the higher semester. This will not be applicable for the courses
which do not have an end semester examination.

6.2 The candidates who need to reappear for the courses which have only continuous
assessment shall enroll for the same in the subsequent semester, when offered next, and
repeat the course. In this case, the candidate shall attend the classes, satisfy the
attendance requirements (vide clause 8), earn continuous assessment marks. This will be
considered as an attempt for the purpose of classification.

6.3 If a candidate is prevented from writing end semester examination of a course due to lack
of attendance, the candidate has to attend the classes, when offered next, and fulfill the
attendance requirements as per clause 8 and earn continuous assessment marks. If the
course, in which the candidate has a lack of attendance, is an elective, the candidate may
register for the same or any other elective course in the subsequent semesters and that
will be considered as an attempt for the purpose of classification.

6.4 A candidate shall register for the chosen courses as well as arrear courses (if any vide
clause 6.2 and 6.3) from the list of courses specified under Honours degree.

7. ASSESSMENT AND EXAMINATION PROCEDURE FOR AWARDING MARKS

7.1 The BE/BTech programmes consist of Theory Courses, Theory cum Practical courses,
Practical courses, Project Work, Professional Skills Training / Industrial Training,
Internship and Entrepreneurships/ Start ups. Performance in each course of study shall
be evaluated based on (i) Continuous Assessments (CA) throughout the semester and (ii)
[Link] Artificial Intelligence and Data Science - R2020 Page 12
 Kongu Engineering College, Perundurai, Erode – 638060, India
End Semester Examination (ESE) at the end of the semester except for the courses which
are evaluated based on continuous assessment only. Each course shall be evaluated for a
maximum of 100 marks as shown below:

Sl. Continuous End Semester

Category of Course Assessment Examination
No.
Marks Marks
1. Theory / Practical 50 50

2. Theory cum Practical The distribution of marks shall be

decided based on the credit
weightage assigned to theory and
practical components.

3. Professional Skills Training / / 100 ---

Comprehensive Test & Viva /
Entrepreneurships / Start ups / Project
Work 1 / Industrial Training /
Mandatory Course
4. Project Work 2 Phase I / Project Work 2 50 50
Phase II / Internships

5. Value Added Course The distribution ---

of marks shall be
6. All other Courses decided based on
the credit
weightage
assigned
7.2 Examiners for setting end semester examination question papers for theory courses,
theory cum practical courses and practical courses and evaluating end semester
examination answer scripts, project works, internships and entrepreneurships/start ups
shall be appointed by the Controller of Examinations after obtaining approval from the
Principal.

7.3 Theory Courses

For all theory courses out of 100 marks, the continuous assessment shall be 50 marks and
the end semester examination shall be for 50 marks. However, the end semester
examinations shall be conducted for 100 marks and the marks obtained shall be reduced
to 50. The continuous assessment tests shall be conducted as per the schedule laid down
in the academic schedule. Three tests shall be conducted for 50 marks each and reduced
to 30 marks each. The total of the continuous assessment marks and the end semester
examination marks shall be rounded off to the nearest integer.

[Link] Artificial Intelligence and Data Science - R2020 Page 13

 Kongu Engineering College, Perundurai, Erode – 638060, India

7.3.1 The assessment pattern for awarding continuous assessment marks shall be as
follows:
Sl. Max.
Type Remarks
No. Marks
Test - I 30
1. Test - II 30 Average of best two
Test - III 30
Should be of Open
Book/Objective Type.
Average of best 4 (or
2. Tutorial 15 more, depending on the
nature of the course, as
may be approved by
Principal)
Assignment / Paper Presentation
To be assessed by the
in Conference / Seminar /
3. 05 Course Teacher based
Comprehension / Activity based
on any one type.
learning / Class notes
Rounded off to the one
Total 50
decimal place
However, the assessment pattern for awarding the continuous assessment marks
may be changed based on the nature of the course and is to be approved by the
Principal.
7.3.2 A reassessment test or tutorial covering the respective test or tutorial portions
may be conducted for those candidates who were absent with valid reasons
(Sports or any other reason approved by the Principal).
7.3.3 The end semester examination for theory courses shall be for a duration of
three hours and shall be conducted between November and January during odd
semesters and between April and June during even semesters every year.
7.4 Theory cum Practical Courses
For courses involving theory and practical components, the evaluation pattern as per the
clause 7.1 shall be followed. Depending on the nature of the course, the end semester
examination shall be conducted for theory and the practical components. The
apportionment of continuous assessment and end semester examination marks shall be
decided based on the credit weightage assigned to theory and practical components
approved by Principal.
7.5 Practical Courses
For all practical courses out of 100 marks, the continuous assessment shall be for 50
marks and the end semester examination shall be for 50 marks. Every exercise /
experiment shall be evaluated based on the candidate’s performance during the practical
class and the candidate's records shall be maintained.
7.5.1 The assessment pattern for awarding continuous assessment marks for each
course shall be decided by the course coordinator based on rubrics of that
particular course, and shall be based on rubrics for each experiment.

[Link] Artificial Intelligence and Data Science - R2020 Page 14

 Kongu Engineering College, Perundurai, Erode – 638060, India
7.6 Project Work II Phase I / Project Work II Phase II
7.6.1 Project work shall be assigned to a single candidate or to a group of
candidates not exceeding 4 candidates in a group. The project work is mandatory
for all the candidates.
7.6.2 The Head of the Department shall constitute review committee for project
work. There shall be two assessments by the review committee during the
semester. The candidate shall make presentation on the progress made by
him/her before the committee.
7.6.3 The continuous assessment and end semester examination marks for Project
Work II (both Phase I and Phase II) and the Viva-Voce Examination shall be
distributed as below:

Continuous Assessment End Semester Examination

(Max. 50 Marks) (Max. 50 Marks)
Report
Review I Review II Evaluation Viva - Voce
Zeroth Review
(Max.. 20 Marks) (Max. 30 Marks) (Max. 20 (Max. 30 Marks)
Marks)
Rv. Guide Review Guide Review Guide Ext. Exr. Guide Exr.1 Exr.2
Com Committee Committee
(excluding (excluding
guide) guide)
0 0 10 10 15 15 20 10 10 10

7.6.4 The Project Report prepared according to approved guidelines and duly signed
by the Supervisor shall be submitted to Head of the Department. The
candidate(s) must submit the project report within the specified date as per the
academic schedule of the semester. If the project report is not submitted within
the specified date then the candidate is deemed to have failed in the Project
Work and redo it in the subsequent semester.
7.6.5 If a candidate fails to secure 50% of the continuous assessment marks in the
project work, he / she shall not be permitted to submit the report for that
particular semester and shall have to redo it in the subsequent semester and
satisfy attendance requirements.
7.6.6 The project work shall be evaluated based on the project report submitted by
the candidate in the respective semester and viva-voce examination by a
committee consisting of two examiners and guide of the project work.
7.6.7 If a candidate fails to secure 50 % of the end semester examination marks in the
project work, he / she shall be required to resubmit the project report within 30
days from the date of declaration of the results and a fresh viva-voce
examination shall be conducted as per clause 7.6.6.
7.6.8 A copy of the approved project report after the successful completion of
viva-voce examination shall be kept in the department library.

[Link] Artificial Intelligence and Data Science - R2020 Page 15

 Kongu Engineering College, Perundurai, Erode – 638060, India

7.7 Project Work I Phase I / Industrial Training

The evaluation method shall be same as that of the Project Work II as per clause 7.6
excluding 7.6.3, 7.6.5, 7.6.6 and 7.6.7. The marks distribution is given below:

Continuous Assessment
(Max. 100 Marks)

Review III
(Max. 50 Marks)
Review I Review II Report
Zeroth Review
(Max.. 20 Marks) (Max.. 30 Marks) Evaluation Viva - Voce
(Max. 20 (Max. 30 Marks)
Marks)
Review Guide Review Guide Review Guide Review Guide Review
Commi Committee Committee Committee Committee
ttee (excluding (excluding
guide) guide)

0 0 10 10 15 15 20 10 20
If a candidate fails to secure 50 % of the continuous assessment marks in this course, he /
she shall be required to resubmit the project report within 30 days from the date of
declaration of the results and a fresh viva-voce examination shall be conducted.
7.8 Professional Skills Training
Phase I training shall be conducted for minimum of 80 hours in 4th semester vacation and
during 5th semester. Phase II training shall be conducted for minimum of 80 hours in 5th
semester vacation and during 6th semester. The evaluation procedure shall be approved
by the Principal.

7.9 Comprehensive Test/Viva

A candidate can earn 2 credits by successfully completing this course. The evaluation
procedures shall be approved by the Principal.

7.10 Entrepreneurships/ Start ups

A start up/business model may be started by a candidate individually or by a group of
maximum of three candidates during the programme vide clause 4.3.1. The head of the
department concerned shall assign a faculty member as a mentor for each start up.

A review committee shall be formed by the Principal for reviewing the progress of the
Start ups / Business models, innovativeness, etc. The review committee can recommend
the appropriate grades for academic performance for the candidate(s) involved in the
start ups. This course shall carry a maximum of two credits in fifth semester and two
credits in sixth semester respectively and shall be evaluated through continuous
assessments for a maximum of 100 marks vide clause 7.1. A report about the start ups is
to be submitted to the review committee for evaluation for each start up and the marks
will be given to Controller of Examinations after getting approval from Principal.

[Link] Artificial Intelligence and Data Science - R2020 Page 16

 Kongu Engineering College, Perundurai, Erode – 638060, India
7.11 Projects through Internships
Each candidate shall submit a brief report about the internship undergone and a
certificate issued from the organization concerned at the time of Viva-voce examination
to the review committee. The evaluation method shall be same as that of the Project
Work II as per clause 7.6.
7.12 Value Added Course
Minimum of two assessments shall be conducted during the value added course duration
by the offering department concerned.

7.13 Online Course

The Board of Studies will provide methodology for the evaluation of the online courses.
The Board can decide whether to evaluate the online courses through continuous
assessment and end semester examination or through end semester examination only. In
case of credits earned through online mode from NPTEL / SWAYAM / a University /
Other Agencies approved by Chairman, Academic Council, the credits may be
transferred and grades shall be assigned accordingly.

7.14 Self Study Course

The member of faculty approved by the Head of the Department shall be responsible for
periodic monitoring and evaluation of the course. The course shall be evaluated through
continuous assessment and end semester examination. The evaluation methodology shall
be the same as that of a theory course.
7.15 Audit Course
A candidate may be permitted to register for specific course not listed in his/her
programme curriculum and without undergoing the rigors of getting a 'good' grade, as an
Audit course, subject to the following conditions.
The candidate can register only one Audit course in a semester starting from
second semester subject to a maximum of two courses during the entire programme of
study. Such courses shall be indicated as 'Audit' during the time of registration itself.
Only courses currently offered for credit to the candidates of other branches can be
audited.
A course appearing in the curriculum of a candidate cannot be considered as an audit
course. However, if a candidate has already met the Professional Elective and Open
Elective credit requirements as stipulated in the curriculum, then, a Professional Elective
or an Open Elective course listed in the curriculum and not taken by the candidate for
credit can be considered as an audit course.
Candidates registering for an audit course shall meet all the assessment and examination
requirements (vide clause 7.3) applicable for a credit candidate of that course. Only if
the candidate obtains a performance grade, the course will be listed in the semester
Grade Sheet and in the Consolidated Grade Sheet along with the grade SF (Satisfactory).
Performance grade will not be shown for the audit course.
Since an audit course has no grade points assigned, it will not be counted for the purpose
of GPA and CGPA calculations.

[Link] Artificial Intelligence and Data Science - R2020 Page 17

 Kongu Engineering College, Perundurai, Erode – 638060, India
7.16 Mandatory Course
A candidate shall attend and complete the induction training program of duration three
weeks at the beginning of the first semester. It is mandatory for all candidates who have
joined in various branches of all BE/BTech programmes. The induction training program
includes the courses recommended by AICTE. Apart from this induction program, a
candidate shall undergo the courses listed by AICTE as mandatory courses during their
programme. No credits shall be given for such courses and shall be evaluated through
continuous assessment tests only vide clause 7.1 for a maximum of 100 marks each.
Since these courses have no grade points assigned, these courses will not be counted for
the purpose of GPA and CGPA calculations.
7.17 Yoga and Values for Holistic Development (YVHD) and Universal Human Values
(UHV)
Courses such as YVHD and UHV shall be offered to all candidates of all BE/BTech
programmes. These courses shall carry a maximum of 100 marks each and shall be
evaluated through continuous assessment tests only vide clause 7.1. The candidate(s) can
earn 2 credits for UHV and 1 credit for YVHD by successfully completing these courses.
Two continuous assessment tests will be conducted and the average marks will be taken
for the calculation of grades.
8. REQUIREMENTS FOR COMPLETION OF A SEMESTER
8.1 A candidate who has fulfilled the following conditions shall be deemed to have
satisfied the requirements for completion of a semester and permitted to appear for the
examinations of that semester.
8.1.1 Ideally, every candidate is expected to attend all classes and secure 100 %
attendance. However, a candidate shall secure not less than 80 % (after
rounding off to the nearest integer) of the overall attendance taking into account
the total number of working days in a semester.
8.1.2 A candidate who could not satisfy the attendance requirements as per clause
8.1.1 due to medical reasons (hospitalization / accident / specific illness) but has
secured not less than 70 % in the current semester may be permitted to appear
for the current semester examinations with the approval of the Principal on
payment of a condonation fee as may be fixed by the authorities from time to
time. The medical certificate needs to be submitted along with the leave
application. A candidate can avail this provision only twice during the entire
duration of the degree programme.
A candidate who could not satisfy the attendance requirements as per clause
8.1.1 due to his/her entrepreneurships/ start ups activities, but has secured not
less than 60 % in the current semester can be permitted to appear for the current
semester examinations with the recommendation of review committee and
approval from the Principal.
8.1.3 In addition to clause 8.1.1 or 8.1.2, a candidate shall secure not less than 60 %
attendance in each course.

8.1.4 A candidate shall be deemed to have completed the requirements of study of any
semester only if he/she has satisfied the attendance requirements (vide clause
8.1.1 to 8.1.3) and has registered for examination by paying the prescribed fee.

[Link] Artificial Intelligence and Data Science - R2020 Page 18

 Kongu Engineering College, Perundurai, Erode – 638060, India

8.1.5 Candidate’s progress is satisfactory.

8.1.6 Candidate’s conduct is satisfactory and he/she was not involved in any
indisciplined activities in the current semester.

8.2. The candidates who do not complete the semester as per clauses from 8.1.1 to 8.1.6
except 8.1.3 shall not be permitted to appear for the examinations at the end of the
semester and not be permitted to go to the next semester. They have to repeat the
incomplete semester in next academic year.

8.3 The candidates who satisfy the clause 8.1.1 or 8.1.2 but do not complete the course as
per clause 8.1.3 shall not be permitted to appear for the end semester examination of
that course alone. They have to repeat the incomplete course in the subsequent
semester when it is offered next.

9. REQUIREMENTS FOR APPEARING FOR END SEMESTER EXAMINATION

9.1 A candidate shall normally be permitted to appear for end semester examination of the
current semester if he/she has satisfied the semester completion requirements as per
clause 8, and has registered for examination in all courses of that semester. Registration
is mandatory for current semester examinations as well as for arrear examinations
failing which the candidate shall not be permitted to move on to the higher semester.

9.2 When a candidate is deputed for a National / International Sports event during End
Semester examination period, supplementary examination shall be conducted for such a
candidate on return after participating in the event within a reasonable period of time.
Such appearance shall be considered as first appearance.

9.3 A candidate who has already appeared for a course in a semester and passed the
examination is not entitled to reappear in the same course for improvement of letter
grades / marks.

10. PROVISION FOR WITHDRAWAL FROM EXAMINATIONS

10.1 A candidate may, for valid reasons, be granted permission to withdraw from appearing
for the examination in any regular course or all regular courses registered in a particular
semester. Application for withdrawal is permitted only once during the entire duration
of the degree programme.

10.2 The withdrawal application shall be valid only if the candidate is otherwise eligible to
write the examination (vide clause 9) and has applied to the Principal for permission
prior to the last examination of that semester after duly recommended by the Head of
the Department.

10.3 The withdrawal shall not be considered as an appearance for deciding the eligibility of a
candidate for First Class with Distinction/First Class.

[Link] Artificial Intelligence and Data Science - R2020 Page 19

 Kongu Engineering College, Perundurai, Erode – 638060, India

10.4 If a candidate withdraws a course or courses from writing end semester examinations,
he/she shall register the same in the subsequent semester and write the end semester
examinations. A final semester candidate who has withdrawn shall be permitted to
appear for supplementary examination to be conducted within reasonable time as per
clause 14.

10.5 The final semester candidate who has withdrawn from appearing for project viva-voce
for genuine reasons shall be permitted to appear for supplementary viva-voce
examination within reasonable time with proper application to Controller of
Examinations and on payment of prescribed fee.

11. PROVISION FOR BREAK OF STUDY

11.1 A candidate is normally permitted to avail the authorised break of study under valid
reasons (such as accident or hospitalization due to prolonged ill health or any other valid
reasons) and to rejoin the programme in a later semester. He/She shall apply in advance
to the Principal, through the Head of the Department, stating the reasons therefore, in
any case, not later than the last date for registering for that semester examination.
A candidate is permitted to avail the authorised break of study only once during the
entire period of study for a maximum period of one year. However, in extraordinary
situation the candidate may apply for additional break of study not exceeding another one
year by paying prescribed fee for the break of study.

11.2 The candidates permitted to rejoin the programme after break of study / prevention due
to lack of attendance shall be governed by the rules and regulations in force at the time
of rejoining.

11.3 The candidates rejoining in new Regulations shall apply to the Principal in the
prescribed format through Head of the Department at the beginning of the readmitted
semester itself for prescribing additional/equivalent courses, if any, from any semester
of the regulations in-force, so as to bridge the curriculum in-force and the old
curriculum.

11.4 The total period of completion of the programme reckoned from the commencement of
the semester to which the candidate was admitted shall not exceed the maximum period
specified in clause 5 irrespective of the period of break of study in order to qualify for
the award of the degree.

11.5 If any candidate is prevented for want of required attendance, the period of prevention
shall not be considered as authorized break of study.

11.6 If a candidate has not reported to the college for a period of two consecutive semesters
without any intimation, the name of the candidate shall be deleted permanently from the
college enrollment. Such candidates are not entitled to seek readmission under any
circumstances.

12. PASSING REQUIREMENTS

[Link] Artificial Intelligence and Data Science - R2020 Page 20

 Kongu Engineering College, Perundurai, Erode – 638060, India

12.1 A candidate who secures not less than 50 % of total marks (continuous assessment and
end semester examination put together) prescribed for the course with a minimum of
45 % of the marks prescribed for the end semester examination in all category of
courses vide clause 7.1 except for the courses which are evaluated based on continuous
assessment only shall be declared to have successfully passed the course in the
examination.

12.2 A candidate who secures not less than 50 % in continuous assessment marks prescribed
for the courses which are evaluated based on continuous assessment only shall be
declared to have successfully passed the course. If a candidate secures less than 50% in
the continuous assessment marks, he / she shall have to re-enroll for the same in the
subsequent semester and satisfy the attendance requirements.

12.3 For a candidate who does not satisfy the clause 12.1, the continuous assessment marks
secured by the candidate in the first attempt shall be retained and considered valid for
subsequent attempts. However, from the fourth attempt onwards the marks scored in the
end semester examinations alone shall be considered, in which case the candidate shall
secure minimum 50 % marks in the end semester examinations to satisfy the passing
requirements, but the grade awarded shall be only the lowest passing grade irrespective
of the marks secured.
13. REVALUATION OF ANSWER SCRIPTS
A candidate shall apply for a photocopy of his / her semester examination answer script within
a reasonable time from the declaration of results, on payment of a prescribed fee by submitting
the proper application to the Controller of Examinations. The answer script shall be pursued and
justified jointly by a faculty member who has handled the course and the course coordinator and
recommended for revaluation. Based on the recommendation, the candidate can register for
revaluation through proper application to the Controller of Examinations. The Controller of
Examinations will arrange for revaluation and the results will be intimated to the candidate
concerned. Revaluation is permitted only for Theory courses and Theory cum Practical courses
where end semester examination is involved.

14. SUPPLEMENTARY EXAMINATION

If a candidate fails to clear all courses in the final semester after the announcement of final end
semester examination results, he/she shall be allowed to take up supplementary examinations to
be conducted within a reasonable time for the courses of final semester alone, so that he/she
gets a chance to complete the programme.
The candidates who have failed in the courses Professional Skill Training I/II and
Comprehensive Test/Viva shall be permitted to take up supplementary examinations.

[Link] Artificial Intelligence and Data Science - R2020 Page 21

 Kongu Engineering College, Perundurai, Erode – 638060, India

15. AWARD OF LETTER GRADES

Range of % of Total Marks Letter Grade Grade Point
91 to 100 O (Outstanding) 10
81 to 90 A+ (Excellent) 9
71 to 80 A (Very Good) 8
61 to 70 B+ (Good) 7
50 to 60 B (Average) 6
Less than 50 RA (Reappear) 0
Satisfactory SF 0
Withdrawal W -
Absent AB -
Shortage of Attendance in a SA -
course
The Grade Point Average (GPA) is calculated using the formula:
course credits  grade points  for all courses in the specific semester
GPA =
course credits  for all courses in the specific semester
The Cumulative Grade Point Average (CGPA) is calculated from first semester (third semester
for lateral entry candidates) to final semester using the formula
course credits  grade points  for all courses in all the semesters so far
CGPA=
course credits  for all courses in all the semesters so far
The GPA and CGPA are computed only for the candidates with a pass in all the courses.
The GPA and CGPA indicate the academic performance of a candidate at the end of a semester
and at the end of successive semesters respectively.
A grade sheet for each semester shall be issued containing Grade obtained in each course, GPA
and CGPA.
A duplicate copy, if required can be obtained on payment of a prescribed fee and satisfying
other procedure requirements.
Withholding of Grades: The grades of a candidate may be withheld if he/she has not cleared
his/her dues or if there is a disciplinary case pending against him/her or for any other reason.

16. ELIGIBILITY FOR THE AWARD OF DEGREE

A candidate shall be declared to be eligible for the award of the BE / BTech Degree provided
the candidate has
i. Successfully completed all the courses under the different categories, as specified in the
regulations.
ii. Successfully gained the required number of total credits as specified in the curriculum
corresponding to the candidate’s programme within the stipulated time (vide clause 5).
iii. Successfully passed any additional courses prescribed by the respective Board of Studies
whenever readmitted under regulations other than R-2020 (vide clause 11.3)
iv. No disciplinary action pending against him / her.
17. CLASSIFICATION OF THE DEGREE AWARDED

[Link] Artificial Intelligence and Data Science - R2020 Page 22

 Kongu Engineering College, Perundurai, Erode – 638060, India
17.1 First Class with Distinction:
17.1.1 A candidate who qualifies for the award of the degree (vide clause 16) and
who satisfies the following conditions shall be declared to have passed
the examination in First class with Distinction:
 Should have passed the examination in all the courses of all the eight
semesters (six semesters for lateral entry candidates) in the First
Appearance within eight consecutive semesters (six consecutive
semesters for lateral entry candidates) excluding the authorized break of
study (vide clause 11) after the commencement of his / her study.
 Withdrawal from examination (vide clause 10) shall not be
considered as an appearance.
 Should have secured a CGPA of not less than 8.50
(OR)

17.1.2 A candidate who joins from other institutions on transfer and who gets
readmitted and has to move from one regulations to another regulations and
who qualifies for the award of the degree (vide clause 16) and satisfies the
following conditions shall be declared to have passed the examination
in First class with Distinction:
 Should have passed the examination in all the courses of all the
eight semesters (six semesters for lateral entry candidates) in the
First Appearance within eight consecutive semesters (six consecutive
semesters for lateral entry candidates) excluding the authorized break
of study (vide clause 11) after the commencement of his / her
study.
 Submission of equivalent course list approved by the respective
Board of studies.
 Withdrawal from examination (vide clause 10) shall not be
considered as an appearance.
 Should have secured a CGPA of not less than 9.00
17.2 First Class:
A candidate who qualifies for the award of the degree (vide clause 16) and who
satisfies the following conditions shall be declared to have passed the
examination in First class:

 Should have passed the examination in all the courses of all eight semesters (six
semesters for lateral entry candidates) within ten consecutive semesters (eight
consecutive semesters for lateral entry candidates) excluding authorized break of
study (vide clause 11) after the commencement of his / her study.
 Withdrawal from the examination (vide clause 10) shall not be considered as an
appearance.
 Should have secured a CGPA of not less than 7.00

[Link] Artificial Intelligence and Data Science - R2020 Page 23

 Kongu Engineering College, Perundurai, Erode – 638060, India

17.3 Second Class:

All other candidates (not covered in clauses 17.1 and 17.2) who qualify for the award
of the degree (vide clause 16) shall be declared to have passed the examination in
Second Class.

17.4 A candidate who is absent for end semester examination in a course / project work after
having registered for the same shall be considered to have appeared for that examination
for the purpose of classification.

17.5 Honours Degree:

A candidate who qualifies for the award of the degree (vide clause 16) and who
satisfies the following conditions shall be declared to have earned the BE/BTech
degree with Honours (vide clause 16 and clause 4.2.2):
 Should have passed the examination in all the courses of all the eight
semesters (six semesters for lateral entry candidates) in the First Appearance
within eight consecutive semesters (six consecutive semesters for lateral entry
candidates) excluding the authorized break of study (vide clause 11) after the
commencement of his / her study.
 Withdrawal from examination (vide clause 10) shall not be considered as an
appearance.
 Should have secured a CGPA of not less than 8.00

18. MALPRACTICES IN TESTS AND EXAMINATIONS

If a candidate indulges in malpractice in any of the tests or end semester examinations, he/she
shall be liable for punitive action as per the examination rules prescribed by the college from
time to time.

19. AMENDMENTS
Notwithstanding anything contained in this manual, the Kongu Engineering College through the
Academic council of the Kongu Engineering College, reserves the right to modify/amend
without notice, the Regulations, Curricula, Syllabi, Scheme of Examinations, procedures,
requirements, and rules pertaining to its BE / BTech programme.
******

[Link] Artificial Intelligence and Data Science - R2020 Page 24

 Kongu Engineering College, Perundurai, Erode – 638060, India

CURRICULUM BREAKDOWN STRUCTURE

Summary of Credit Distribution

Total Curriculum Content
Semester number of (% of total number of
Category credits credits of the program)
I II III IV V VI VII VIII

HS 3 4 3 3 13
7.69
BS 11 5 3 19
11.24
ES 4 9 4 4 21
12.43
PC 4 4 14 14 15 11 4 66
39.05
PE 3 12 3 18
10.65
OE 4 4 3 3 11
8.28
EC 2 6 3 7 18
10.65
Semesterwise
22 22 24 22 24 20 22 13 169 100.00
Total

Category Abbreviation
Lecture hours per week L
Tutorial hours per week T
Practical, Project work, Internship, Professional Skill Training, Industrial Training hours per week P
Credits C

CATEGORISATION OF COURSES
HUMANITIES AND SOCIAL SCIENCE INCLUDING MANAGEMENT (HS)
S. Course
Course Name L T P C Sem
No. Code

1. 20EGT11 English Language Skills 1 3 0 0 3 I

2. Advanced Communication Skills 3 0 0 3 II

Yoga and Values for Holistic
3. 1 0 1 1 II
Development
English for Workplace Communication
4. 0 0 2 1 III
Laboratory
5 Universal Human Values 2 0 0 2 III
Engineering Economics and
6 3 0 0 3 VII
Management
Total Credits to be earned 13

[Link] Artificial Intelligence and Data Science - R2020 Page 25

 Kongu Engineering College, Perundurai, Erode – 638060, India

BASIC SCIENCE (BS)

S. Course
Course Name L T P C Sem
No. Code

1. 20MAC11 Matrices and Differential Equation 3 1* 2* 4 I

2. 20PHT11 Applied Physics 3 0 0 3 I

3. 20CYT11 Applied Chemistry 3 0 0 3 I

4. 20PHL11 Physical Sciences Laboratory 0 0 2 1 I

5. Discrete Mathematics and Linear Algebra 3 1 0 4 II

6. Open Source Laboratory 0 0 2 1 II

Probability Theory and Inferential
7. 3 0 0 3 III
Statistics
Total Credits to be earned 19

ENGINEERING SCIENCE (ES)

S. Course
Course Name L T P C Sem
No. Code
Basic of Electrical and Electronic
1. 20ADC11 3 0 2 4 I
Engineering
2. Digital Principles and Design 3 0 2 4 II

3. Engineering Practices Laboratory 0 0 2 1 II

4. Python Programming 3 0 2 4 II
Foundation of Artificial Intelligence and
5 3 0 2 4 III
Data Science
6 Web Technology 3 0 0 3 IV

7 Web Technology Laboratory 0 0 2 1 IV

Total Credits to be earned 21

PROFESSIONAL CORE (PC)

S. Course Domain/
Course Name L T P C Sem
No. Code Stream

1. 20ADT11 Problem Solving and Programming 3 0 0 3 I SD

Problem Solving and Programming
2. 20ADL11 0 0 2 1 I SD
Laboratory
3. Data Structures 3 0 0 3 II SD

4. Data Structures Laboratory 0 0 2 1 II SD

5. Design and Analysis of Algorithms 3 0 2 4 III SD

6. Computer Organization 3 0 0 3 III AP

7. Database Management System 3 0 0 3 III AP

[Link] Artificial Intelligence and Data Science - R2020 Page 26

 Kongu Engineering College, Perundurai, Erode – 638060, India
8. Data Analysis 2 0 2 3 III AI
Database Management System
9. 0 0 2 1 III SD
Laboratory
10. Optimization Techniques 3 1 0 4 IV AI

11. Object Oriented Programming 2 0 2 3 IV SD

12. Operating Systems 3 0 0 3 IV AP

13. Applied Machine Learning 3 0 0 3 IV AI

14. Applied Machine Learning Laboratory 0 0 2 1 IV AI

15. Artificial Intelligence 3 0 0 3 V AI

16. Deep Learning 3 0 0 3 V AI

17. Data Modeling and Business Intelligence 3 0 2 4 V AI

18. Big Data Analytics 3 0 2 4 V AI

19. Deep Learning Laboratory 0 0 2 1 V AI

20. Artificial Intelligence and Robotics 3 0 0 3 VI AI

21. Text and Speech Analytics 2 0 2 3 VI AI

22. Regression Analysis 3 1 0 4 VI AI

Artificial Intelligence and Robotics
23. 0 0 2 1 VI AI
Laboratory
24. Image and Video Analytics 3 0 2 4 VII AI
Total Credits to be earned 66

PROFESSIONAL ELECTIVE (PE)

S. Course Domain/
Course Name L T P C Sem
No. Code Stream
Elective 1
Theory of Computation
1. 3 0 0 3 V SD
Multi-core Architecture
2. 3 0 0 3 V AI
Design Patterns and Principles
3. 2 0 2 3 V SD
Computer Networks
4. 3 0 0 3 V NS
Elective 2
5 Wireless and Sensor Networks 3 0 0 3 VII NS

6. Cloud Computing 2 0 2 3 VII NS

7. Nature Inspired Optimization Techniques 3 0 0 3 VII AI

8. Modeling and Simulation 3 0 0 3 VII AI

Elective 3

[Link] Artificial Intelligence and Data Science - R2020 Page 27

 Kongu Engineering College, Perundurai, Erode – 638060, India
9. Information Security 3 0 0 3 VII NS

10. Information Retrieval Techniques 3 0 0 3 VII AI

11. Reinforcement Learning 3 0 0 3 VII AI

12. Healthcare Analytics 3 0 0 3 VII AI

Elective 4

13. Time Series Analysis and Forecasting 3 0 0 3 VII AI

14. Social Media Analytics 3 0 0 3 VII AI

15. Real Time Analytics 3 0 0 3 VII AI

16. Ethics of Artificial Intelligence 3 0 0 3 VII AI

Elective 5

17. Neural Machine Translation 3 0 0 3 VII AI

18. Multivariate Data Analysis 3 0 0 3 VII AI

19. Cognitive Science and Analytics 3 0 0 3 VII AI

20. Graph Theory and its Applications 3 0 0 3 VII AI

Elective 6

21. Software Defined Networks 3 0 0 3 VIII NS

22. Software Quality and Testing 3 0 0 3 VIII SDE

23. Software Project Management 3 0 0 3 VIII SDE

24. Cyber Forensics 3 0 0 3 VIII NS

Agile Methodologies for Software
3 0 0 3 VIII SDE
Development
Total Credits to be earned 18
EMPLOYABILITY ENHANCEMENT COURSES (EC)
S. Course Domain/
Course Name L T P C Sem
No. Code Stream
Professional Skills Training 1 / Industrial
1. - - - 2 V --
Training 1
2. Comprehensive Test and Viva - - - 2 VI --
Professional Skills Training 2 / Industrial
3. - - - 2 VI --
Training 2
4. Project Work 1 - - 4 2 VI --

5. Project Work 2 Phase 1 - - 6 3 VII --

6. Internship / Project Work 2 Phase 2 - - 14 7 VIII --

Total Credits to be earned 18

* AI – Artificial Intelligence, SD-Systems Development, SDE – Software Development and Engineering, NS- Networks and
Security, AP-

[Link] Artificial Intelligence and Data Science - R2020 Page 28

 Kongu Engineering College, Perundurai, Erode – 638060, India

EMPLOYABILITY ENHANCEMENT COURSES (EC)

S. Course Domain/
Course Name L T P C Sem
No. Code Stream
Professional Skills Training 1 / Industrial
1. - - - 2 V --
Training 1
2. Comprehensive Test and Viva - - - 2 VI --
Professional Skills Training 2 / Industrial
3. - - - 2 VI --
Training 2
4. Project Work 1 - - 4 2 VI --

5. Project Work 2 Phase 1 - - 6 3 VII --

6. Internship / Project Work 2 Phase 2 - - 14 7 VIII --

Total Credits to be earned 18

MANDATORY COURSES
S. Course
Course Name L T P C Sem
No. Code
1
20MNT11 Induction Training Program - - - 0 I
2.
Environmental Science 2 0 0 0 IV

OPEN ELECTIVE COURSES OFFERED TO OTHER DEPARTMENTS (OE)

S. Course
Course Name L T P C Sem
No. Code
Deep Learning for Engineering Applications
1. 3 0 2 4 IV
Computer Vision
2. 3 0 2 4 V
Artificial Intelligence for Data Science
3. 3 0 0 3 VI
Business Analytics
4. 3 0 0 3 VIII

Total Credits to be earned 14

[Link] Artificial Intelligence and Data Science - R2020 Page 29

 Kongu Engineering College, Perundurai, Erode – 638060, India

ADDITIONAL COURSES FOR [Link] HONORS:

Eligibility norms for registering Honors degree:

 A candidate shall have not less than 8.0 CGPA and no history of arrears till third semester to opt for the honors degree.
List of Additional Courses to be registered for BTech Honors:

Specialization: Internet of Things

Hours / Week
S. No. Course Name Credit
L T P
1 Introduction to IOT 3 0 0 3

2 IOT Architecture and its Protocols 3 0 0 3

3 Cognitive IoT 3 0 0 3

4 Industrial and Medical IOT 3 0 0 3

5 IOT and Machine learning 3 0 0 3

6 Privacy and security in IOT 3 0 0 3

Total Credits 18

Specialization: Blockchain Technology

Hours / Week
S. No. Course Name Credit
L T P
1 Introduction to Blockchain 3 0 0 3

2 Cryptography 3 0 0 3

3 Bitcoin Technology 3 0 0 3

4 Blockchain and Cryptocurrency Technologies 3 0 0 3

Blockchain application development through smart
5 3 0 0 3
contracts
6 Practical Aspects of Blockchain 3 0 0 3

Total Credits 18

[Link] Artificial Intelligence and Data Science - R2020 Page 30

 Kongu Engineering College, Perundurai, Erode – 638060, India
KEC R2020: SCHEDULING OF COURSES – [Link](ARTIFICIAL INTELLIGENCE AND DATA SCIENCE)
Total Credits: 169
Sem.
Course1 Course2 Course3 Course4 Course5 Course6 Course7 Course8 Course9 Course10 Credits

Basics of Problem
Matrices and Problem Physical Induction
English Applied Applied Electrical and Solving and
Differential Solving and Sciences Training
I Language Physics(3-0-0- Chemistry(3-0- Electronics Programming 22
Equations (3- Programming( Laboratory I(0- Program (0-0-
Skills(3-0-0-3) 3) 0-3) Engineering Laboratory(0-
1*-2*-4) 3-0-0-3) 0-2-1) 0-0)
(3-0-2-4) 0-2-1)
Discrete
Advance Digital Engineering Yoga Values
Mathematics Data Python Data Structures Open Source
Communicatio Principles and Practices for Holistic
II and Linear Structures(3-0- Programming Laboratory(0- Laboratory(0- 22
n Skills(3-0-0- Design (3-0-2- Laboratory(0- Development(1
Algebra(3-1-0- 0-3) (3-0-2-4) 0-2-1) 0-2-1)
3) 4) 0-2-1) -0-1-1)
4)
Foundations of English for
Probability Database
Artificial Design and Database Workplace Universal
Theory And Computer Management
Intelligence Analysis of Management Data Analysis Communicatio Human
III Inferential Organization System 24
and Data Algorithms(3- System(3-0-0- (2-0-2-3) n Values(2-0-0-
Statistics (3-0- (3-0-0-3) Laboratory(0-
Science(3-0-2- 0-2-4) 3) Laboratory(0- 2)
0-3) 0-2-1)
4) 0-2-1)
Applied
Object Applied Web
Optimization Web Operating Machine Environmental
Oriented Machine Open Elective Technology
IV Techniques(3- Technology(3- Systems(3-0-0- Learning Science(2-0-0- 22
Programming( Learning(3-0- - I(3-1/0-0/2-4) Laboratory(0-
1-0-4) 0-0-3) 3) Laboratory(0- 0)
2-0-2-3) 0-3) 0-2-1)
0-2-1)

Data Modeling
Artificial Deep Big Data Professional Open Elective Deep Learning Professional
and Business
V Intelligence(3- Learning(3-0- Analytics (3- Elective -1(3- – 2(3-1/0-0/2- Laboratory(0- Skills Training 24
intelligence (3-
0-0-3) 0-3) 0-2-4) 0-0-3) 4) 0-2-1) 1 (0-0-0-2)
0-2-4)

Artificial Professional
Artificial Text and
Regression Open Elective Intelligence Comprehensiv Skills Training
Intelligence Speech Project Work 1
VI Analysis (3-1- - 3(2/3-0-0/2- and Robotics e Test / 2/ Industrial 20
and Robotics Analytics(2-0- (0-0-4-2)
0-4) 3) Laboratory(0- Viva(0-0-0-2) Training 2 /(0-
(3-0-0-3) 2-3)
0-2-1) 0-0-2)

Engineering Image and

Professional Professional Professional Professional Project Work 2
Economics & Video
VII Elective – 2(3- Elective – 3(3- Elective – 4(3- Elective – 5(3- Phase I(0-0-6- 22
Management(3 Analytics(3-0-
0-0-3) 0-0-3) 0-0-3) 0-0-3) 3)
-0-0-3) 2-4)

Internship /
Professional Open Elective
Project work 2
VIII Elective -6(3- – 4(2/3-0-0/2- 13
Phase 2(0-0-
0-0-3) 3)
14-7)

[Link] Artificial Intelligence and Data Science - R2020 Page 31

 Kongu Engineering College, Perundurai, Erode – 638060, India

MAPPING OF COURSES WITH PROGRAM OUTCOMES AND PROGRAM SPECIFIC OUTCOMES

Course
Sem. Course Title PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
Code
1 English Language Skills     
1 Matrices and Differential Equations     
1 Applied Physics   
1 Applied Chemistry    
1 Problem Solving and Programming      
1 Basics of Electrical and Electronics Engineering      
1 Problem Solving and Programming Laboratory        
1 Physical Sciences Laboratory I 
1 Induction Training Program #

2 Advance Communication Skills     

2 Discrete Mathematics and Linear Algebra     
2 Digital Principles and Design           
2 Data Structures     
2 Python Programming       
2 Data Structures Laboratory        
2 Open Source Laboratory       
2 Engineering Practices Laboratory         
2 Yoga Values for Holistic Development    
3 Probability Theory And Inferential Statistics     
Foundations of Artificial Intelligence and Data
3
Science
      
3 Design and Analysis of Algorithms       
3 Computer Organization     
3 Database Management System      
3 Data Analysis       
3 Database Management System Laboratory         
[Link] Artificial Intelligence and Data Science - R2020 Page 32
 Kongu Course
Sem. Engineering College, Perundurai,Course
Erode –Title
638060, India PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
Code
3 English for Workplace Communication Laboratory   
3 Universal Human Values  
4 Optimization Techniques     
4 Web Technology       
4 Object Oriented Programming       
4 Operating Systems     
4 Applied Machine Learning     
4 Web Technology Laboratory       
4 Applied Machine Learning Laboratory       
4 Environmental Science    
5 Artificial Intelligence     
5 Deep Learning     
5 Data Modeling and Business intelligence       
5 Big Data Analytics       
5 Deep Learning Laboratory       
Professional Skills Training 1 /
5
Industrial Training 1 *$
6 Artificial Intelligence and Robotics     
6 Text and Speech Analytics       
6 Regression Analysis     
6 Artificial Intelligence and Robotics Laboratory       
6 Comprehensive Test / Viva
Professional Skills Training 2 /
6
Industrial Training 2 @
6 Project Work 1

7 Engineering Economics & Management            

7 Image and Video Analytics       
7 Project Work 2 Phase I

8 Internship / Project work 2 Phase 2

[Link] Artificial Intelligence and Data Science - R2020 Page 33

 Kongu Engineering College, Perundurai, Erode – 638060, India
Course
Sem. Course Title PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
Code
Professional Elective Courses

5 Theory of Computation     
5 Multi-core Architecture     
5 Design Patterns and Principles       
5 Computer Networks      
7 Wireless and Sensor Networks      
7 Cloud Computing       
7 Nature Inspired Optimization Techniques     
7 Modeling and Simulation     
7 Information Security     
7 Information Retrieval Techniques     
7 Reinforcement Learning      
7 Healthcare Analytics     
7 Time Series Analysis and Forecasting       
7 Social Media Analytics     
7 Real Time Analytics      
7 Ethics of Artificial Intelligence       
7 Neural Machine Translation     
7 Multivariate Data Analysis     
7 Cognitive Science and Analytics     
7 Graph Theory and its Applications     
8 Software Defined Networks      
8 Software Quality and Testing     
8 Software Project Management     
8 Cyber Forensics     
8 Agile Methodologies for Software Development        

[Link] Artificial Intelligence and Data Science - R2020 Page 34

 Kongu Engineering College, Perundurai, Erode – 638060, India

Course
Sem. Course Title PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
Code
Open Elective Courses
Deep Learning for Engineering Applications
4     
5 Computer Vision     
6 Artificial Intelligence for Data Science   
8 Business Analytics   

Honours Degree

IOT

Introduction to IOT      
IOT Architecture and its Protocols      
Cognitive IoT      
Industrial and Medical IOT      
IOT and Machine learning      
Privacy and Security in IOT     
BLOCK CHAIN

Introduction to Blockchain     
Cryptography     
Bitcoin Technology     
Blockchain and Cryptocurrency Technologies     
Blockchain application development through smart
contracts
    
Practical Aspects of Blockchain       

[Link] Artificial Intelligence and Data Science - R2020 Page 35

 Kongu Engineering College, Perundurai, Erode – 638060, India

[Link]. ARTIFICIAL INTELLIGENCE AND DATA SCIENCE CURRICULUM – R2020

SEMESTER – I

Course Hours / Week Maximum Marks Cate

Course Title Credit
Code L T P CA ESE Total gory

Theory/Theory with Practical

20EGT11 English Language Skills 3 0 0 3 50 50 100 HS

20MAC11 Matrices and Differential Equations 3 1* 2* 4 50 50 100 BS

20PHT11 Applied Physics 3 0 0 3 50 50 100 BS

20CYT11 Applied Chemistry 3 0 0 3 50 50 100 BS

20ADT11 Problem Solving and Programming 3 0 0 3 50 50 100 PC

20ADC11 Basics of Electrical and Electronics Engineering 3 0 2 4 50 50 100 ES

Practical / Employability Enhancement

20ADL11 Problem Solving and Programming Laboratory 0 0 2 1 50 50 100 PC

20PHL11 Physical Sciences Laboratory I 0 0 2 1 50 50 100 BS

20MNT11 Student Induction Program # --- --- --- 0 100 0 100 MC

Total Credits to be earned 22

*# Induction Training Program (including, Indian Constitution and Essence of Indian Knowledge Tradition, etc.) to
be conducted at the beginning of the semester for 3 weeks.

SEMESTER – II

Course Hours / Week Maximum Marks Cate

Course Title Credit
Code L T P CA ESE Total gory

Theory/Theory with Practical

20EGT21 Advanced Communication Skills 3 0 0 3 50 50 100 HS

20MAT21 Discrete Mathematics and Linear Algebra 3 1 0 4 50 50 100 BS

20ADC21 Digital Principles and Design 3 0 2 4 50 50 100 ES

20ADT21 Data Structures 3 0 0 3 50 50 100 PC

20ADC22 Python Programming 3 0 2 4 50 50 100 ES

Practical / Employability Enhancement

20ADL21 Data Structures Laboratory 0 0 2 1 50 50 100 PC

20ADL22 Open Source Laboratory 0 0 2 1 50 50 100 BS

20MEL11 Engineering Practices Laboratory 0 0 2 1 50 50 100 ES

20VEC11 Yoga and Values for Holistic Development 1 0 1 1 100 0 100 HS

Total Credits to be earned 22

[Link] Artificial Intelligence and Data Science - R2020 Page 36

 Kongu Engineering College, Perundurai, Erode – 638060, India
[Link]. ARTIFICIAL INTELLIGENCE AND DATA SCIENCE CURRICULUM – R2020

SEMESTER – III

Course Hours / Week Maximum Marks Cate

Course Title Credit
Code L T P CA ESE Total gory

Theory/Theory with Practical

20MAT35 Probability Theory And Inferential Statistics 3 0 0 3 50 50 100 BS

20ADC31 Foundations of Artificial Intelligence and Data Science 3 0 2 4 50 50 100 ES

20ADC32 Design and Analysis of Algorithms 3 0 2 4 50 50 100 PC

20ADT31 Computer Organization 3 0 0 3 50 50 100 PC

20ADT32 Database Management Systems 3 0 0 3 50 50 100 PC

20ADC33 Data Analysis 2 0 2 3 50 50 100 PC

Practical / Employability Enhancement

20ADL31 Database Management Systems Laboratory 0 0 2 1 50 50 100 PC

20EGL31 English for Workplace Communication Laboratory 0 0 2 1 50 50 100 HS

20GET31 Universal Human Values 2 0 0 2 100 0 100 HS

Total Credits to be earned 24

SEMESTER – IV

Course Hours / Week Maximum Marks Cate

Course Title Credit
Code L T P CA ESE Total gory

Theory/Theory with Practical

20ADT41 Optimization Techniques 3 1 0 4 50 50 100 PC

20ADT42 Web Technology 3 0 0 3 50 50 100 ES

20ADC41 Object Oriented Programming 2 0 2 3 50 50 100 PC

20ADT43 Operating Systems 3 0 0 3 50 50 100 PC

20ADT44 Applied Machine Learning 3 0 0 3 50 50 100 PC

Open Elective - I 3 1/0 0/2 4 50 50 100 OE

Practical / Employability Enhancement

20ADL41 Web Technology Laboratory 0 0 2 1 50 50 100 ES

20ADL42 Applied Machine Learning Laboratory 0 0 2 1 50 50 100 PC

20MNT31 Environmental Science 2 0 0 0 100 0 100 MC

Total Credits to be earned 22

[Link] Artificial Intelligence and Data Science - R2020 Page 37

 Kongu Engineering College, Perundurai, Erode – 638060, India
[Link]. ARTIFICIAL INTELLIGENCE AND DATA SCIENCE CURRICULUM – R2020

SEMESTER – V

Course Hours / Week Maximum Marks Cate

Course Title Credit
Code L T P CA ESE Total gory

Theory/Theory with Practical

20ADT51 Artificial Intelligence 3 0 0 3 50 50 100 PC

20ADT52 Deep Learning 3 0 0 3 50 50 100 PC

20ADC51 Data Modeling and Business intelligence 3 0 2 4 50 50 100 PC

20ADC52 Big Data Analytics 3 0 2 4 50 50 100 PC

Professional Elective -1 3 0 0 3 50 50 100 PE

Open Elective – 2 3 1/0 0/2 4 50 50 100 OE

Practical / Employability Enhancement

20ADL51 Deep Learning Laboratory 0 0 2 1 50 50 100 PC

Professional Skills Training 1 /
20GEL51 -- -- -- 2 100 0 100 EC
Industrial Training 1 *$
Total Credits to be earned 24
$ Professional Skills Training / Industrial Training for a total period of about 80 hr during the period of
4thsem end summer holidays and 5th sem.

SEMESTER – VI

Course Hours / Week Maximum Marks Cate

Course Title Credit
Code L T P CA ESE Total gory

Theory/Theory with Practical

20ADT61 Artificial Intelligence and Robotics 3 0 0 3 50 50 100 PC

20ADC61 Text and Speech Analytics 2 0 2 3 50 50 100 PC

20ADT62 Regression Analysis 3 1 0 4 50 50 100 PC

Open Elective - 3 2/3 0 0/2 3 50 50 100 OE

Practical / Employability Enhancement

20ADL61 Artificial Intelligence and Robotics Laboratory 0 0 2 1 50 50 100 PC

20GEP61 Comprehensive Test / Viva --- --- --- 2 100 0 100 EC

Professional Skills Training 2 /
20GEL61 --- --- --- 2 100 0 100 EC
Industrial Training 2 @
20ADP61 Project Work 1 0 0 4 2 100 0 100 EC

Total Credits to be earned 20

@ Professional Skills Training / Industrial Training for a total period of about 80 hr during 5 thsem end summer
holidays and 6thsem.

[Link] Artificial Intelligence and Data Science - R2020 Page 38

 Kongu Engineering College, Perundurai, Erode – 638060, India
[Link]. ARTIFICIAL INTELLIGENCE AND DATA SCIENCE CURRICULUM – R2020

SEMESTER – VII

Course Hours / Week Maximum Marks Cate

Course Title Credit
Code L T P CA ESE Total gory

Theory/Theory with Practical

20MBT71 Engineering Economics and Management 3 0 0 3 50 50 100 HS

20ADC71 Image and Video Analytics 3 0 2 4 50 50 100 PC

Professional Elective – 2 3 0 0 3 50 50 100 PE

Professional Elective – 3 3 0 0 3 50 50 100 PE

Professional Elective – 4 3 0 0 3 50 50 100 PE

Professional Elective – 5 3 0 0 3 50 50 100 PE

Practical / Employability Enhancement

20ADP71 Project Work 2 Phase I 0 0 6 3 50 50 100 EC

Total Credits to be earned 22

SEMESTER – VIII

Course Hours / Week Maximum Marks Cate

Course Title Credit
Code L T P CA ESE Total gory

Theory/Theory with Practical

Professional Elective -6 3 0 0 3 50 50 100 PE

Open Elective – 4 2/3 0 0/2 3 50 50 100 OE

Practical / Employability Enhancement

20ADP81 Internship / Project work 2 Phase 2 $ --- --- 14 7 50 50 100 EC

Total Credits to be earned 13

$ Mandatory for all students

[Link] Artificial Intelligence and Data Science - R2020 Page 39

 Kongu Engineering College, Perundurai, Erode – 638060, India

PROFESSIONAL ELECTIVE (PE)

S. Course Domain/
Course Name L T P C Sem
No. Code Stream
Elective 1

1. 20ADE01 Theory of Computation 3 0 0 3 V SD

2. 20ADE02 Multi-core Architecture 3 0 0 3 V AI

3. 20ADE03 Design Patterns and Principles 2 0 2 3 V SD

4. 20ADE04 Computer Networks 3 0 0 3 V NS

Elective 2

5. 20ADE05 Wireless and Sensor Networks 3 0 0 3 VII NS

6. 20ADE06 Cloud Computing 2 0 2 3 VII NS

7. 20ADE07 Nature Inspired Optimization Techniques 3 0 0 3 VII AI

8. 20ADE08 Modeling and Simulation 3 0 0 3 VII AI

Elective 3

9. 20ADE09 Information Security 3 0 0 3 VII NS

10. 20ADE10 Information Retrieval Techniques 3 0 0 3 VII AI

11. 20ADE11 Reinforcement Learning 3 0 0 3 VII AI

12. 20ADE12 Healthcare Analytics 3 0 0 3 VII AI

Elective 4

13. 20ADE13 Time Series Analysis and Forecasting 3 0 0 3 VII AI

14. 20ADE14 Social Media Analytics 3 0 0 3 VII AI

15. 20ADE15 Real Time Analytics 3 0 0 3 VII AI

16. 20ADE16 Ethics of Artificial Intelligence 3 0 0 3 VII AI

Elective 5

17. 20ADE17 Neural Machine Translation 3 0 0 3 VII AI

18. 20ADE18 Multivariate Data Analysis 3 0 0 3 VII AI

19. 20ADE19 Cognitive Science and Analytics 3 0 0 3 VII AI

20. 20ADE20 Graph Theory and its Applications 3 0 0 3 VII AI

Elective 6

21. 20ADE21 Software Defined Networks 3 0 0 3 VIII NS

22. 20ADE22 Software Quality and Testing 3 0 0 3 VIII SDE

23. 20ADE23 Software Project Management 3 0 0 3 VIII SDE

24. 20ADE24 Cyber Forensics 3 0 0 3 VIII NS

Agile Methodologies for Software
25. 20ADE25 3 0 0 3 VIII SDE
Development
Total Credits to be earned 18

[Link] Artificial Intelligence and Data Science - R2020 Page 40

 Kongu Engineering College, Perundurai, Erode – 638060, India
OPEN ELECTIVE COURSES OFFERED TO OTHER DEPARTMENTS (OE)
(Common to all departments except offering department)

Course
S. No. Course Name L T P C Sem
Code
1 20ADO01 Deep Learning for Engineering Applications 3 0 2 4 IV

2 20ADO02 Computer Vision 3 0 2 4 V

3 20ADO03 Artificial Intelligence for Data Science 3 0 0 3 VI

4 20ADO04 Business Analytics 3 0 0 3 VIII

[Link] Artificial Intelligence and Data Science - R2020 Page 41

 Kongu Engineering College, Perundurai, Erode – 638060, India

SEMESTER I
20EGT11 ENGLISH LANGUAGE SKILLS
(Common to all Engineering and Technology Branches)

Programme &
All BE/BTech branches Sem. Category L T P Credit
Branch
Prerequisites Nil 1 HS 3 0 0 3

Preamble This course is designed to impart required levels of fluency in using the English Language at A2/B1 Level in the
Common European Framework (CEFR).
Listening, Speaking, Reading, Writing and Grammar & Vocabulary. Activity Based Learning –
Unit - I 9
Phase – I
Listening - Talking about past experiences - listening to descriptions - Speaking - Exchanging personal information - Talking
about cities and transportation - Reading - Life and achievements of a famous personality - Global transport systems - Writing
- Childhood experiences - Process Description – Grammar & Vocabulary – Past tense – Expressions of quantity – Indirect
questions.
Listening, Speaking, Reading, Writing and Grammar & Vocabulary. Activity Based Learning –
Unit - II 9
Phase – II
Listening - Information about hotels and accommodation - Recipes and food items - Speaking - Life style changes and making
comparisons - Talking about food - Reading - Habit formation and changing habits - International cuisine - Writing - Personal
email - emails about food and recipes – Grammar & Vocabulary – Evaluations and Comparisons with adjectives – Simple past
and present perfect tenses.
Listening, Speaking, Reading, Writing and Grammar & Vocabulary. Activity Based Learning –
Unit - III 9
Phase – III
Listening - Information about travel - descriptions / conversations about family life - Speaking - Vacations and Holidays -
Requests, complaints and offering explanations - Reading - Tourist places and travel experiences - Group behaviour and
politeness - Writing - Personal letter about travelling - Writing guidelines and checklists – Grammar & Vocabulary – Future
tense – Modals – Two-part verbs.
Unit - IV Listening, Speaking, Reading, Writing and Grammar & Vocabulary. Activity Based Learning –
9
Phase – IV
Listening - Descriptions about festivals - Presentations on technology - Speaking - About technology - festivals, special events
and traditions - Reading - Sports, hobbies and past time - About different cultures - Writing - Product Description - Writing web
content – Grammar & Vocabulary – Infinitives and Gerunds for uses and purposes – Imperatives for giving suggestions –
Relative clauses of time.
Listening, Speaking, Reading, Writing and Grammar & Vocabulary. Activity Based Learning –
Unit - V 9
Phase – V
Listening - Talking about changes - Job preferences - Speaking - Comparing different periods or phases in life – Changes that
happen - Skills and abilities, Personality Development - Employability Skills – Reading - Reading about life experiences -
Emotions and feelings – Job preferences – Jobs and Personality – Writing - Writing about one’s past, present and future –
Researching job options – Choosing the right job – Grammar & Vocabulary – Time contrasts – Conditional sentences with “if
clauses” – Gerunds – short responses.

Lecture: 45, Total: 45

TEXT BOOK:
1. Jack C. Richards, Jonathan Hull, and Susan Proctor, “Interchange - Student’s Book 2”, 4th Edition, Cambridge University
Press, New York, 2017. for Unit I, II, III, IV and V.

REFERENCES:
1. Sanjay Kumar and Pushp Lata, “Communication Skills”, 2 nd Edition, Oxford University Press, New Delhi, 2015.
2. Pamela Hartmann and Brenda Wegmann, “New Interactions English Language Learning and Assessment Platform
(Level Intro - Level IV )”, McGraw Hill India, 2020.

[Link] Artificial Intelligence and Data Science - R2020 Page 42

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 use language effectively and accurately acquiring vocabulary from real-life context Applying (K3)
CO2 listen/view and comprehend different spoken discourses / excerpts in different accents Applying (K3)
CO3 read different genres of texts adopting various reading strategies Analyzing (K4)
CO4 write cohesively, coherently and flawlessly avoiding grammatical errors, using a wide range of Creating (K6)
vocabulary, organizing their ideas logically on a topic
CO5 speak clearly, confidently, comprehensibly and communicate with others using appropriate Creating (K6)
communicative strategies

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 2 2 3 2 2
CO2 2 3 1
CO3 1 3 1 1
CO4 3 1
CO5 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 16 30 37 17 100
CAT2 17 30 37 16 100
CAT3 13 33 37 17 100
ESE 7 21 37 35 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 43

 Kongu Engineering College, Perundurai, Erode – 638060, India
20MAC11 - MATRICES AND DIFFERENTIAL EQUATIONS
(Common to All Engineering and Technology Branches)

Programme &
All BE/BTech branches Sem. Category L T P Credit
Branch
Prerequisites Nil 1 BS 3 1* 2* 4

Preamble To provide the skills to the students for solving different real time problems by applying matrices and differential
equations.
Unit - I Matrices: 9
Introduction – Characteristic equation – Eigen values and Eigen vectors of a real matrix – Properties of Eigen values and
Eigen vectors (without proof) – Cayley - Hamilton theorem (Statement and applications only) – Orthogonal matrices –
Orthogonal transformation of a symmetric matrix to diagonal form – Quadratic form – Nature of Quadratic forms - Reduction of
quadratic form to canonical form by orthogonal transformation.
Unit - II Ordinary Differential Equations: 9
Introduction – Solutions of First order differential equations: Exact differential equations – Leibnitz’s Linear Equation –
Bernoulli's equation – Clairaut's equation.
Unit - III Ordinary Differential Equations of Higher Order: 9
Linear differential equations of second and higher order with constant coefficients - Particular Integrals for the types: – eax
cosax / sinax – xn – eaxxn, eaxsinbx and eaxcosbx – xnsinax and xncosax – Differential Equations with variable coefficients:
Euler-Cauchy’s equation – Legendre’s equation.
Unit - IV Applications of Ordinary Differential Equations: 9
Method of variation of parameters – Simultaneous first order linear equations with constant coefficients – Applications of
differential equations: Simple harmonic motion – Electric circuits (Differential equations and associated conditions need to be
given).
Unit - V Laplace Transform & Inverse Laplace Transform: 9
Laplace Transform: Conditions for existence – Transform of elementary functions – Basic properties – Derivatives and
integrals of transforms – Transforms of derivatives and integrals – Transform of unit step function – Transform of periodic
functions. Inverse Laplace transform: Inverse Laplace transform of elementary functions – Partial fraction method –
Convolution theorem (Statement only) – Solution of linear ODE of second order with constant coefficients.
List of Exercises / Experiments:
1. Introduction to MATLAB
2. Computation of eigen values and eigen vectors
3. Plotting and visualizing single variable functions
4. Solving first and second order ordinary differential equations
5. Solution of Simultaneous first order ODEs
6. Solving second order ODE by variation of parameters
7. Determining Laplace and inverse Laplace transform of basic functions
8. Solution of Second order ODE by employing Laplace transforms
*Alternate week
Lecture: 45, Tutorial and Practical:15, Total:60
TEXT BOOK:
1. Ravish R. Singh, Mukul Bhatt “Engineering Mathematics”, 1 st Edition, McGraw Hill Education, New Delhi, 2016. for Unit I,
II, III, IV and V.

REFERENCES:
1. Kreyszig E., “Advanced Engineering Mathematics”, 10th Edition, John Wiley Sons, 2011.
2. Kandasamy P., Thilagavathy K. and Gunavathy K., “Engineering Mathematics For First Year B.E/[Link]”, Reprint Edition
2014, [Link] and Co., New Delhi.
3. Duraisamy C., Vengataasalam S., Arun Prakash K. and Suresh M., “Engineering Mathematics – I”, 2nd Edition, Pearson
India Education, New Delhi, 2020.
4. MATLAB Manual.

[Link] Artificial Intelligence and Data Science - R2020 Page 44

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 solve engineering problems which needs matrix computations. Applying (K3)
CO2 identify the appropriate method for solving first order ordinary differential equations. Applying (K3)
CO3 solve higher order linear differential equations with constant and variable coefficients. Applying (K3)
CO4 apply the concept of ordinary differential equations for modeling and finding solutions to Applying (K3)
engineering problems.
CO5 apply Laplace Transform to find solutions of Linear Ordinary Differential Equations Applying (K3)
CO6 know the basics of MATLAB and computing eigen values and eigen vectors of real matrix by Understanding (K2),
MATLAB. Manipulation (S2)
CO7 solve ordinary differential equations with constant and variable coefficients and simultaneous first Applying (K3),
order ordinary differential equations using MATLAB. Manipulation (S2)
CO8 compute Laplace and inverse Laplace Transform of basic functions and solve Second Order ODE Applying (K3),
by using Laplace Transform with MATLAB. Manipulation (S2)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 3 2 1
CO2 3 3 2 1
CO3 3 3 2 1
CO4 3 3 2
CO5 3 3 2 1
CO6 3
CO7 3
CO8 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 10 20 70 100
CAT2 10 20 70 100
CAT3 10 20 70 100
ESE 10 20 70 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 45

 Kongu Engineering College, Perundurai, Erode – 638060, India
20PHT11 - APPLIED PHYSICS
(Common to All Engineering and Technology Branches)

Programme &
All BE/BTech Branches Sem. Category L T P Credit
Branch
Prerequisites Nil 1 BS 3 0 0 3

Preamble This course aims to impart the essential concepts of propagation of elastic waves, acoustics, ultrasonics, laser
and fiber optics, quantum physics, crystal structure and crystal defects. It also describes the physical phenomena
related to the aforementioned concepts and their applications in engineering and provides motivation towards
innovations
Unit - I Propagation of Elastic Waves: 9
Oscillatory Motion: Introduction to simple harmonic motion - Damping velocity - Damping coefficient - Differential equation of
simple harmonic motion - Velocity and acceleration - Restoring force - Vibration of a spring and mass system - Frequency
response - Phase response - Resonance - Wave motion: Definition of a plane progressive wave - Attenuation of waves -
Differential equation of a plane progressive wave - Phase velocity - Phase and phase difference - Solution of the differential
equation of a plane progressive wave.
Unit - II Acoustics and Ultrasonics: 9
Acoustics: Introduction - Reverberation and reverberation time - Growth and decay of sound - Sabine’s formula for
reverberation time – Determination of sound absorption coefficient – Design of an auditorium: Factors affecting acoustics of
buildings and the remedies. Ultrasonics: Introduction – Properties of ultrasonic waves – Generation of ultrasonic waves:
Magnetostrictive generator and Piezoelectric generator - Determination of velocity of ultrasonics in a liquid: Acoustic grating –
Industrial application: Non-destructive testing - Other applications of ultrasonic waves (qualitative).
Unit - III Laser and Fiber Optics: 9
Laser and Applications: Introduction – Interaction of light with matter - Three quantum process: Stimulated absorption,
spontaneous emission and stimulated emission - Population inversion - Einstein’s coefficients and their relations - Pumping
methods - Nd:YAG laser - CO2 laser - Holography. Fiber Optics and Applications: Introduction - Numerical aperture and
acceptance angle - Classification of optical fibers based on refractive index, modes and materials - Fiber optics
communication system (qualitative) - Fiber optic sensors: Temperature and displacement sensors.
Unit - IV Quantum Physics: 9
Introduction - Blackbody radiation - Planck’s quantum hypothesis - Compton scattering (qualitative) - de Broglie’s hypothesis
- Properties of matter waves - Application of Heisenberg uncertainty principle - Schrodinger’s time independent and time
dependent wave equations - Physical significance of wave function - The free particle - Potential energy step - Infinite
potential well (one - dimensional).
Unit - V Crystal Physics: 9
Introduction - Classification of solids - Space lattice - Crystal structure - Unit cell - Bravais lattice - Single and polycrystalline
materials - Lattice planes - Miller indices - Indices of crystal direction - Interplanar spacing in cubic system - Hexagonal close
packed crystal structure and c/a ratio - Symmetry -Symmetry elements in cubic crystal - Crystal imperfections: line, surface
and volume imperfections - Features of crystal imperfections (qualitative).

Total: 45
TEXT BOOK:
1. Avadhanulu M.N., Kshirsagar P.G. and Arun Murthy T.V.S., “A Textbook of Engineering Physics”,11th Edition, S. Chand &
Company Pvt. Ltd., New Delhi, 2019. for Unit I, II, III, IV and V.

REFERENCES:
1. Purnima Khare and Swarup A.,”Engineering Physics: Fundamentals and Modern Applications”, 1st Edition, Jones and
Bartlett Publishers, Sudbury, Massachusetts, 2009.
2. Gaur R.K. and Gupta S.L., “Engineering Physics”, 8th Edition, Dhanpat Rai and Sons, New Delhi, 2009.
3. Tamilarasan K. and Prabu K., “Engineering Physics – I”, 3rd Edition, McGraw Hill Education Pvt. Ltd., New Delhi, 2014.

[Link] Artificial Intelligence and Data Science - R2020 Page 46

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 make use of the concepts of oscillatory and wave motion to comprehend the phenomena related Applying (K3)
to the propagation of elastic waves.
CO2 apply the concepts of growth and decay of sound energy in a hall to compute Sabine’s formula to Applying (K3)
recognize the requirements of acoustically good buildings, and to describe the production of
ultrasonic wave, working of acoustic grating & non-destructive testing using ultrasonic waves.
CO3 apply the concepts of stimulated emission to explain the working and the applications of laser in Applying (K3)
engineering and technology, and to apply the principle of propagation of light through optical fiber
to compute acceptance angle and numerical aperture to comprehend the loss in optical fiber, fiber
optic communication system and working of fiber optic sensors.
CO4 use the concepts of quantum mechanics to describe the behavior of electrons in a metal by Applying (K3)
solving Schrodinger’s wave equation for particle motion in infinite potential well.
CO5 utilize the concepts of the seven crystal systems to obtain interplanar spacing in cubic lattice and Applying (K3)
c/a ratio of HCP crystal structure, and to comprehend symmetry elements, reciprocal lattice and
the types of crystal imperfections and their impacts.

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1
CO2 3 2 1
CO3 3 2 1
CO4 3 2 1
CO5 3 2 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 40 40 100
CAT2 20 35 45 100
CAT3 25 35 40 100
ESE 20 40 40 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 47

 Kongu Engineering College, Perundurai, Erode – 638060, India
20CYT11 - APPLIED CHEMISTRY
(Common to All Engineering and Technology Branches)

Programme &
All BE/BTech Branches Sem. Category L T P Credit
Branch
Prerequisites Nil 1 BS 3 0 0 3

Preamble Applied Chemistry course explores the basic principles and advancements of chemistry in the field of engineering
and technology. It aims to impart the fundamentals of chemistry towards innovations in science and technology
and also for societal applications.
Unit - I Water Technology: 9
Introduction - sources of water - impurities in water - types of water - hardness of water- expression of hardness (simple
problems) - units of hardness –estimation of hardness of water by EDTA method – determination of alkalinity - disadvantages
of using hard water in Industries - boiler troubles - scale and sludge, boiler corrosion, caustic embrittlement, priming and
foaming - softening of water: i) Internal treatment process - carbonate and calgon conditioning ii) External treatment method -
demineralization process iii) Treatment of water for municipal water supply (Removal of suspended particles and disinfection
methods, Break-point of chlorination).
Unit - II Electrochemistry: 9
Introduction – electrochemical cells - applications of electrochemical series - reference electrode - standard calomel electrode
- ion selective electrode - glass electrode - concentration cells - electrode and electrolyte concentration cells (simple
problems) -applications- potentiometric titrations - acid-base, redox, precipitation titrations - advantages- conductometric
titrations - strong acid vs strong base, weak acid vs strong base, mixture of weak and strong acid vs strong base- advantages
of conductometric titrations.
Unit - III Corrosion and its Control: 9
Introduction – causes and effects of corrosion - types of corrosion - chemical corrosion – Pilling Bed-worth rule -
electrochemical corrosion –types - galvanic corrosion, concentration cell corrosion – other types of corrosion -stress,
intergranular and microbiological corrosion- galvanic series - factors influencing rate of corrosion – corrosion control methods
- design and material selection, anodic protection, corrosion inhibitors, protective coatings - i) metallic coatings : hot dipping
(tinning and galvanizing) ii) non-metallic coating : anodizing iii) organic coating : paints – constituents and their functions.
Unit - IV Fuels and Combustion: 9
Introduction – classification of fuels - characteristics of a good fuel - combustion - calorific values – gross and net calorific
values - Dulong‘s formula (simple problems) - Flue gas analysis by Orsat‘s method - ignition temperature - spontaneous
ignition temperature - explosive range - solid fuels - coal and its varieties – proximate and ultimate analysis – significance –
metallurgical coke - Otto-Hoffman byproduct method - liquid fuel - refining of petroleum – manufacture of synthetic petrol -
hydrogenation of coal - Bergius process - knocking - octane number – cetane number - gaseous fuel - water gas.
Unit - V Polymers: 9
Introduction – terminology - classification - polymerization - types of polymerization (definition only)- polymerisation
techniques- bulk, solution, suspension and emulsion polymerisation - plastics- difference between thermoplastics and
thermosetting plastics - compounding of plastics- plastic moulding methods - compression, injection, extrusion and blow
moulding methods - industrial polymers: preparation, properties and applications of PVC, PAN, polyurethane, polyesters –
biodegradable polymers-classification and applications.

Lecture: 45, Total: 45

TEXT BOOK:
1. Wiley Editorial Board, ”Wiley Engineering Chemistry”, 2 nd Edition, Wiley India Pvt. Ltd, New Delhi, Reprint 2019. for Unit I,
II, III, IV and V.

REFERENCES:
1. Palanisamy P.N., Manikandan P., Geetha A.& Manjula Rani K., “Applied Chemistry”, 6 th Edition, Tata McGraw Hill
Education Private Limited, New Delhi, 2019.
2. Payal B. Joshi, Shashank Deep, “Engineering Chemistry”, Oxford University Press, New Delhi, 2019.
3. Palanna O., “Engineering Chemistry”, McGraw Hill Education, New Delhi, 2017.

[Link] Artificial Intelligence and Data Science - R2020 Page 48

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 apply the suitable water softening methods to avoid boiler troubles. Applying (K3)
CO2 apply the principle of electrochemistry for various applications. Applying (K3)
CO3 make use of corrosion control methods to solve corrosion related problems. Applying (K3)
CO4 illustrate the quality of fuels from its characteristics. Understanding (K2)
CO5 explain the types of polymers, plastics and fabrication methods. Understanding (K2)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 1
CO2 3 2 1 1
CO3 3 2 1 1
CO4 3 1
CO5 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 25 35 40 100
CAT2 25 35 40 100
CAT3 25 35 40 100
ESE 25 35 40 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 49

 Kongu Engineering College, Perundurai, Erode – 638060, India
20ADT11 - PROBLEM SOLVING AND PROGRAMMING

Programme &
BTech. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 1 PC 3 0 0 3

Preamble Problem solving skill is the most important skill to be possessed by any student. Most of the time, the emphasis is
on learning a programming language rather than on inculcating the problem solving skills. This course is designed
for use by freshmen students taking their first course in programming. It deals with the techniques needed to
practice computational thinking, the art of using computers to solve problems and the ways the computers can be
used to solve problems. This course also focuses on developing programming skills using C language.
Unit - I Introduction to Computer and Problem Solving: 9
Overview of computers : Types, Generations, Characteristics, Basic computer Organization – Programming methodologies –
Structured programming Problem solving techniques: Algorithms - Flowcharts – Pseudo codes – Structuring the logic:
Sequential, selection and repetitive structure.
Unit - II Introduction to C and Control Statements: 9
Introduction to C and Control Statements: The life cycle of a C program – features of C - Data - Variables – Declaring,
assigning and printing variables – Data Classification : integer, float and character types – constants – operators and
expressions – Control Structures : decision making and looping statements – Input and output functions.
Unit - III Arrays and Functions: 9
Arrays : Declaring and initializing 1D array - Two dimensional arrays – Multidimensional arrays. Functions: Basics, The
anatomy of a function – Types of functions based on arguments and return types – Passing 1D and 2D arrays as arguments
to functions – Calling function from another function – recursive functions -Variable scope and lifetime - Storage classes.
Unit - IV Pointers and Strings: 9
Pointers: Memory access and pointers, pointer basics, declaring, initializing and dereferencing a pointer, parameter passing
mechanisms , operations on pointers. Strings : Basics, declaring and initializing strings – pointers for string manipulation –
string handling functions : standard and user defined functions – character oriented functions, Two dimensional array of
strings
Unit - V User-defined data types: 9
Structure basics –declaring and defining a structure - attributes of structures – nested structures – arrays as structure
members – arrays of structure – Passing structures as arguments to functions - Unions – Bit Fields -Enumerated type.

Lecture: 45, Total:45

TEXT BOOK:
1. Sumitabha Das, “Computer Fundamentals and C Programming”, 1st Edition, McGraw Hill, 2020. for Unit I, II, III, IV and V.

REFERENCES:
1. Yashavant Kanetkar, "Let us C", 16th Edition, BPB Publications, 2020.
2. Reema Thareja., “Programming in C ”, 2nd Edition, Oxford University Press, New Delhi, 2020.
3. Balagurusamy E., "Programming in ANSI C", 7th Edition, Mc Graw Hill Education, 2017.

[Link] Artificial Intelligence and Data Science - R2020 Page 50

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 outline the basics of computers and apply problem solving techniques to express the solution for Applying (K3)
the given problem
CO2 identify the appropriate looping and control statements in C and develop applications using Applying (K3)
these statements
CO3 develop simple C programs using the concepts of arrays and modular programming Applying (K3)
CO4 recall the basic concepts of pointers and develop C programs using strings and pointers Applying (K3)
CO5 make use of user defined data types to solve given problems Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 3 1
CO2 3 2 2 3 1
CO3 3 2 2 3 1
CO4 3 2 2 3 1
CO5 3 2 2 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 30 50 100
CAT2 10 30 60 100
CAT3 10 30 60 100
ESE 10 30 60 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 51

 Kongu Engineering College, Perundurai, Erode – 638060, India
20ADC11 - BASICS OF ELECTRICAL AND ELECTRONICS ENGINEERING

Programme &
BTech- Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 1 ES 3 0 2 4

Preamble To provide comprehensive idea about power Systems, AC and DC circuit analysis, working principles and
applications of basic machines in electrical engineering.
Unit - I Introduction to Power Systems: 9
Fundamentals of electricity:Definition – Symbol and unit of Quantities-Work - Power and Energy -Power Generation –
Transmission system – Comparison of Overhead and Underground Systems - Star to Delta and to Star Transformations -
House Wiring: Materials and Accessories –Types of wiring – Principles of Earthing.
Unit - II DC Circuits and AC Circuits: 9
DC Circuits and AC Circuits: Resistance: Resistors in Series and Parallel - Network Reduction - Voltage and Current Division
Rule - Ohm‘s Law- Method of solving a circuit by Kichoff’s laws. AC Circuits: Alternating (Sinusoidal) Voltage and Current,
R.M.S and Average Value, Power Factor, Form Factor and Peak Factor –Analysis of AC Circuit.
Unit - III Electrical Machines: 9
DC Machines: Construction, Principle of Operation of DC Motor-Types and Applications. AC Machines: Construction and
Working Principle of AC Generator, Single Phase Transformer, Three Phase Induction Motor and Single Phase Induction
Motor (Split Phase and Capacitor Start Induction Motor) - Applications.
Unit - IV Basic Electronics: 9
Theory of PN Junction Diode - Operation of Rectifiers (Half wave, Full wave) and Filters - Zener Diodes - Zener Diode as
Voltage Regulator - Transistors: Types - Operation of NPN Transistor - Transistor as an Amplifier - Operation and
Characteristics of Thyristor: Silicon Controlled Rectifier – Triac.
Unit - V Fundamentals of Communication Engineering: 9
Introduction – Communication System - Need for Modulation –Basic principles of Modulation: Amplitude Modulation –
Frequency Modulation – Comparison of AM & FM - Communication Systems (Block Diagram approach): Radio Broadcast, TV:
Standards, Transmitter and Receiver- Satellite and Optical Fibre Communication

List of Experiments / Exercises:

1. Verification of Ohm‘s Law and Kichoff’s Law
2. Measurement of real power, reactive power, power factor and impedance of RC, RL and RLC circuits.
3. Load test on DC shunt motor
4. Performance characteristics of single phase Transformer
5. Load test on single phase induction motor
6. VI characteristics of PN junction diode.
7. VI characteristics of Zener diode.
8. Voltage Regulator using Zener diode.
9. Voltage regulator using 78XX
10. Study of Mixie, Ceiling Fan and Vacuum Cleaner

Lecture: 45, Practical: 30, Total: 75

TEXT BOOK:
1. Muthusubramanian R. and Salivahanan S., “Basics of Electrical and Electronics Engineering”, 18th Reprint, Tata McGraw
Hill, 2014. for Unit I, II, III, IV and V.

REFERENCES:
1. Jegathesan V., Vinoth Kumar K. and Saravanakumar R., “Basic Electrical and Electronics Engineering”, 1 st Edition, Wiley
India, 2011.
2. Sukhija M.S. and Nagsarkar T.K., “Basics of Electrical and Electronics Engineering”, 1 st Edition, Oxford University Press,
2012.
3. Laboratory Manual

[Link] Artificial Intelligence and Data Science - R2020 Page 52

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 interpret the basic concepts of electrical power systems Applying (K3)
CO2 analyze the DC and AC circuits Analyzing (K4)
CO3 interpret the construction and working of different types of electric machines Applying (K3)
CO4 demonstrate the basic functions of electronic components Applying (K3)
CO5 apply the basic concepts of Communication Engineering in simple applications. Applying (K3)
CO6 experiment the electric circuits by applying various theorems Applying (K3),
Manipulation (S2)
CO7 test basic electrical machines like transformer, DC motors and induction motor Applying (K3),
Precision (S3)
CO8 analyze the characteristics of semiconductor devices Analyzing (K4),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 2 1
CO2 3 2 1 2 1
CO3 3 2 1 2 1
CO4 3 2 1 2 1
CO5 3 2 1 2 1
CO6 3 2 1 1 2 1
CO7 3 2 1 1 2 1
CO8 3 2 1 1 2 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 10 40 40 10 100
CAT2 10 40 40 10 100
CAT3 10 60 30 100
ESE 10 40 40 10 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 53

 Kongu Engineering College, Perundurai, Erode – 638060, India
20ADL11 - PROBLEM SOLVING AND PROGRAMMING LABORATORY
Programme &
BTech- Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 1 PC 0 0 2 1

Preamble The purpose of the course is to introduce problem solving aspects and inculcate the logical thinking capability to
solve a given problem. The course will also introduce to students to the field of programming using C language.
The students will be able to enhance their analyzing and problem solving skills and use the same for writing
programs in C.

List of Exercises / Experiments:

Electric Circuits
1. Writing algorithms and drawing flowcharts using Raptor Tool for problems involving sequential structures
2. Writing algorithms and drawing flowcharts using Raptor Tool for problems involving selective structures
3. Writing algorithms and Drawing flowcharts using Raptor Tool for problems involving repetitive structures
4. Programs for demonstrating the use of different types of operators like arithmetic, logical, relational and ternary
operators (Sequential structures)
5. Programs to Illustrate the different formatting options for input and output
6. Programs using decision making statements like ‘if’, ‘else if’, ‘switch’, conditional and unconditional ‘goto’ (Selective
structures)
7. Programs for demonstrating repetitive control statements like ‘for’, ‘while’ and ‘do-while’ (Iterative structures)
8. Programs for demonstrating one-dimensional and two-dimensional numeric array
9. Programs to demonstrate modular programming concepts using functions (Using built-in and user-defined functions)
10. Programs to implement various character and string operations with and without built-in library functions.
11. Programs to demonstrate the use of pointers
12. Programs to illustrate the use of user-defined data types

Total: 30

REFERENCES /MANUALS/SOFTWARES:
1. Raptor and C Compiler

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 demonstrate the execution of flowchart for the given problem using Raptor Applying (K3),
Precision (S3)
CO2 demonstrate the application of sequential, selective and repetitive control structures Applying (K3),
Precision (S3)
CO3 implement solutions to the given problem using derived and user defined data types and functions Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 1 1 1 1 2
CO2 3 2 1 1 1 1 1 2
CO3 3 2 1 1 1 1 1 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

[Link] Artificial Intelligence and Data Science - R2020 Page 54

 Kongu Engineering College, Perundurai, Erode – 638060, India
20PHL11 – PHYSICAL SCIENCES LABORATORY I
(Common to All Engineering and Technology Branches)
Programme &
All BE/BTech Branches Sem. Category L T P Credit
Branch
Prerequisites NIL 1 BS 0 0 2 1

Preamble This course aims to impart hands on training in the determination of the physical parameters such as Young’s
modulus, rigidity modulus, frequency of vibration, velocity of ultrasonic waves, compressibility of water,
wavelength of laser, acceptance angle and the numerical aperture of an optical fiber, and to develop the skills in
handling different basic instruments and also aims to impart the basic concepts of volumetric, conductometric and
pH meter experiments and thereby, to improve the analytical capability.

List of Exercises / Experiments:

1. Determination of the Young’s modulus of the material of a given beam using uniform bending method.
2. Determination of the rigidity modulus of the material of a given wire using torsional pendulum.
3. Determination of frequency of electrically vibrating rod by forming standing waves using Melde’s apparatus.
4. Determination of the velocity of ultrasonic waves in a liquid and the compressibility of a liquid using ultrasonic
interferometer.
5. Determination of (i) the wavelength of a semiconductor laser and (ii) the acceptance angle and the numerical aperture
of a given optical fiber.
6. Estimation of total, temporary and permanent hardness of water by EDTA method.
7. Estimation of Ca2+and Mg2+hardness separately by EDTA method.
8. Estimation of alkalinity of the given water sample.
9. Conductometric titration -Mixture of acids.
10. Estimation of hydrochloric acid using pH meter.
Total: 30
REFERENCES:
1. Tamilarasan K. and Prabu K.,”Physics Laboratory Manual’, 1st Edition, SCM Publishers, Erode, 2020.
2. Palanisamy P.N., Manikandan P., Geetha A. and Manjula Rani K., ”Chemistry Laboratory Manual”, 1 st Edition,
Rajaganapathy Publishers, Erode, 2020.

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 determine the Young’s modulus of a material using the concepts of elasticity and bending Applying (K3),
moment of a beam and to determine the rigidity modulus of a wire using the concepts of twisting Precision (S3)
couple and to compute the frequency of electrically vibrating rod using the concept of standing
waves formed in fixed vibrating string.
CO2 determine the wavelength of a semiconductor laser beam using the concept of diffraction of light, Applying (K3),
and to compute the acceptance angle and the numerical aperture of an optical fiber using the Precision (S3)
concepts of total internal reflection and divergence of light in air and estimate the amount of
hardness for the given water sample by EDTA method, and the amount of alkalinity for the given
water sample.
CO3 demonstrate the conductivity meter and pH meter to estimate the amount of the given solution. Applying (K3),
Precision (S3)
Mapping of COs with POs and PSOs
COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3
CO2 3
CO3 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

[Link] Artificial Intelligence and Data Science - R2020 Page 55

 Kongu Engineering College, Perundurai, Erode – 638060, India
SEMESTER-II
20EGT21 ADVANCED COMMUNICATION SKILLS
(Common to all Engineering and Technology Branches)

Programme &
All BE/BTech branches Sem. Category L T P Credit
Branch
Prerequisites 20EGT11 – English Language Skills 2 HS 3 0 0 3

Preamble This course is designed to impart required levels of fluency in using the English Language at B1Level in the
Common European Framework (CEFR).
Listening, Speaking, Reading, Writing and Grammar & Vocabulary. Activity Based Learning –
Unit - I 9
Phase –VI
Listening – Job and career related descriptions and conversations – requests of different kinds and the responses –
Speaking - Career choices and professional skills – making requests and responding to requests – Reading – Using texts
about jobs and careers – about different societies and cultural differences – Writing – Resumes, CVs and job oriented
advertisements – business and career related emails – Grammar &Vocabulary – Gerunds and elements of comparison –
requests and indirect requests.
Listening, Speaking, Reading, Writing and Grammar & Vocabulary. Activity Based Learning –
Unit - II 9
Phase – VII
Listening – Expository and narrative descriptions – information about different cultures, nations and societies. Speaking –
Narrating and describing – talking about other countries and other cultures – Reading – Using texts about media and
information technology – living abroad and experiencing different cultures – Writing – Blog writing – brochures and tourist
pamphlets – Grammar & Vocabulary – The past tense forms - noun phrases and relative clauses.
Listening, Speaking, Reading, Writing and Grammar & Vocabulary. Activity Based Learning –
Unit - III 9
Phase – VIII
Listening – Consumerism – product description – complaints and redressal – environmental issues – ecology – saving the
planet – Speaking – Talking about problems, issues, complaints – solutions and redressal – talking about environmental
issues – Reading – Using texts on segregating wastes – recycling and reusing – texts on environmental issues – Writing –
Online reviews, articles and writing web content – Grammar & Vocabulary – Phrases and sentences used for describing
problems – passives – prepositions and infinitives.
Unit - IV Listening, Speaking, Reading, Writing and Grammar & Vocabulary. Activity Based Learning –
9
Phase – IX
Listening – Education, learning and the choice of courses – various services needed in daily life – self-
improvement for success in life – Speaking - Discussions about educational and career oriented issues – talking about
everyday services – giving advice and self improvement – Reading – Reading about learning strategies and learning styles –
using texts about personality development – Writing – Writing about hobbies – pastime and individual skills – writing short
articles on everyday life and personality development – Grammar & Vocabulary – Using of “would” and certain gerund forms
– use of modals, verbs, gerunds, negative questions and infinitives.
Listening, Speaking, Reading, Writing and Grammar & Vocabulary. Activity Based Learning –
Unit - V 9
Phase – X
Listening – Historical narratives – biographies and learning about the future – important life events, milestones and
happenings of the past – Speaking – Talking about the past, present and the future – talking about important events in life –
Reading – Texts about new technologies and future science – using texts about social organization, culture and social
practices – Writing – Biographical sketches – historical events – famous personalities, stages of life and getting along with
people – Grammar & Vocabulary – Future tense forms – time clauses and certain “if clauses”.

Lecture: 45, Total: 45

TEXT BOOK:
1. Jack C. Richards, Jonathan Hull, and Susan Proctor, “Interchange - Student’s Book 3”, 4th Edition, Cambridge University
Press, New York, 2017. for Unit I, II, III, IV and V.

REFERENCES:
1. Sanjay Kumar and Pushp Lata, “Communication Skills: A Workbook based on AICTE Syllabus”, Oxford University Press,
2020.
2. Board of Editors, “Skills Annexe: Functional English for Success”, Orient BlackSwan, Hyderabad, 2013.

[Link] Artificial Intelligence and Data Science - R2020 Page 56

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 use functional grammar for improving communication skills Applying (K3)
CO2 listen and comprehend different spoken excerpts critically and infer Unspoken and implied Applying (K3)
meanings.
CO3 read different genres of texts, infer implied meanings and critically analyze and evaluate them for Analyzing (K4)
ideas as well as for method of presentation.
CO4 write effectively and persuasively and produce different types of writing such as narration, Creating (K6)
description, exposition and argument as well as creative, critical, analytical and evaluative writing.
CO5 speak effectively, to express opinions clearly, initiate and sustain a discussion and also negotiate Creating (K6)
using appropriate communicative strategies.

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 2 1 3 1 1
CO2 2 3 1
CO3 1 3 1 1
CO4 3 2
CO5 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 13 30 33 - 17 100
CAT2 13 33 37 - 17 100
CAT3 20 30 33 - 17 100
ESE 6 40 36 - 18 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 57

 Kongu Engineering College, Perundurai, Erode – 638060, India
20MAT21 – DISCRETE MATHEMATICS AND LINEAR ALGEBRA
(Common to AI & DS and AI & ML branches)

Programme &
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 2 BS 3 1 0 4

Preamble To provide in depth knowledge in various concepts of linear algebra,mathematical logic, relations and various
category of functions which serves as a foundation for machine learning and data scienceand also develop skills
to apply algebraic structures in coding theory.
Unit - I Mathematical Logic 9+3
Propositional Calculus: Propositions – Logical connectives – Compound propositions – Conditional and biconditional
propositions – Truth tables – Tautologies and contradictions – Theory of Inference – Rules of inference – Arguments – Validity
of arguments.
Predicate Calculus: Predicates – Statement function – Variables – Quantifiers – Universe of discourse – Theory of inference
for Predicate calculus – Rules of universal specification and generalization – Rules of Existential specification and
generalization.
Unit - II Relations and Functions 9+3
Relations: Definition – Partial ordered relation – Poset – Hasse diagram – Lattices – Properties of lattices – Boolean algebra –
Definition – Properties.
Functions: Definition – Types of functions – Composition of functions – Inverse functions – Recursive functions.
Unit - III Algebraic Structures 9+3
Groups and Subgroups (Definitions only) – Cosets – Lagrange’s theorem – Rings andFields (Definitions and examples) –
Coding Theory – Group codes – Basic notions of error correction – Error recovery in group codes (Excluding theorems in
coding theory).
Unit - IV Vector spaces 9+3
Real vector spaces – Subspaces – Linear combinations and Span – Linear independence – Bases and dimension –Row
space, Column space andNull Space – Rank and nullity.
Unit - V Inner Product Spaces 9+3
Inner products – Angle and Orthogonality in inner product spaces – Orthonormal vectors – Gram Schmidt orthonormalization
process – QR decomposition – Singular value decomposition.

Lecture: 45, Tutorial: 15, Total: 60

TEXT BOOK:
1. Veerarajan T., “Discrete Mathematics with Graph Theory and Combinatorics”, Reprint Edition, Tata McGraw Hill
Publishing Company, New Delhi, 2013. for Unit I, II, III, IV and V.
2. Howard Anton, Chris Rorres, “Elementary Linear Algebra”, 11 thEdition, John Wiley & Sons, 2014. for Unit IV and V.

REFERENCES:
1. Kenneth H. Rosen , “Discrete Mathematics and its applications”, 8thEdition, Tata McGraw Hill, 2019
2. Gilbert Strang, “Introduction to Linear Algebra”, 4 thEdition, Wellesley-Cambridge Press, Wellesley, USA, 2016.
3. David C. Lay, Steven R. Lay, Judith McDonald, “Linear Algebra and Its Applications”, 5thEdition, Pearson Education
Limited, England, 2016.

[Link] Artificial Intelligence and Data Science - R2020 Page 58

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 apply propositional and predicate logic to validate the arguments. Applying (K3)
CO2 understand various types of relations and functions which has applications in Understanding (K2)
cryptography and combinatorial optimization.
CO3 apply the concepts of group structures in coding theory. Applying (K3)
CO4 illustrate the concept of vector spaces commonly used in intelligent systems. Understanding (K2)
CO5 apply the concepts of inner product spaces in orthogonalization and decomposition in Applying (K3)
data reduction.

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 1 1
CO2 3 2 1 2
CO3 3 2 1 2 2
CO4 3 2 1 1
CO5 3 3 3 3 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 10 20 70 100
CAT2 10 20 70 100
CAT3 10 20 70 100
ESE 10 20 70 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 59

 Kongu Engineering College, Perundurai, Erode – 638060, India
DIGITAL PRINCIPLES AND DESIGN
(Common to AI & DS and AI & ML branches)

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites NIL 2 ES 3 0 2 4

Preamble This course enables the students to gain knowledge about the basic principles of number system, Binary Codes,
Boolean algebra, digital logic gates and its minimization techniques and to design different combinational and
sequential logic circuits.
Unit - I Number Systems and Boolean Algebra: 9
Number Systems and Boolean Algebra: Number Systems and their conversions - Complements – Signed Binary Numbers –
Binary Codes – Binary Logic - Boolean Algebra –Theorems of Boolean Algebra – Boolean functions: Realization of functions
using Logic gates.
Unit - II Gate Level Minimization: 9
Gate Level Minimization: Canonical and Standard Forms of Boolean functions – Minimization of functions using Karnaugh
Map up to four variable – Don’t–Care Conditions – NAND and NOR Implementation– Minimization of functions using Quine-
McCluskey method.
Unit - III Combinational Logic: 9
Combinational Logic: Half Adder – Full Adder - Half Subtractor – Full Subtractor – Binary Adder - Subtractor – Magnitude
Comparator – Decoders – Encoders – Multiplexers – Demultiplexers – Boolean Functions implementation using Multiplexers.
Unit - IV Synchronous Sequential Logic: 9
Sequential Logic: Introduction – Latches and Flip-flops – Analysis of clocked sequential circuits: State Equations – State
Table – State Diagram – State Reduction and Assignment.-Shift Registers-Counters.
Unit - V Asynchronous Sequential Logic and Programmable Logic Devices: 9
Introduction to Asynchronous Sequential Circuits: Concepts of Analysis Procedure - Race conditions - types.– Programmable
Logic devices: PROM – PLA – PAL.
Lecture: 45, Practical: 30, Total: 75

List of Exercises / Experiments:

1. Verification of Boolean theorems using digital logic gates
2. Design and implementation of combinational circuits using basic gates
3. Design and implementation of binary adder and subtractor
4. Design and implementation of multiplexer and de-multiplexer
5. Design and implementation of encoder and decoder
6. Truth table verification of flip flops
7. Design and implementation of shift registers using suitable ICs
8. Design and implementation of counters
Lecture: 45, Practical:30, Total:75
TEXT BOOK:
1. Morris Mano M, "Digital Design", 6th Edition, Pearson Education Pvt. Ltd, New Delhi, 2020. for Unit I, II, III, IV and V.

REFERENCES:
1. Anandkumar A, "Fundamentals of Digital Circuits", 4th Edition, Prentice Hall of India, New Delhi, 2016.
2. Salivahanan S &Arivazhagan S, "Digital Circuits and Design", 5th Edition, Oxford University Press, New
Delhi, 2020

[Link] Artificial Intelligence and Data Science - R2020 Page 60

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 verify the Boolean Algebra Applying (K3)
CO2 realization of Boolean Functions Applying (K3)
CO3 apply Karnaugh map techniques for gate level logic minimization Applying (K3)
CO4 design adders and subtractors Applying (K3)
CO5 design multiplexers and demultiplexers Applying (K3)
CO6 design the combinational circuits Applying (K3)
CO7 design the sequential circuits Applying (K3)
CO8 realize boolean functions using PLDs Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 1 3 2 2 1 2 2
CO2 3 2 3 2 2 2 2 2 1 3 2
CO3 3 2 3 2 2 2 2 2 1 3 2
CO4 3 2 3 2 2 2 2 2 2 3 2
CO5 3 2 3 2 2 2 3 2
CO6 3 2 3 2 2 2 3 2
CO7 3 2 3 2 2 2 3 2
CO8 3 2 3 2 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 10 45 45 100
CAT2 10 45 45 100
CAT3 10 45 45 100
ESE 10 45 45 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 61

 Kongu Engineering College, Perundurai, Erode – 638060, India
DATA STRUCTURES
(Common to AI & DS and AI & ML branches)

Programme &
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 2 PC 3 0 0 3

Preamble The course focuses on the basic concepts and applications of linear data structures and non linear data
structures.
Unit - I List: 9
Data Structures – Abstract Data Types (ADT)–List ADT and Array Implementation – Linked List – Doubly Linked List –
Circular Linked List – Applications of Linked Lists.
Unit - II Stack and Queue: 9
Stack ADT – Array and Linked List implementation of Stacks – Applications of Stacks – Queue ADT – Array and Linked List
implementation of Queue – Circular Queue – Applications of Queue.
Unit - III Trees: 9
Preliminaries: Implementation of trees –Tree Traversals – Binary trees: Implementation– Expression trees – The Search Tree
ADT – Binary Search Trees: Construction – Searching – Insertion – Deletion – Find Min – Find Max – AVL trees: Rotation –
Insertion – Deletion.
Unit - IV Graphs: 9
Definitions – Representation of Graphs – Types of Graph – Depth-first traversal – Breadth-first traversal – Topological Sort –
Applications of DFS: Bi-connectivity – Euler circuits – Finding Strongly Connected Components – Applications of BFS:
Bipartite graph – Graph Coloring.
Unit - V Searching, Sorting and Hashing: 9
Searching: Linear search – Binary Search – Sorting: Internal sorting: Bubble sort – Shell sort – Bucket sort – External sorting:
Multiway Merge – Polyphase Merge - Hashing: Hash Functions – Separate Chaining – Open Addressing: Linear Probing –
Quadratic Probing – Double Hashing – Rehashing – Extendible Hashing.
Lecture: 45, Total: 45
TEXT BOOK:
1. Weiss M. A., “Data Structures and Algorithm Analysis in C”, 2 nd Edition, Pearson Education, 2016. for Unit I, II, III, IV and
V.

REFERENCE:
1. Thomas H. Cormen, Charles E. Leiserson, Ronald [Link], Clifford Stein, “Introduction to Algorithms”, 3rd Edition, Mcgraw
Hill, 2009 for Unit IV.

[Link] Artificial Intelligence and Data Science - R2020 Page 62

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 solve problems using various implementations of linked list. Applying (K3)
CO2 make use of ADTs like stack and queue for solving real world problems. Applying (K3)
CO3 implement the tree structure and its operations. Applying (K3)
CO4 apply appropriate graph algorithms for computing problems. Applying (K3)
CO5 demonstrate the concept of sorting, searching and hashing techniques. Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 3 2
CO2 3 2 2 3 2
CO3 3 2 2 3 2
CO4 3 2 2 3 2
CO5 3 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 5 20 75 100
CAT2 10 20 70 100
CAT3 10 20 70 100
ESE 10 20 70 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 63

 Kongu Engineering College, Perundurai, Erode – 638060, India

PYTHON PROGRAMMING
(Common to AI & DS and AI & ML branches)
Programme &
BTech.& Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites C Programming 2 ES 3 0 2 4

Preamble To provide practical exposure to basic concepts of Python Programming including object oriented
programming, GUI and Web programming
Unit – I Introduction 9
Basic Concepts: Keywords, identifiers and variables- Data types - type casting – user input – modules – operators – Flow
control statements- Strings – Calendars and clocks.
Unit - II Functions and Data types 9
Functions: Basics –function arguments – modules – Recursion – Special functions. Lists: Creating, traversing and slicing -
functions – nested lists. Tuples: Creating, initializing and accessing – tuple functions – swapping tuples, unpacking tuples –
Dictionaries: Basics of Creating, initializing and accessing – dictionary functions and methods-view objects.
Unit - III Object Oriented Programming 9
Concepts of OOP- OOP concepts for Python – Built in Attributes and methods –polymorphism- operator overloading -
Inheritance and Namespace – Method types - Exceptions: Built-in and User defined exceptions.
Unit - IV Strings, Files and Regular Expressions 9
Strings: Built-in methods for string manipulation – Case studies. Modules and Packages : import statement – creating user
defined modules and packages. Files: File operations –Reading and Writing a file. Regular Expressions: match, search, sub,
find all and finite functions - Case studies.
Unit - V User Interface and GUI Programming 9
User Interface design: Tkinter - Events – Connecting with databases. Web Frameworks: - Web servers - Introduction to web
server frameworks (Bottle, Django and Flask)
Lecture: 45, Practical:30, Total:75
List of Exercises / Experiments :
1. Program using user-defined functions with different types of argument passing methods
2. Demonstrate tuple, list and dictionary operations
3. Program to illustrate the concept of constructors
4. Program to implement different types of inheritance
5. Program to demonstrate the usage of exception handling
6. Explore string manipulation functions
7. Find the most frequent words from a given text file and copy the same into another file
8. Perform validation of inputs using Regular Expressions
9. Design applications using TKInter
10. Develop web pages using Web frameworks

TEXT BOOK:
1. Anurag Gupta, G P Biswas. Python Programming, McGraw Hill Education,1 st edition, 2020. for Unit I, II, III, IV and V.

REFERENCES:
1 Bill Lubanovic, ―Introducing Python Modern Computing in Simple Packages, 2 nd Edition O'Reilly Media, 2019.
2. Samuel Dauzon, Aidas Bendoraitis and Arun Ravindran. Django: Web Development with Python: Web Development with
Python. Packt Publisher, 1st edition, 2017.

[Link] Artificial Intelligence and Data Science - R2020 Page 64

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1: apply basic constructs of Python Programming to solve simple problems Applying (K3)
CO2: write programs using functions and data types Applying (K3)

CO3: get familiar with implementation of object oriented concepts in python Applying (K3)
CO4: Perform string, file and Regular expression operations and process data Applying (K3)

CO5: use TKinter and other web frameworks for addressing solutions for various real life Applying (K3)
problems
CO6 implement basic concepts of python programming and use it to solve the given problem Applying (K3),
Precision (S3)
CO7 make use of object oriented concepts to solve real world problems Applying (K3),
Precision (S3)
CO8 develop applications using GUI and web frameworks Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 3 3 3 2
CO2 3 2 2 2 3 3
CO3 3 2 3 3 3
CO4 3 2 3 3 3
CO5 3 2 2 3 3 3
CO6 3 2 1 2 1 3 2
CO7 3 2 1 2 1 3 2
CO8 3 2 1 2 1 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT 1 15 30 55 100
CAT 2 15 30 55 100
CAT 3 15 30 55 100
ESE 15 30 55 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 65

 Kongu Engineering College, Perundurai, Erode – 638060, India

DATA STRUCTURES LABORATORY

(Common to AI & DS and AI & ML branches)

Programme & [Link]. &Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 2 PC 0 0 2 1

The course provides knowledge to develop applications using the concepts of Linear and Non-linear Data
Preamble
Structures.

List of Exercises / Experiments:

1. Implementation of singly linked list and its operations
2. Implementation of doubly linked list and its operations
3. Implementation of stack and its operations
4. Infix to postfix conversion using stack ADT
5. Evaluating postfix expression using stack ADT
6. Implementation of queue and its operations
7. Implementation of circular queue and its operations
8. Reverse a queue using stack
9. Implementation of binary search tree traversals
10. Implementation of graph traversal techniques
11. Implementation of linear and binary search algorithms
12. Implementation of sorting algorithms
Total: 30
REFERENCES/MANUAL/SOFTWARE:
1. Operating System : Windows/Linux
2. Software : C
3. Laboratory Manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 implement linear and non linear data structures to solve the given problem Applying (K3),
Precision (S3)
CO2 use a data structure to implement another data structure Applying (K3),
Precision (S3)
CO3 implement searching and sorting operations for a given problem Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

PSO
COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1
2
CO1 3 2 2 2 2 2 3 2
CO2 3 2 2 2 2 2 3 2
CO3 3 2 2 2 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

[Link] Artificial Intelligence and Data Science - R2020 Page 66

 Kongu Engineering College, Perundurai, Erode – 638060, India

OPEN SOURCE LABORATORY

(Common to AI & DS and AI & ML branches)

Programme&
BTech. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 2 BS 0 0 2 1
This course provides knowledge about basic Linux commands, shell script programming and Internet
Preamble
hosting for software development and version control using Git

List of Exercises / Experiments:

1. Implementation of Linux Commands
2. Implementation of Shell programming for constructs like loops and patterns
3. Implementation of Shell programming for string operations
4. Git Installation and Setup
5. Experiment on basic Git Commands
6. Creation of Git local and remote repository
7. Creation of branches and merging branches
8. Experiment on merge conflicts and resolution
9. Working with multiple repositories and configuration files
10. Experiment on Fetch, Pull, Clone and rebasing on repositories
11. Working with Patches and Hooks
12. Experiment on Git graph model and version tracking
Total: 30
REFERENCES/MANUAL/SOFTWARE:
1. Operating System : Linux
2. Software : GitHub Desktop
3. Laboratory Manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 explore linux commands and apply it for various operations at terminal Applying (K3),
Precision (S3)
CO2 solve the given problem using shell script Applying (K3),
Precision (S3)
CO3 explore the functionality of Git Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 2 1 3 2
CO2 3 2 1 2 1 3 2
CO3 3 2 1 2 1 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

[Link] Artificial Intelligence and Data Science - R2020 Page 67

 Kongu Engineering College, Perundurai, Erode – 638060, India
ENGINEERING PRACTICES LABORATORY
(Common to all Engineering and Technology Branches)

Programme &
BTech. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites NIL 2 ES 0 0 2 1

List of Exercises / Experiments:

PART A – MECHANICAL ENGINEERING
1. To prepare square or rectangular shaped MS plates using power tools for cutting, polishing and shaping to the required
dimensions.
2. To carryout drilling, tapping and assembly on the given MS plates.
3. To carryout thread forming on a GI/PVC pipes and prepare water leak proof water line from overhead tank.
4. To prepare a wood or plywood box/tray/any innovative models using modern power tools like cutting machine, router,
jigsaw, power screw driver etc.
5. To prepare a leak proof sheet metal tray/box/funnel using modern power tools.
6. Welding practice using welding simulator.
7. Project: Preparing innovative articles using wood/sheet metal.
PART B – ELECTRICAL AND ELECTRONICS ENGINEERING
8. Safety Aspects of Electrical Engineering, Electrical Symbols, Components Identification, Fuse selection and installation,
Circuit Breakers selection
9. Wiring circuit for fluorescent lamp and stair case wiring
10. Measurement of earth resistance
11. Soldering of simple circuits and trouble shooting
12. Implementation of half wave and full wave rectifier using diodes

Total:30
REFERENCES/MANUAL/SOFTWARE:
1. Engineering Practices Laboratory Manual.

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 plan the sequence of operations for effective completion of the planned models/innovative Creating (K6),
articles Precision(S3)
CO2 identify and use appropriate modern power tools and complete the exercises/models Applying (K3),
accurately Precision(S3)
CO3 select fuses and Circuit breakers Understanding (K2),
Manipulation(S2)
CO4 perform house wiring and realize the importance of earthing Applying(K3),
Manipulation(S2)
CO5 trouble shoot the electrical and electronic circuits Applying(K3),
Manipulation(S2)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 3 3 3 3 3 3 2 3
CO2 3 2 1 1 3 2 2 3
CO3 2 1 3 2 2 3
CO4 3 2 1 1 3 3 2 3
CO5 3 2 1 1 3 2 2 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

[Link] Artificial Intelligence and Data Science - R2020 Page 68

 Kongu Engineering College, Perundurai, Erode – 638060, India
YOGA AND VALUES FOR HOLISTIC DEVELOPMENT
(Common to all Engineering and Technology Branches)

Programme& [Link]. & Artificial Intelligence and

Branch Sem. Category L T P Credit
Data Science
Prerequisites Nil 2 HS 1 0 1 1

Preamble ProvidingValueEducationtoimprovetheStudents‟character-understanding yogic life and physical health-

maintaining youthfulness- Measure and method in five aspects of life
Unit- I Physical Health: 2
Manavalakalai (SKY) Yoga: Introduction - Education as a means for youth empowerment - Greatness of Education - Yoga
for youthEmpowerment. Simplified Physical Exercises: Need and Objectives of Simplified Physical Exercise - Hand, Leg,
Breathing, Eyeexercises - Kapalabathi, Makarasana Part I, Makarasana Part II, Body Massage, Acu pressure, Relaxation
exercises - [Link]: Pranamasana - HasthaUttanasana - Pada Hasthasana - AswaSanjalana Asana -
ThuvipathaasvaSanjalana asana -AstangaNamaskara - Bhujangasana - Atha Muktha Savasana - AswaSanjalana Asana -
Pada Hasthasana - HasthaUttanasana -[Link]:Naddisuddi-Clearance Practice- Benefits.
Unit- II LifeForce: 2
Reasons for Diseases: Body Function - Reason for Diseases and Prevention - Natural reasons (Genetic / imprints,
Planetary Position,Natural calamities and climatic changes) - Unnatural reasons (Food habits, Thoughts, Deeds).
Philosophy of Kaya kalpa: EnrichingBio-Magnetism-Physicalbody-Sexualvitalfluid-Lifeforce-Bio-Magnetism-
[Link]:Postponingold age
- Transformation of food into seven components - Importance of sexual vital fluid - Measure and method in five aspects of life
-[Link]: AswiniMudra- Ojasbreath-BenefitsofKayaKalpa.
Unit- III MentalHealth: 2
Mental Frequencies: Beta, Apha, Theta and Delta wave- Agna Meditation explanation - benefits. Shanti meditation:
ShanthiMeditation explanation – benefits. Thuriya Meditation: Thuriya Meditation explanation – benefits. Benefits of
Blessing: Self blessing(Autosuggestion)-Familyblessing-Blessing theothers-Worldblessing-Divine protection.
Unit- IV Values: 2
Human Values: Self control - Self confidence - Honesty Contentment - Humility – Modesty - Tolerance - Adjustment -
Sacrifice –Forgiveness - Purity (Body, Dress, Environment) - Physical purity - Mental purity - Spiritual purity. Social Values:
Non violence –Service. Patriotism –Equality. Respect for parents and elders- care and protection - Respect for teacher.
Punctuality- TimeManagement.
Unit- V Morality(Virtues): 2
ImportanceofIntrospection:I-Mine(Ego,Possessiveness).SixEvilTemperaments-Greed-Anger-Miserliness-
Immoralsexualpassion-InferiorityandsuperiorityComplex–[Link]:Contentment-
Tolerance-Charity-
Chastity-Equality-Pardon(Forgiveness).FiveessentialQualitiesacquiredthroughMeditation:Perspicacity-Magnanimity-
Receptivity- Adaptability - Creativity(Improved MemoryPower).

Lecture:10,Practical:10,Total:20
TEXT BOOK:

1. ThathuvagnaniVethathiriMaharishi,“YogaforYouthEmpowerment”,VethathiriPublications,2019. for Unit I, II, III, IV and V.

REFERENCES:
1. ThathuvagnaniVethathiriMaharishi,“YogaforModernAge”,VethathiriPublications,2019.
2. ThathuvagnaniVethathiriMaharishi,“SimplifiedPhysicalExercises”,VethathiriPublications,2019.
3. NeelamSharma,“HolisticEducationandYoga”,ShipraPublications,2017.
4 [Link],“ThePowerofYourSubconsciousMind“,PushpakPublication,2019.

[Link] Artificial Intelligence and Data Science - R2020 Page 69

 Kongu Engineering College, Perundurai, Erode – 638060, India

Mapping of COs with POs and PSOs

COs/PO PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
s
CO1 3 2 1 1
CO2 3 2 1
CO3 3 3 1
CO4 3 2 1 1
CO5 3 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom‟s Taxonomy

ASSESSMENT PATTERN
Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating (K6) Tot
Category* (K1) % (K2) % (K3) % (K4) % (K5) % % al
%
CAT1 NA
CAT2 NA
CAT3 100 100
ESE NA
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 70

 Kongu Engineering College, Perundurai, Erode – 638060, India
SEMESTER –III

20MAT35 PROBABILITY THORY AND INFERENTIAL STATISTICS

(Common to AI & DS and AI & ML branches)

Programme & [Link]. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science
Prerequisites Nil 3 BS 3 0 0 3

Preamble To impart knowledge and problem solving capability in probability and statistical concepts necessary for handling
real time applications in Artificial intelligence.
Unit - I Probability and Random Variables 9
Probability – Axioms of probability – Conditional probability – Total probability – Baye’s theorem – Random variable – Discrete
and Continuous random variables – Probability mass function – Probability density function – Cumulative distribution function
– Moments – Moment generating functions.
Unit - II Standard Probability Distributions 9
Discrete Distributions: Binomial distribution – Poisson distribution – Geometric distribution – Continuous Distributions: Uniform
distribution – Exponential distribution – Gaussian distribution.
Unit - III Correlation and Estimation Theory 9
Correlation and Regression: Covariance – Correlation – Karl Pearson’s Coefficient of Correlation – Regression – Lines of
Regression – Properties of Regression lines and coefficients.
Estimation Theory: Concept of Estimation – Characteristics of estimators – Unbiasedness – Consistency –Methods for
Estimation: Method of Maximum Likelihood Estimation - Method of Moments.
Unit - IV Testing of Hypothesis 9
Introduction – Critical region and level of significance – Types of Errors – Large sample tests - Z-test for single mean and
difference of means – Small sample tests: Student’s t-test for testing significance of single mean and difference of means – F-
test for comparison of variances – Chi-square test: Test of goodness of fit – Test of independence of attributes.
Unit - V Design of Experiments 9
Analysis of variance – One way classification: Completely Randomized Design – Two way classification: Randomized Block
Design – Three way classification: Latin Square Design.

Lecture: 45, Total: 45

TEXT BOOK:
1. Jay L. Devore, “Probability and Statistics for Engineering and Sciences”, 9 thEdition, Cengage Learning USA, 2016.
for Unit I, II, III, IV and V.

REFERENCES:
1. Douglas C. Montgomery & George C. Runger, "Applied Statistics and Probability for Engineers ", 7 thEdition, John Wiley and
Sons, USA, 2020.
2. Veerarajan, T, “Probability, Statistics, Random Processes and Queuing Theory”, 1st Edition, Tata McGraw-Hill, New Delhi,
2019.
3. Gupta S.C. and Kapoor V.K. “Fundamentals of Mathematical Statistics”, 11 thEdition, Sultan Chand and Sons, 2002.

[Link] Artificial Intelligence and Data Science - R2020 Page 71

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 interpret the concept of random variables. Applying (K3)
CO2 apply different types of distributions in engineering problems. Applying (K3)
CO3 utilize the concepts of correlation and point estimation in intelligent systems Applying (K3)
CO4 apply statistical tests for solving engineering problems involving small and large Applying (K3)
samples.
CO5 apply the concepts of analysis of variance to experimental data. Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 3 1 1
CO2 3 3 2 2
CO3 3 3 2 3 2
CO4 3 3 2 3 3
CO5 3 3 2 3 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 10 20 70 - - - 100
CAT2 10 20 70 - - - 100
CAT3 10 20 70 - - - 100
ESE 10 20 70 - - - 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 72

 Kongu Engineering College, Perundurai, Erode – 638060, India
FOUNDATIONS OF ARTIFICIAL INTELLIGENCE AND DATA SCIENCE

Programme&
BTech. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 3 PC 3 0 2 4

Preamble The course focuses on the methodology of how to translate a data driven business problem into an effective
solution by using the powerful AI technologies according to the Data Science paradigm.
Unit - I The AI-Based Data Science Workflow and Data Preparation 9
The AI-Based Data Science Workflow: Overview of Workflow - Key Steps of AI-Based Data Science Workflow - Project
Organization. Data Preparation: Data Collection - Visual Data Exploration - Data Preprocessing.
Unit - II Data Analysis and Model Development 9
Data Analysis: Translation of Data into Insight - Multivariate Data Analysis - Variable Selection - Feature Extraction - Data
Visualization. Model Development: Advantages of mathematical models - Key features of a good model - Fighting Overfitting
the Data - Model Generation - Model Ensembles.
Unit - III Revolution of AI and ML, Prediction using Regression 9
Introduction to Machine Learning – Machine Learning vs Classical Programming – The ability to predict – Introduction to
Regression – Regression Models – Linear Regression Model and Machine Learning – Evaluating Model Quality using different
metrics – Insurance cost prediction problem
Unit - IV Non-Linear Models and Feature Engineering 9
Non-Linear Models – Feature Engineering - Insurance cost modeling problem – Reasons for Model Errors – Rectification of
Model Errors – Overfitting and Underfitting – Deriving Data to Train the Model – Train/Test Split on the Insurance Problem
Unit - V Classification Problems and Confusion Matrix 9
Introduction to Classification – Approach followed by Classification Algorithms – A Visual Representation of Logistic Regression
– Evaluating Classification Model Accuracy – Classification with Logistic Regression – Introduction to Confusion Matrix –
Hands-on with Confusion Matrix- Importance of Class wise Accuracy.

List of Exercises / Experiments:

1. Installation and exploration of Weka tool
2. Perform data preprocessing tasks for given dataset
3. Demonstration of classification using ID3, J48 and Naïve Bayes Algorithm
4. Demonstrate performing clustering on dataset
5. Demonstrate performing Linear Regression and Logistic Regression on datasets
6. Demonstrate performing k-Nearest Neighbors on dataset
7. Explore Weka Experimenter to find the performance of classification algorithms
8. Explore Weka knowledge flow for implementing a project

Lecture: 45, Practical:30, Total:75

TEXT BOOK:
1. Arthur K. Kordon “Applying Data Science: How to Create Value with Artificial Intelligence”. Springer Nature, Switzerland, 1 st
edition, 2020. for Unit I, II.
2. Sujit Bhattacharyya, Subhrajit Bhattacharyya, “Practical Handbook of Machine Learning”, Career Launcher Infrastructure
Pvt Ltd and G.K. PublicationsPvt Ltd, 1st edition, 2021. for Unit III, IV and V.

REFERENCES:
1. Avrim Blum, John Hopcroft and Ravindran Kannan. “Foundations of Data Science”. Cambridge University Press, 1 st edition,
England, 2020.
2. Dr. LavikaGoel, “Artificial Intelligence: Concepts and Applications ”. Wiley India PvtLtd., 1 st edition, India, 2021.
3. Stuart Russell, Peter Norvig. “Artificial Intelligence: A Modern Approach”. Pearson, 4 th edition, India, 2020

[Link] Artificial Intelligence and Data Science - R2020 Page 73

 Kongu Engineering College, Perundurai, Erode – 638060, India

REFERENCES/MANUAL/SOFTWARE:
1. Operating System : Linux / Windows
2. Software : Weka / Rapid Miner / Python
3. Laboratory Manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 adapt the data science workflow for finding solution to a given problem Applying (K3)
CO2 examine data analysis sequence and various modeling methods Applying (K3)
CO3 use regression models to solve problems Applying (K3)
CO4 apply feature engineering techniques and estimate model errors Applying (K3)
CO5 use the metrics and evaluate the performance of machine learning algorithms Applying (K3)
CO6 exhibit proficiency to build and evaluate models using weka / Rapid Miner tools Applying (K3),
Precision (S3)
CO7 demonstrate various classification model Applying (K3),
Precision (S3)
CO8 demonstrate various clustering and regression model Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 1 3 1
CO2 3 2 1 1 3 1
CO3 3 2 1 1 3 1
CO4 3 2 1 1 3 1
CO5 3 2 1 1 3 1
CO6 3 2 1 2 1 3 2
CO7 3 2 1 2 1 3 2
CO8 3 2 1 2 1 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 45 55 100
CAT2 35 65 100
CAT3 20 55 25 100
ESE 20 55 25 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 74

 Kongu Engineering College, Perundurai, Erode – 638060, India
DESIGN AND ANALYSIS OF ALGORITHMS
(Common to AI & DS and AI & ML branches)

Programme & [Link]. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Data Structures 3 PC 3 0 2 4

Preamble This course offers formal introduction to common algorithm design techniques and methods for analyzing the
performance of algorithms.
Unit - I Introduction 9
Notion of an Algorithm – Fundamentals of Algorithmic Problem Solving – Important Problem Types – Fundamentals of the
Analysis of Algorithm Efficiency – Analysis Framework – Asymptotic Notations and its properties – Mathematical analysis for
Recursive and Non-recursive algorithms – Empirical analysis of algorithm – Algorithm visualization.
Unit - II Brute Force & Divide and Conquer 9
Selection sort– Sequential search and String Matching – closest pair and convex hull problem – Divide and Conquer
methodology: Merge sort – Quick sort – Binary search – Binary tree traversals and related properties – Multiplication of large
integers and Strassen’s Matrix Multiplication – closest pair and convex hull problem.
Unit - III Decrease and Conquer & Transform and Conquer 9
Insertion sort – Topological Sorting – Fake coin problem – Computing a Median and the Selection Problem – Transform and
conquer: Presorting – Balanced search trees – AVL trees – 2-3Trees – Heaps and Heap sort.
Unit - IV Dynamic Programming & Greedy technique 9
Warshall’s and Floyd’s algorithm – Optimal Binary Search Trees – Knapsack Problem and Memory functions – Greedy
Technique: Prim’s algorithm – Kruskal’s Algorithm – Dijkstra’s Algorithm – Huffman Trees.
Unit - V Backtracking & Branch and Bound 9
n-Queens problem – Hamiltonian Circuit Problem – Subset Sum Problem – Branch and Bound: Assignment problem –
Knapsack Problem – Traveling Salesman Problem – Overview of P, NP and NP-Complete Problems – Randomized algorithms.

List of Exercises:
1. Find the order of growth of the given problems. Identify the basic operation and count the number of times the basic
operation is executed.
2. Analyze the different sorting algorithms and find out the best algorithm with respect to space and time.
3. Using Decrease and conquer technique, compute the kth smallest element in the list of ‘n’ numbers. Also, find the time
complexity.
4. Write the heap sort algorithm to sort ‘n’ numbers using transform and conquer.
5. Compare top down and bottom-up approaches of solving the Knapsack problem using Dynamic Programming.
6. Construct huffman code for the given data. Also perform encoding and decoding (use Greedy technique).
7. Apply backtracking to solve the given instance of subset sum problem.
8. Solve the travelling salesman problem of the given graph using branch and bound technique.

Lecture: 45, Practical:30, Total:75

TEXT BOOK:
1. Anany Levitin, “Introduction to the Design and Analysis of Algorithms”, 3 rd Edition, Pearson Education, 2012. for Unit I, II,
III, IV and V.

REFERENCES:
1. Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest and Clifford Stein, "Introduction to Algorithms", 3 rd Edition,
Prentice Hall of India, 2009.
2. Alfred V. Aho, John E. Hopcroft and Jeffrey D. Ullman, "Data Structures and Algorithms", Reprint Edition, Pearson
Education, 2006.

[Link] Artificial Intelligence and Data Science - R2020 Page 75

 Kongu Engineering College, Perundurai, Erode – 638060, India
REFERENCES/MANUAL/SOFTWARE:
1. Operating System : Windows/Linux
2. Software : C
3. Laboratory Manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 analyze the efficiency of algorithms using various frameworks Analyzing (K4)
CO2 apply brute force and divide-and-conquer techniques to solve various problems and analyze their
Analyzing (K4)
efficiency.
CO3 utilize decrease-and-conquer and transform-and-conquer strategies for solving problems Applying (K3)
CO4 make use of dynamic programming and greedy techniques to solve problems Applying (K3)
CO5 solve difficult combinatorial problems with backtracking and branch & bound techniques Applying (K3)
Analyzing (K4)
CO6 evaluate the Space and Time efficiency of various algorithms
Precision (S3)
Analyzing (K4)
CO7 estimate the performance of various algorithm design techniques
Precision (S3)
Applying (K3)
CO8 use appropriate design strategies for solving a given problem
Precision (S3)
.
Mapping of COs with POs and PSOs
COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 3 2 3 2
CO2 3 3 2 3 2
CO3 3 2 2 3 2
CO4 3 2 2 3 2
CO5 3 2 2 3 2
CO6 3 2 2 2 2 3 2
CO7 3 2 2 2 2 3 2
CO8 3 2 2 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

7ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 10 30 40 20 100
CAT2 10 30 50 10 100
CAT3 10 30 60 100
ESE 10 20 50 20 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 76

 Kongu Engineering College, Perundurai, Erode – 638060, India
COMPUTER ORGANIZATION
(Common to CSE, IT, AI & DS and AI & ML branches)

Programme& BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science
Prerequisites Nil 3 PC 3 0 0 3

Preamble This course provides knowledge on basics of computer organization, introduces various arithmetic operations
and discusses the performance issues of processor, memory and I/O units.
Unit - I Basic Structure of Computers and Machine Instructions 9
Functional Units – Basic Operational Concepts – Number Representation and Arithmetic Operations – Performance – Memory
Locations and Addresses – Memory Operations – Instruction and Instruction Sequencing – Addressing Modes – CISC
Instruction Sets – RISC and CISC Styles.
Unit - II Arithmetic Unit 9
Addition and Subtraction of Signed Numbers – Design of Fast Adders – Multiplication of Unsigned Numbers – Multiplication of
Signed Numbers – Fast Multiplication – Integer Division – Floating Point Numbers and Operations.
Unit - III Processing Unit 9
Fundamental Concepts – Instruction Execution – Hardware Components – Instruction Fetch and Execution Steps – Control
Signals - Hardwired control – CISC Style Processors. Pipelining : Pipelining – Basic concepts – Pipeline Organization –
Pipelining Issues - Data Dependencies – Memory Delay – Branch Delay – Performance Evaluation.
Unit - IV Memory System 9
Basic Concepts – Semiconductor RAM Memories – Read-Only Memories – Direct Memory Access – Memory Hierarchy –
Cache Memories : Mapping Functions – Performance Consideration – Virtual Memory – Secondary Storage : Magnetic Hard
Disks.
Unit - V I/O Organization 9
Accessing I/O Devices – Interrupts – Enabling and Disabling Interrupts – Handling Multiple Devices – Bus Structure – Bus
Operation – Arbitration – Interface Circuits – Interconnection Standards : USB.
Total: 45
TEXT BOOK:
1. Carl Hamacher, ZvonkoVranesic, SafwatZaky and NaraigManjikian, “Computer Organization and Embedded Systems”, 6 th
Edition, McGraw Hill International Edition, 2012. for Unit I, II, III, IV and V.

REFERENCES:
1. Patterson David, A. and Hennessy John L., “Computer Organization and Design: The Hardware / Software Interface”, 5 th
Edition, Harcourt Asia, Morgan Kaufmann, Singapore, 2014.
2. Stallings William, “Computer Organization and Architecture: Designing for Performance”, 9th Edition, Pearson Education,
New Delhi, 2012.

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 describe the basic structure, arithmetic and memory operations of a digital computer and Applying (K3)
determine the addressing modes for the set of instructions.
CO2 describe and apply algorithms for performing different arithmetic operations. Applying (K3)
CO3 make use of the data path in a processor to write the sequence of steps to fetch and execute a Applying (K3)
given instruction and apply the concepts of pipelining to determine and handle the hazards.

distinguish between different types of memory, and apply the mapping functions between main Applying (K3)
CO4 memory and cache.
CO5 demonstrate the need for and types of interrupts in I/O transfer and the role of different types of Applying (K3)
bus and arbitration in I/O operations.

[Link] Artificial Intelligence and Data Science - R2020 Page 77

 Kongu Engineering College, Perundurai, Erode – 638060, India

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 60 20 100
CAT2 20 50 30 100
CAT3 20 55 25 100
ESE 20 40 40 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 78

 Kongu Engineering College, Perundurai, Erode – 638060, India
DATABASE MANAGEMENT SYSTEMS
(Common to AI & DS and AI & ML branches)

Programme &
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 3 PC 3 0 0 3

Preamble The course provides an emphasis on how to organize, maintain and retrieve information from a database
management systemmore efficiently and effectively.
Unit - I Data Models 9
Introduction – Database System Applications – Purpose of database systems – View of data – Database Languages –
Relational Databases – Database Architecture – Database Users and administrators – Relational Model – Structure of
Relational Databases – Database Schema – Keys – Schema Diagrams – Relational Query Languages – Relational Algebra –
Fundamental Relational Operations – Additional Relational Operations.
Unit - II SQL and Database Design 9
Database Design – ER model – Constraints – ER diagrams – Reduction to Relational Schema – ER design issues – SQL:
Basic structure – Operations – Aggregate Functions –Sub queries – Nested Sub queries – modification of the database –
Intermediate SQL: Joins – views– Index – Integrity Constraints – SQL data types and schemas – Authorization.
Unit - III Relational Database Design 9
Features of good relational designs – Functional dependency – Decomposition using functional dependencies – Normal Forms:
1NF, 2NF, 3NF, BCNF, 4NF, 5NF.
Unit - IV Indexing and Hashing 9
Ordered indices – B tree index files – B+ Tree index files – Multiple key access – Static and Dynamic Hashing – Bitmap indices
– Overview of Query Processing.
Unit - V Transactions 9
Transaction concept – Transaction model –Storage structure – Transaction atomicity and durability – Isolation – Serializability–
Concurrency control: Lock-based Protocols – Deadlock Handling.
Total: 45
TEXT BOOK
1. Silberschatz Abraham, Korth Henry F. and Sudarshan S., "Database System Concepts", 7 th Edition , McGraw Hill, New
York, 2019. for Unit I, II, III, IV and V.

REFERENCES
1. ElmasriRamez and NavatheShamkant B., "Fundamental Database Systems", 6 th Edition, Pearson Education, New Delhi,
2010.
2. Date C.J., Kannan A. and Swamynathan S., "An Introduction to Database Systems", 8 th Edition, Pearson Education, New
Delhi, 2006.

[Link] Artificial Intelligence and Data Science - R2020 Page 79

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 determine various keys and sketch a suitable schema for a given application. Applying (K3)
CO2 design an ER model and write SQL queries for a queries for a given scenario. Applying (K3)
CO3 design relational database using normalization methods for a given application. Applying (K3)
CO4 apply indexing and hashing techniques in the design of relational database. Applying (K3)
CO5 apply the concept of concurrency control in transaction processing. Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 3 2
CO2 3 2 2 2 3 2
CO3 3 2 2 2 3 2
CO4 3 2 2 3 2
CO5 3 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 10 30 60 100
CAT2 10 30 60 100
CAT3 10 30 60 100
ESE 10 30 60 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 80

 Kongu Engineering College, Perundurai, Erode – 638060, India
DATA ANALYSIS
(Common to AI & DS and AI & ML branches)

Programme & [Link]. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 3 PC 2 0 2 3

Preamble This course provides a concise introduction to the fundamental concepts of data analysis using Power BI

Unit - I Foundations of Power BI 6

Introducing Power BI - Importing Data into Power BI Desktop - Data Munging with Power Query

Unit - II Data Model and DAX 6

Creating the Data Model - Creating Calculations with DAX - Creating Measures with DAX

Unit - III Time Intelligence and Reports 6

Incorporating Time Intelligence - Creating Reports with Power BI Desktop - Publishing Reports and Creating Dashboards in the
Power BI Portal
Unit - IV Power Pivot, Pivot Tables and Charts 6
Introducing Power Pivot in Excel - Data Analysis with Pivot Tables and Charts - Creating a Complete Solution
Unit - V Advanced Topics 6
Advanced Topics in Power Query - Advanced Topics in Power BI Desktop - Advanced Topics in Power BI Data Modeling -
Integrating Power BI with Other Applications

List of Exercises / Experiments:

1. Import data into power BI desktop and perform basic operations
2. Develop data model for the given problem
3. Create Calculations and measures with DAX
4. Create and publish Power BI reports
5. Create Power BI dashboards
6. Demonstrate basic operations using Power Pivot in Excel
7. Perform data Analysis with Pivot Tables and Charts
8. Integrate Power BI with Other Applications
Lecture: 30; Practical: 30; Total: 60
TEXT BOOK:
Dan Clark. “Beginning Microsoft Power BI: A Practical Guide to Self-Service Data Analytics”. 3rd edition, Apress, 2020. for
1.
Unit I, II, III, IV and V.

REFERENCE BOOK:
1. Brett Powell. Microsoft Power BI Cookbook. 1st edition, Packt Publishing, 2017.

[Link] Artificial Intelligence and Data Science - R2020 Page 81

 Kongu Engineering College, Perundurai, Erode – 638060, India

REFERENCES/MANUAL/SOFTWARE:
1. Power BI
2. Linux / Windows
3. Lab manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 install Power BI and implement the basic operations of Power BI Applying (K3)
CO2 understand and design data model and DAX applications Applying (K3)
CO3 interpret the concepts in developing Power BI reports and dashboards Applying (K3)
CO4 develop applications using Power Pivot, Pivot Tables and Charts Applying (K3)
CO5 implement advanced operations in Power BI Applying (K3)
CO6 create data model and implement DAX operations for various applications Applying (K3)
Precision (S3)
CO7 create customized reports and dashboards using Power BI Applying (K3)
Precision (S3)
CO8 integrate Power BI with other Applications Applying (K3)
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 2
CO2 3 2 1 3 2
CO3 3 2 1 3 2
CO4 3 2 1 3 2
CO5 3 2 1 3 2
CO6 3 2 2 2 3 3 3
CO7 3 2 2 2 3 3 3
CO8 3 2 2 2 3 3 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 15 25 60 100
CAT2 15 20 65 100
CAT3 15 20 65 100
ESE 10 20 70 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 82

 Kongu Engineering College, Perundurai, Erode – 638060, India
DATABASE MANAGEMENT SYSTEMS LABORATORY
(Common to AI & DS and AI & ML branches)

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 3 PC 0 0 2 1
The course explores the features of database management systems and how to interface with front end tools.
Preamble

List of Exercises / Experiments:

1. Demonstrate Data Definition Language and integrity constraints.
2. Demonstrate Data Manipulation Language, Data Control Language commands and TCL commands.
3. Execute nested and sub queries in SQL.
4. Demonstrate Join operations in SQL.
5. Create Views and index and perform SQL operations in it.
6. Demonstrate the concept of looping using PL/SQL statements.
7. Implement Cursors and its operations.
8. Implement Triggers and its operations.
9. Develop Procedures and Functions to perform operations in SQL.
10. Embed SQL queries in high level languages.
11. Mini project on Application Development using Oracle/ SQL SERVER / MYSQL.
Total: 30
REFERENCES/MANUAL/SOFTWARE:
1. Front End: Microsoft Visual Studio 6.0, Microsoft .NET Framework SDK v2.0, Java etc.,
2. Back End : ORACLE / SQL SERVER / MYSQL
3. Manuals: [Link]
4. Laboratory Manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 develop PL/SQL commands to create and manipulate databases Applying (K3),
Precision (S3)
CO2 execute queries using concepts of embedded query languages Applying (K3),
Precision (S3)
CO3 solve real world problems using database concepts Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 2 2 2 2 3 2
CO2 3 3 2 2 2 2 2 3 2
CO3 3 2 2 2 2 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

[Link] Artificial Intelligence and Data Science - R2020 Page 83

 Kongu Engineering College, Perundurai, Erode – 638060, India

20EGL31 - ENGLISH FOR WORKPLACE COMMUNICATION LABORATORY

(Common to all Engineering and Technology Branches)

Programme & All BE/BTech Engineering & Technology

Sem. Category L T P Credit
Branch branches
Prerequisites Nil 3 HS 0 0 2 1

Preamble This course is designed to impart required levels of fluency in using the English Language at B1/B2 level in the
CEFR through activities, hands-on training and application.

Unit - I Listening 6

Techniques for effective listening and note taking; listening to audio scripts, podcasts and TED talks; listening to discourse
samples of native speakers and imitating; improving pronunciation; introduction to the basics of phonetics and understanding
different accents

Unit - II Reading 6

Speed reading skills; reading to gain knowledge; reading newspaper articles to improve writing; academic journals to enrich
vocabulary and word power; reading aloud with proper stress and intonation; reading to draw inferences
Unit – III Soft Skills 6
Importance of soft skills at workplace - understanding soft skills through case studies - developing positive attitude; goal setting;
time management; team work; telephone etiquette; developing professionalism, interpersonal skills and work ethics.
Unit – IV Writing 6
Introduction to pre-writing, style and mechanics of writing; mind mapping; creating content from an outline; paragraph and
resume writing; nuances of academic writing; writing Statement of Purpose (SOP), editing, revising and proof reading for clarity
and readability; structural and grammatical accuracy.
Unit – V Speaking 6
Verbal and non-verbal communication; fluency and spoken English; introducing oneself and others; making presentations on
topics using prepared material; mock interviews; dynamics of Group Discussion.

List of Exercises / Experiments:

1. Mock Interview
2. Presentation
3. Reading Aloud
4. Group Discussion
5. Soft Skills through Case Studies
6. Listening Test
Total:30
TEXT BOOK

1. Jeff Butterfield, “Soft Skills for Everyone”, 1st Edition, Cengage Learning, New Delhi, 2011.
2. Bob Dignen, Steve Flinders and Simon Sweeney, “Professional English for Work and Life, English 365, Student‟s Book
2”, 1st Edition, Cambridge University Press, New Delhi, 2004.

[Link] Artificial Intelligence and Data Science - R2020 Page 84

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1: acquire effective listening and reading skills Understanding (K2),
Imitation (S1)
CO2: acquire and demonstrate appropriate professional skills for the workplace Applying (K3),
Naturalization (S5)
CO3: speak fluently and write meaningfully in English in the given context Applying (K3),
Articulation (S4)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 2 3 2
CO2 2 3 2
CO3 2 3 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 20 30 50
CAT2 20 30 50
CAT3 20 30 50
ESE 10 40 50
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 85

 Kongu Engineering College, Perundurai, Erode – 638060, India
UNIVERSAL HUMAN VALUES
(Common to all Engineering and Technology Branches)

Programme &
BTech. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites NIL 3 HS 2 0 0 2

Preamble To make the student to know what they ‘really want to be’ in their life and profession, understand the meaning of
happiness and prosperity for a human being. Also to facilitate the students to understanding of harmony at all the
levels of human living, and live accordingly
Unit - I Introduction 6
Need and Basic Guidelines of Value Education – Content and Process of Value Education – Self Exploration – purpose of self-
Exploration – Content and Process of Self exploration – Natural Acceptance – Realization and Understanding – Basic Human
Aspirations – Continuous Happiness and Prosperity – Exploring Happiness and Prosperity – Basic Requirement for Fulfillment
of Human Aspirations – Relationships – Physical Facilities – Right Understanding.
Unit - II Harmony in the Self and Body 6
Human Begin and Body – Understanding Myself as Co–existence of Self (‘I’) and Body, Needs of the Self and Body, Activities
in the Self and Body, Self (‘I’) as the Conscious Entity, the Body as the Material Entity – Exercise – Body as an Instrument–
Harmony in the Self (‘I) – Understanding Myself – Harmony with Body.
Unit - III Harmony in the Family and Society 6
Harmony in the Family – Justice – Feelings (Values) in Human Relationships – Relationship from Family to Society –
Identification of Human Goal – Five dimensions of Human Endeavour.
Unit - IV Harmony in Nature and Existence 6
Order of Nature – Interconnectedness – Understanding the Four order – Innateness – Natural Characteristic – Basic Activity –
Conformance – Introduction to Space – Co–existence of units of Space – Limited and unlimited – Active and No–activity –
Existence is Co–existence.
Unit - V Implications of the above Holistic Understanding of Harmony on Professional Ethics 6
Values in different dimensions of Human Living – Definitiveness of Ethical Human Conduct –Implications of Value based Living
– Identification of Comprehensive Human Goal – Humanistic Education – Universal Human Order – Competence and Issues in
Professional Ethics.
Lecture: 45; Total: 45
TEXT BOOK:
1. Gaur R.R., Sangal R., Bagaria G.P., “A Foundation Course in Human Values and Professional Ethics”, 1 st Edition, Excell
Books Pvt. Ltd., New Delhi, 2016. for Unit I, II, III, IV and V.

REFERENCES:
1. Ivan Illich, “Energy & Equity”, The Trinity Press, USA, 1974.
2. Schumacher E.F., “Small is Beautiful: a study of economics as if people mattered”, Britain, 1973.

[Link] Artificial Intelligence and Data Science - R2020 Page 86

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 understand the significance of value inputs in a classroom, distinguish between values and Understanding (K2)
skills, understand the need, basic guidelines, content and process of value education, explore
the meaning of happiness and prosperity and do a correct appraisal of the current scenario in
the society.
CO2 distinguish between the Self and the Body, understand the meaning of Harmony in the Self Understanding (K2)
the Co–existence of Self and Body.
CO3 understand the value of harmonious relationship based on trust, respect and other naturally Understanding (K2)
acceptable feelings in human–human relationships and explore their role in ensuring a
harmonious society.
CO4 understand the harmony in nature and existence, and work out their mutually fulfilling Understanding (K2)
participation in the nature.
CO5 distinguish between ethical and unethical practices, and start working out the strategy to Understanding (K2)
actualize a harmonious environment wherever they work.

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 1 3
CO2 2
CO3 1 3
CO4 2
CO5 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 25 75 100
CAT2 25 75 100
CAT3 NA
ESE NA
* ±3% may be varied (CAT 1, 2, 3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 87

 Kongu Engineering College, Perundurai, Erode – 638060, India
SEMESTER IV
OPTIMIZATION TECHNIQUES
(Common to AI & DS and AI & ML branches)

Programme &
BTech. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 4 PC 3 1 0 4

Preamble The course focuses on the basic concepts, various techniques and applications of engineering optimization.
Unit - I Classical Optimization Techniques 9+3
Introduction to Optimization– Statement of an Optimization problem – Mathematical formulation– Multi variable optimization with
equality constraints – Lagrange multipliers method – Multi variable optimization with inequality constraint – KuhnTucker
conditions.
Unit - II Non-Linear Programming: One-Dimensional Minimization Method 9+3
Introduction – Unimodal function – Elimination Methods: Unrestricted search – Exhaustive search– Dichotomous search–
Interval halving method– Fibonacci method – Golden section method – Direct root methods: Newton method – Secant method.
Unit - III Non-Linear Programming: Unconstrained Optimization Techniques 9+3
Introduction to Unconstrained optimization – Direct Search Methods: Random search methods – Grid search method –
Univariate method –Hookes and Jeeve’s method – Powell’s method – Indirect Search Methods: Steepest descent method –
Fletcher-Reeves method – Newton’s method.
Unit - IV Non-Linear Programming: Constrained Optimization Techniques 9+3
Introduction – Characteristics of a Constrained Problem – Direct Methods: Random search method – Sequential linear
programming – Indirect methods: Transformation techniques – Exterior penalty function method – Interior penalty function
method.
Unit - V Advanced Non-Linear Optimization 9+3
Genetic Algorithms – Introduction – Working Principle –Genetic operators –Particle swarm optimization – Computational
Implementation – Ant colony optimization – Working principle – Neural network based optimization.
Total: 45, Tutorial: 15, Total: 60
TEXT BOOK:
1. [Link], Engineering Optimization Theory and Practice,5th Edition, New Age International, 2019. for Unit I, II, III, IV and V.

REFERENCES:

1. David Luenberger and Yinyu Ye, Linear and Nonlinear Programming, 4 th edition, Springer-Verlag, 2015
2. [Link], [Link], [Link], Engineering Optimization: Methods andapplications, 2 ndEdition, Wiley India Pvt.
Ltd., 2006.
3. Yang, Xin-She. Optimization Techniques and Applications with Examples. 1st Edition, John Wiley & Sons, United
Kingdom: Wiley, 2020.

[Link] Artificial Intelligence and Data Science - R2020 Page 88

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 solve problems with equality and inequality constraints . Applying (K3)

CO2 solve nonlinear programming problems of functions of single variable. Applying (K3)
CO3 use methods of unconstrained optimization to solve non linear problems Applying (K3)
CO4 solve nonlinear optimization problems in the presence of inequality and equality constraints. Applying (K3)
CO5 apply several modern methods of optimization for solving engineering problems Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 5 10 85 100
CAT2 5 10 85 100
CAT3 5 10 85 100
ESE 5 20 75 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 89

 Kongu Engineering College, Perundurai, Erode – 638060, India
WEB TECHNOLOGY
(Common to CSE, AI & DS and AI & ML branches)

Programme& [Link]. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Object Oriented Programming 4 ES 3 0 0 3

Preamble This course provides an introduction to HTML, CSS, Bootstrap, Client-Side JS and Server-Side JS Framework.
The course also addresses the web application development using React JS
Unit - I UI Design 9

Introduction – Basic tags – HTML5 Forms Element – Page Structured Elements – Media Tags. Cascading Style Sheet: Types
of CSS – Positioning Elements – Backgrounds – Box Model – Dropdown Menus. Responsive Web Design: Introduction –
Bootstrap – Grid basics – Nav – Nav Bar – List – Drop down – Tables – Button –Images – Forms-Input – Input Groups.

Unit - II JavaScript 9
Introduction – Operators – Control Structures: Selection- Repetition- Functions: Function Definition – Scope Rules – Recursion.
Array: Declaration – Initialization – Growing Arrays – Passing Arrays to Function. Event Handling. Introduction to REST API-
GET-POST-PUT Methods.
Unit - III Server-side JS Framework 9

Node JS: Introduction – Architecture – Features – Creating Web Servers with HTTP Request – Response – Event Handling –
GET and POST Methods – Modules – Connect to NoSQL Database using Node JS – Implementation of CRUD operations.

Unit - IV ReactJS – Part 1 9

React: Introduction – Installation – create React app - components – state – props - props validation – state vs props –
constructor – Component API – Component Life cycle - Forms – controlled and uncontrolled component – Events – conditional
rendering.
Unit - V ReactJS - Part 2 9

List – keys – refs – Fragments - Router – CSS – Animation – Map – Table –Code splitting – hooks – API Integration.

Lecture:45, Total:45

TEXT BOOKS:
1. Paul Deitel, Harvey [Link] and Abbey Deitel, ―Internet and World Wide Web - How To Program, 5th Edition, Prentice
Hall, 2011. for Unit I(first half), II.
2. Infosys campus connect material shared by infy. for Unit I (Second Half), III.
3. [Link] for Unit IV and V.

[Link] Artificial Intelligence and Data Science - R2020 Page 90

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)

CO1 design static web pages using HTML, CSS and Bootstrap. Applying (K3)
CO2 develop interactive and dynamic web pages using javascript Applying (K3)
CO3 develop a web application using node JS with database connectivity Applying (K3)
CO4 apply the features of ReactJS to develop web applications. Applying (K3)
CO5 demonstrate client-side JS framework to develop web applications Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 1 2 3 2
CO2 3 2 2 1 2 3 2
CO3 3 2 2 1 2 3 2
CO4 3 2 2 1 2 3 2

CO5 3 2 2 1 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %

CAT1 20 20 60 100

CAT2 20 20 60 100

CAT3 10 20 70 100

ESE 10 30 60 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 91

 Kongu Engineering College, Perundurai, Erode – 638060, India
OBJECT ORIENTED PROGRAMMING
(Common to CSE, AI & DS and AI & ML branches)

Programme & [Link]. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 4 PC 2 0 2 3

Preamble This course provides a concise introduction to the fundamental concepts of Java programming including
inheritance, interfaces, exception handling and threads.
Unit - I Introduction to OOP and Java 6

Overview of OOP – Object oriented programming paradigms – Features of Object Oriented Programming – Java Buzz words –
Evolution of Java – Overview of Java–Data Types, Variables and Arrays – Operators – Control Statements.

Unit - II Classes, objects and Methods 6

Classes: Class Fundamentals-objects–Assigning Object Reference Variables – Introducing Methods – Constructors – this
keyword – Garbage Collection – Stack Class. Overloading Methods – Objects as Parameters – Argument Passing – Returning
Objects – Recursion – Access Control–Static – Nested and Inner Classes – Command–Line Arguments – Variable Length
Arguments.
Unit - III Inheritance, Packages and Interfaces 6

Inheritance: Basics – Super keyword -Multilevel Hierarchy–Method Overriding – Dynamic Method Dispatch –Abstract Classes –
final with Inheritance - Packages and Interfaces: Packages – Packages and Member Access –Importing Packages – Interfaces.

Unit - IV Exception handling, Multithreading and I/O 6

Exception Handling basics – Multiple catch Clauses – Nested try Statements – Java’s Built-in Exceptions – User defined
Exception. Multithreaded Programming: Java Thread Model–Creating a Thread and Multiple Threads – Priorities –
Synchronization – Inter Thread Communication- Suspending –Resuming, and Stopping Threads –Multithreading- I/O Basics –
Reading and Writing Console I/O – Reading and Writing Files.
Unit - V String handling, Generics and Collections 6

Generics: Introduction – Example –Parameters – General Form – Generic Methods, Constructors and Interfaces. Strings: Basic
String class, methods and String Buffer Class. Collection frameworks: Overview – Collection Classes – Collection Interfaces.

List of Exercises / Experiments:

1. Write simple Java programs using operators, arrays and control statements.
2. Develop stack and queue data structures using classes and objects.
3. Demonstrate the concepts of inheritance & polymorphism.
4. Develop an application using interfaces by accessing super class constructors and methods.
5. Develop an employee payroll application using packages.
6. Implement exception handling and creation of user defined exception.
7. Implement program to demonstrate multithreading and inter thread communication.
8. Write a program to perform file operations.
9. Develop applications to demonstrate the features of generics classes and interfaces.
10. Implement the concepts of collection frameworks.

Lecture: 30; Practical: 30; Total: 60

TEXT BOOK:
1. Herbert Schildt, “Java: The Complete Reference”, 11th Edition, McGraw Hill Education, New Delhi, 2019 for Unit I, II, III, IV
and V.

[Link] Artificial Intelligence and Data Science - R2020 Page 92

 Kongu Engineering College, Perundurai, Erode – 638060, India

REFERENCES/MANUAL/SOFTWARE:
1. Cay S. Horstmann, “Core Java Fundamentals”, Volume 1, 11th Edition, Prentice Hall, 2020.
2. Linux / Windows
3. Eclipse IDE / Netbeans IDE
4. Lab manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest
Level)
CO1 interpret the role of object oriented programming, java and its variations Applying (K3)
CO2 apply the concepts of classes, objects and methods to solve simple problems Applying (K3)
CO3 develop programs using inheritance, packages and interfaces Applying (K3)
CO4 make use of exception handling mechanisms and multithreaded model along with i/o packages to Applying (K3)
solve real world problems
CO5 build java applications with string classes, collections and generics concepts Applying (K3)
CO6 design and develop java programs using object oriented programming concepts Applying (K3)
Precision (S3)
CO7 develop simple applications using package, exceptions and multithreading. Applying (K3)
Precision (S3)
CO8 develop a solution for real world problems using i/o, generics and collections. Applying (K3)
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
CO6 3 2 2 2 1 3 2
CO7 3 2 2 2 1 3 2
CO8 3 2 2 2 1 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %

CAT1 15 25 60 100
CAT2 15 20 65 100

CAT3 15 20 65 100

ESE 10 20 70 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 93

 Kongu Engineering College, Perundurai, Erode – 638060, India
OPERATING SYSTEMS
(Common to CSE, AI & DS and AI & ML branches)

Programme [Link]. & Artificial Intelligence and Data

Sem. Category L T P Credit
& Branch Science.

Prerequisites NIL 4 PC 3 0 0 3

Preamble
This course provides basic operating system abstractions, system call interface, process, threads, and inter-
process communication. Various management functions of an operating system will also be explored.

Unit - I Operating Systems Overview 9

Introduction – Computer System Organization – Computer System Architecture – Operations – Resource Management –
Security and Protection – Virtualization – Computing Environments. Operating Systems Structures: Services – User and OS
Interface – System Calls – Linkers and Loaders – Operating system Structure – Building and Booting OS.

Unit - II Process Management 9

Process Concept – Process Scheduling – Operations on Processes – Interprocess Communication – IPC in Shared Memory
and Message Passing Systems. CPU Scheduling: Scheduling Criteria – Scheduling Algorithms. Multithreaded Programming:
Threads Overview – Multicore Programming – Multithreading Models.
Unit - III Process Synchronization 9
The Critical Section Problem - Peterson’s solution – Hardware support for Synchronization – Mutex Locks – Semaphores –
Monitors. Deadlocks: Deadlock Characterization – Methods for handling deadlocks - Deadlock Prevention and Avoidance –
Deadlock Detection – Recovery from Deadlock.
Unit - IV Memory Management 9
Main Memory: Background – Contiguous Memory Allocation – Segmentation – Paging – Swapping. Virtual Memory: Background
– Demand Paging – Page Replacement – Case study: Intel 32 Architecture.
Unit - V Storage Management 9
Mass Storage Structure: Overview – HDD Scheduling. File System: File Concept – Access Methods – Directory Structure –
Protection. File System Implementation: File System Structure – File System Operations – Directory Implementation – Allocation
Methods - Free Space Management – Case study: Linux System.

Lecture: 45; Total: 45

TEXT BOOK:
1. Silberschatz, Peter Baer Galvin and Greg Gagne, “Operating System Concepts”, 10 th Edition, John Wiley & Sons Inc.,
2020. for Unit I, II, III, IV and V.

REFERENCES:
1. William Stallings, “Operating Systems Internals and Design Principles”, 9 th Edition, Prentice Hall, 2020.
2. Andrew S. Tanenbaum, “Modern Operating Systems”, 4th Edition, Pearson Education, 2016.

[Link] Artificial Intelligence and Data Science - R2020 Page 94

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 explain operating system structure, services and system calls and identify appropriate system calls for Applying (K3)
a given service
CO2 make use of process management strategies for scheduling processes Applying (K3)
CO3 apply different methods for process synchronization and deadlock handling Applying (K3)
CO4 make use of memory management strategies and apply page replacement policies to address demand Applying (K3)
paging
CO5 apply various disk scheduling algorithms and elaborate file systems concepts Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2

CO1 3 2 1 3 2

CO2 3 2 1 3 2

CO3 3 2 1 3 2

CO4 3 2 1 3 2

CO5 3 2 1 3 2

1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing (K4) Evaluating Creating

Total %
Category* (K1) % (K2) % (K3) % % (K5) % (K6) %

CAT1 25 35 40 100
CAT2 20 20 60 100
CAT3 20 20 60 100
ESE 25 25 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 95

 Kongu Engineering College, Perundurai, Erode – 638060, India
APPLIED MACHINE LEARNING
(Common to AI & DS and AI & ML branches)

Programme& [Link]. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science
Prerequisites Nil 4 PC 3 0 0 3

Preamble The course provides the concepts and algorithms in machine learning and the methods to apply them in real time
problems
Unit - I Introduction to Machine Learning and Learning Theory 9
Need for Machine Learning –Machine Learning in relation to other fields – Types of Machine Learning – Challenges of Machine
Learning – Machine Learning Process and Applications – Data – Data Analytics –Descriptive Statistics– Univariate, Bivariate and
Multivariate Data – Feature Engineering – Dimensionality Reduction techniques– Learning and its Types – Computation Learning
Theory – Concept Learning – Induction Biases – Modeling – Learning Frameworks
Unit - II Similarity based Learning and Regression Analysis 9
Introduction to Similarity based Learning – Nearest Neighbor Learning – Weighted K-Nearest Neighbor Algorithm – Nearest
Centroid Classifier – Locally weighted Regression – Introduction to Regression – Linearity, Correlation and Causation – Linear
Regression – Multiple Linear Regression – Polynomial Regression – Logistic Regression – Ridge, Lasso and Elastic net
Regression
Unit - III Decision Tree and Rule-based Learning 9
Decision Tree learning Model – Decision Tree Induction Algorithms – Validating and Pruning of Decision Trees–
Sequential Covering Algorithm – First Order Rule Learning – Induction as Inverted Deduction – Inverting Resolution – Analytical
Learning – Active Learning
Unit - IV Bayesian Learning, Probabilistic Graphical Models and Support Vector Machines 9
Probability based Learning – Bayes Theorem – Classification using Bayes Model – Naïve Bayes Algorithm for Continuous
Attributes – Other Naïve Bayes Classifiers – Bayesian Belief Network – Markov Chain – Problems Solved with HMM–
Introduction to Support Vector Machine – Optimal Hyperplane – Functional and Geometric Margin – Hard Margin – Soft Margin –
Kernels and Non-Linear Regression
Unit - V Ensemble Learning, Clustering Algorithms and Reinforcement Learning 9
Introduction – Parallel Ensemble Models – Incremental Ensemble Models – Sequential Ensemble Models –Introduction to
Clustering Approaches – Proximity Measures – Hierarchical Clustering Algorithms –Partitional Clustering Algorithm – Density
Based Methods – Grid Based Approach – Probability Model-based Methods – Cluster Evaluation Methods – Overview of
Reinforcement Learning – Reinforcement Learning as Machine Learning – Components – Markov Decision Process

Lecture:45, Total: 45
TEXT BOOK:
1. [Link], [Link], “Machine Learning”, 1 st Edition, Oxford University Press, 2021. for Unit I, II, III, IV and V.

[Link] Artificial Intelligence and Data Science - R2020 Page 96

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 adapt to basic concepts of machine learning, to understand data and concept learning Applying (K3)

CO2 demonstrate similarity based learning and various regression techniques Applying (K3)
CO3 carry out decision tree learning and rule-based learning Applying (K3)
CO4 develop Bayesian , probabilistic and support vector machine models Applying (K3)
CO5 apply learned models to create ensemble models and to work with clustering algorithms, Applying (K3)
reinforcement learning
Mapping of COs with POs and PSOs
COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 3 2
CO2 3 2 2 3 2
CO3 3 2 2 3 2
CO4 3 2 2 3 2
CO5 3 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy
ASSESSMENT PATTERN - THEORY
Test / Bloom’s Remembering Applying Analyzing (K4) Evaluating Creating Total
Understanding (K2) %
Category* (K1) % (K3) % % (K5) % (K6) % %
CAT1 15 35 50 100
CAT2 15 35 50 100
CAT3 15 35 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 97

 Kongu Engineering College, Perundurai, Erode – 638060, India
WEB TECHNOLOGY LABORATORY
(Common to CSE, AI & DS and AI & ML branches)

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Object Oriented Programming 4 ES 0 0 2 1
This course provides an introduction for developing web applications using html, CSS, Bootstrap, Node. js
Preamble
and ReactJS.

List of Exercises / Experiments:

1. Design a web page using HTML tags and host it in github repository
2. Design an attractive webpage using style sheets
3. Design a responsive website using Bootstrap
4. Design a webpage to create simple interactive calculator using Event Handling
5. Design a web application using HTTP Request and HTTP Response
6. Develop simple login page by performing event handling using GET and POST method
7. Design a simple calculator using “Modules” in [Link]
8. Design a webpage to maintain personal information using CRUD operations in MongoDB
9. Design a web application using components and forms in React
10. Design a reactive form to maintain personal information and perform validation using React
11. Implementation of simple project using ReactJS

Practical:30, Total:30

REFERENCES / MANUAL /SOFTWARE

1. Visual Studio code/ GEdit, Node JS+NPM, MongoDB
2. ReactJS, Github

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 Develop interactive web pages using HTML, CSS, JavaScript and Bootstrap. Applying (K3),
Precision (S3)
CO2 Develop a web application to maintain information in a database using server-side scripting. Applying (K3),
Precision (S3)
CO3 Apply the concepts of React to design full-fledged web applications. Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 2 3 3 2
CO2 3 2 2 2 3 3 2
CO3 3 2 2 2 3 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

[Link] Artificial Intelligence and Data Science - R2020 Page 98

 Kongu Engineering College, Perundurai, Erode – 638060, India
APPLIED MACHINE LEARNING LABORATORY
(Common to AI & DS and AI & ML branches)

Programme & [Link]. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science
Prerequisites Python Programming 4 PC 0 0 2 1

Preamble This course provides hands-on experience in applying machine learning algorithms for real world problems.

List of Exercises / Experiments:

1. Create a sample dataset and explore statistical operations using Pandas and visualize the results through plots
2. Create a sample dataset and apply preprocessing techniques
3. Perform dimensionality reduction using Principal Component Analysis
4. Apply Find-S algorithm on sample dataset and find maximally specific hypothesis
5. Implement K-Nearest Neighbor Algorithm
6. Implement linear regression and multiple linear regression algorithms
7. Implement and demonstrate decision tree based ID3 algorithm
8. Implement and demonstrate the working of Naive Bayesian classifier
9. Implement and demonstrate Hidden Markov Model
10. Implement Support Vector Machine
11. Implement and compare the working of Random Forest classifier with Adaboost model
12. Implement K-Means clustering algorithm

Practical: 30; Total: 30

REFERENCES/MANUAL/SOFTWARE:
1. Laboratory Manual
2. Python / MATLAB

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 create dataset and apply preprocessing techniques Applying (K3),
Precision (S3)
CO2 implement supervised learning algorithms with sample dataset Applying (K3),
Precision (S3)
CO3 apply ensemble and clustering methods for sample dataset Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 2 1 3 2
CO2 3 2 2 2 1 3 2
CO3 3 2 2 2 1 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

[Link] Artificial Intelligence and Data Science - R2020 Page 99

 Kongu Engineering College, Perundurai, Erode – 638060, India

20MNT31 - ENVIRONMENTAL SCIENCE

(Common to all Engineering and Technology Branches)

Programme & All BE/BTech Engineering & Technology branches Sem. Category L T P Credit
Branch
Prerequisites Nil 4 MC 2 0 0 0

Preamble This course provides an approach to understand the various natural resources, ecosystem, bio-diversity, pollution
control & monitoring methods for sustainable life and also to provide knowledge and to create awareness for
engineering students on biological sciences.
Unit - I Environmental Studies and Natural Resources 5
Introduction to Environmental Science – uses, over-exploitation and conservation of forest, water, mineral, food, energy and land
resources–case studies
Unit - II Ecosystem and Biodiversity 5
Ecosystems: concept and components of an ecosystem -structural and functional features – Functional attributes (Food chain and
Food web only). Biodiversity: Introduction – Classification – Bio geographical classification of India- Value of biodiversity – Threats
and Conservation of biodiversity - case studies.
Unit - III Environmental Pollution 5
Environmental Pollution: Definition – causes, effects and control measures of: (a) Air pollution - Climate change, global warming,
acid rain, ozone layer depletion (b)Water pollution (c) Soil pollution - Role of an individual in prevention of pollution - case studies.
Unit - IV Environmental Monitoring 5
Sustainability -three pillars of sustainability- factors affecting environmental sustainability-approaches for sustainable development
- Introduction to EIA - objectives of EIA - environment protection act – air (prevention and control of pollution) act – water
(prevention and control of pollution) act.
Unit - V Introduction to Biological Science 5
Functions of Carbohydrates, lipids, proteins and nucleic acids - Cells and its organelles - plasma membrane, mitochondria and
nucleus- Heredity and DNA - organization of DNA in cells - Genes and chromosomes- Cell division -Types of cell division- mitosis
& meiosis - Cell cycle and molecules that control cell cycle.
Total: 25
TEXT BOOK:
1. Anubha Kaushik, and Kaushik C.P., “Environmental Science and Engineering”, 6th Multicolour Edition, New Age International
Pvt. Ltd., New Delhi, 2018.
2. Lodish. H., Berk A., Zipurursky S.L., Matsudaria P., Baltimore D. and Darnell J., “Molecular Cell Biology”, 4th Edition,
Freeman Press, 2000.

REFERENCES:
1. Palanisamy P.N., Manikandan P., Geetha A., Manjula Rani K., Kowshalya V.N., “Environmental Science”, Pearson Education,
New Delhi, Revised Edition 2019.
2. Satyanarayan U.,& Chakrapani U., “Textbook of Biochemistry”,1999 Ed. June 2017.

[Link] Artificial Intelligence and Data Science - R2020 Page 100

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 illustrate the various natural resources and role of individual for its conservation Understanding (K2)
CO2 elaborate the features of ecosystem and biodiversity to find the need for conservation. Understanding (K2)
CO3 manipulate the sources, effects and control methods of various environmental pollution. Applying (K3)
CO4 make use of the knowledge of EIA and environmental legislation laws towards sustainability Applying (K3)
CO5 explain the functions of carbohydrates, lipids, proteins, nucleic acids, Cells and its organelles Understanding (K2)

Mapping of COs with POs and

PSOs
COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 2 1 3
CO2 2 1 3
CO3 3 2 1 3
CO4 3 2 1 3
CO5 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom‟s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 25 40 35 100
CAT2 25 40 35 100
CAT3 NA 100
ESE NA 100
*±3% may be varied (CAT 1, 2 – 50 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 101

 Kongu Engineering College, Perundurai, Erode – 638060, India
SEMESTER V
ARTIFICIAL INTELLIGENCE
(Common to AI & DS and AI & ML branches)

Programme &
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 5 PC 3 0 0 3

Preamble The course focuses on search methods, game playing, constraint satisfaction,planning and knowledge
representation in artificial intelligence.
Unit - I Intelligent Agents 9
Introduction to AI – Agents and Environments – Concept of rationality – Nature of environments – Structure of agents– Problem
Solving agents – search algorithms – uninformed search strategies.
Unit - II Problem Solving 9
Heuristic search strategies – heuristic functions–Local search and optimization problems – local search in continuous space –
search with non- deterministic actions – search in partially observable environments – online search agents and unknown
environments.
Unit - III Game Playing and CSP 9
Game theory – optimal decisions in games – alpha-beta search – monte-carlo tree search – stochastic games – partially
observable games–Constraint satisfaction problems – constraint propagation – backtracking search for CSP – local search for
CSP – structure of CS.
Unit - IV Logical Agents 9
Knowledge-based agents – propositional logic – propositional theorem proving – propositional model checking – agents based
on propositional logic–First-order logic – syntax and semantics – knowledge representation and engineering – inferences in
first-order logic – forward chaining – backward chaining – resolution.
Unit - V Knowledge Representation and Planning 9
Ontological engineering – categories and objects – events – mental objects and modal logic – reasoning systems for categories
– reasoning with default information–Classical planning – algorithms for classical planning – heuristics for planning –
hierarchical planning – non-deterministic domains – time, schedule, and resources – analysis.

Theory:45; Total:45
TEXTBOOK:
1. Stuart Russell and Peter Norvig, “Artificial Intelligence: A Modern Approach”, 3rd Edition, Pearson Education, 2013. for Unit
I, II, III, IV and V.

REFERENCE:
1. Khemani D., “A First Course in Artificial Intelligence”, 1st Edition, 9th reprint, McGraw Hill Education (India) Private Limited,
2019.

[Link] Artificial Intelligence and Data Science - R2020 Page 102

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1: paraphrase Artificial Intelligence, intelligent agents, and apply blind search to solve problems. Applying (K3)

CO2: demonstrate the effectiveness of heuristics in informed search methods. Applying (K3)
CO3: apply game playing in problem solving. Applying (K3)
CO4: make use of propositional logic and first order logic in knowledge-based reasoning. Applying (K3)
CO5: apply knowledge representation and planning to real world problems. Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 3 2
CO2 3 2 2 3 2
CO3 3 2 2 3 2
CO4 3 2 2 3 2
CO5 3 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Remembering Understanding Applying Analyzing Evaluating Creating
Test / Bloom’s Category* Total %
(K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 20 40 40 100
CAT2 20 30 50 100
CAT3 20 30 50 100
ESE 20 30 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 103

 Kongu Engineering College, Perundurai, Erode – 638060, India
DEEP LEARNING
(Common to AI & DS and AI & ML branches)

Programme&
BTech. & Artificial Intelligence and Machine Learning Sem. Category L T P Credit
Branch
Prerequisites Nil 5 PC 3 0 0 3

Preamble This course is designed to impart the skills required to build different deep neural network architectures.
Unit - I Neural Networks: 9
Introduction – Basic Architecture of Neural Networks – Training Neural Network with Backpropagation - Practical Issues in
Neural Network Training - Power of Function Composition – Common Neural Architecutres – Neural Architectures : Binary
Classification Models – Multiclass Models – Matrix Factorization with Autoencoders: Basic Principles – Nonlinear Activations –
Deep Autoencoders
Unit - II Training Deep Neural Networks: 9
Introduction – Backpropagation- Setup and Initialization Issues – Vanishing and Exploding Gradient Problems – Gradient
Descent Strategies – Batch Normalization - Practical Tricks for Acceleration and Compression – Bias- Variance Trade-Off –
Generalization Issues in Model Tuning and Evaluation – Penalty-based Regularization – Ensemble Methods – Early Stopping –
Unsupervised Pretraining – Transfer Learning
Unit - III Radial Basis Function Networks and Boltzmann Machines: 9
Radial Basis Function : Introduction - Training an RBF Network – Hopfield Network – The Boltzman Machine – Restricted
Boltzman Machine – Applications of Restricted Boltzman Machines
Unit - IV Recurrent Neural Networks 9
Introduction – Architecture of Recurrent Neural Networks – Challenges of training Recurrent Networks – Echo-State Networks
– Long Short-Term Memory (LSTM) – Gated Recurrent Units (GRUs) – Applications of Recurrent Neural Networks
Unit - V Convolution Neural Networks: 9
Introduction – Basic Structure of Convolutional Network – Training a Convolutional Network - Case Studies of Convolutional
Architectures - Applications of Convolutional Networks - Attention Mechanism – Generative Adversarial Networks(GANs)

Theory:45; Total: 45

TEXT BOOK:
1. Aggarwal, Charu C, Neural networks and deep learning, Springe,r 2018. for Unit I, II, III, IV and V.

REFERENCES:
1. Ian Goodfellow, YoshuaBengio, and Aaron Courvill, “Deep Learning”, MIT Press, USA, 2016
2. Josh Patterson and Adam Gibson, “Deep Learning – A Practitioner’s Approach”, First Edition, O’Reilly Series, August
2017.
3. Indra den Bakker, “Python Deep Learning Cookbook”, First Edition, Packt Publishing, October 2017.

[Link] Artificial Intelligence and Data Science - R2020 Page 104

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 use Artificial Neural Network .concepts to solve real world problems Applying (K3)
CO2 solve simple real world problems using deep neural networks. Applying (K3)
CO3 use the concepts of RBF and Boltzman machines to solve real world problems Applying (K3)
CO4 exemplify the concepts of CNN models and apply it for solving computer vision related Applying (K3)
problems.
CO5 explicate the concepts of RNN models and apply it for solving Natural Language Applying (K3)
problems.

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 3 2 3
CO2 3 2 3 2 3
CO3 3 2 3 2 3
CO4 3 2 3 2 3
CO5 3 2 3 2 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 10 45 45 100
CAT2 10 45 45 100
CAT3 10 45 45 100
ESE 10 45 45 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 105

 Kongu Engineering College, Perundurai, Erode – 638060, India

DATA MODELING AND BUSINESS INTELLIGENCE

Programme & BTech. & Artificial Intelligence and Machine

Sem. Category L T P Credit
Branch Learning
Prerequisites Database management systems 5 PC 3 0 2 4

Preamble This course provides an exposure on loading, transforming and handling of data. Also it provides Knowledge about
analyzing, reporting results for better decision making.
Unit - I Data preprocessing 9
Data objects and attribute types – Statistical descriptions of data – Measuring data similarity and dissimilarity - Major tasks in
data preprocessing - Data Cleaning – Data Integration – Data Reduction.
Unit - II Data Models 9
OLTP, OLAP and Multidimensional Data Modeling: OLTP – OLAP – OLAP Architectures – Data Model – Role of OLAP Tools in
BI – OLAP Operations. Multidimensional Data Modeling: Basics of Data Modeling – Types of Data Model – Data Modeling
Techniques – Fact Table – Dimension Table – Dimensional Models – Dimensional Modeling Life Cycle
Unit - III ETL Process 9
ETL data structures- Extraction process – cleaning and confirming – delivering dimension tables – delivering fact tables.
Unit - IV ETL and Reporting Tools 9
ETL tools:: Airflow – Basic operations on Airflow. Click view – Azure Data factory – Stitch – Case studies and real time
applications.
Unit - V Performance Management and Enterprise Reporting 9
Performance Management and Enterprise Reporting: Measures, Metrics, KPIs and Performance Management: Understanding
Measures and Performance – Measurement System – Role of metrics – KPIs – Enterprise Reporting: Reporting Perspectives –
Report Standardization and Presentation Practices – Enterprise Reporting Characteristics – Balanced Scorecard – Dashboards
– Creating Dashboards – Scorecards vs. Dashboards – Analysis.
Lecture: 45; Practical: 30; Total:75
TEXT BOOKS:
1. Han Jiawei, and Kamber Micheline, "Data Mining: Concepts and Techniques", 3 rd Edition, Morgan Kaufmann Publishers,
2012. (Units I)
2. Prasad R.N. and Seema Acharya, "Fundamentals of Business Analytics", 2 ndEdition, Wiley, 2016. (Units II, IV, V)
3. Ralph Kimball, Joe Caserta.”The Data Warehouse ETL Toolkit”. 2ndedition, Wiley, 2008. (Unit III)

REFERENCES:
1 Ralph Kimball, Margy Ross, Warren Thornthwaite, Joy Mundy, Bob Becker. The Data Warehouse Lifecycle Toolkit, 3rd
edition, Wiley, 2008.

List of Exercises / Experiments:

1. Evaluate and display statistical descriptions of data
2. Perform data cleaning operations on the given dataset
3. Implement data reduction operations
4. Demonstrate data integration methods
5. Create different types of schema
6. Experiment ETL process in the chosen dataset using Airflow
7. Create reports for real life problems
8. Develop dashboards and score cards for the given problem

[Link] Artificial Intelligence and Data Science - R2020 Page 106

 Kongu Engineering College, Perundurai, Erode – 638060, India

REFERENCES/MANUAL/SOFTWARE:
1. Python
2. Any ETL tool like Airflow, clickview, Azure
3. Lab manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1: interpret basic data preprocessing operations Applying (K3)
CO2: build various data models and perform OLAP operations Applying (K3)

CO3: apply ETL operations on the dataset Applying (K3)

CO4: demonstrate various ETL tools Applying (K3)
CO5: implement Performance Management and Enterprise Reporting Applying (K3)
CO6: experiment various data preprocessing operations Applying (K3)
Precision (S3)
CO7: use ETL tools for processing the data Applying (K3)
Precision (S3)
CO8: create reports for various real life BI applications Applying (K3)
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 3 1
CO2 3 2 3 1
CO3 3 2 3 1
CO4 3 2 1 3 3
CO5 3 2 1 3 3
CO6 3 2 2 2 3 3 3
CO7 3 2 2 2 3 3 3
CO8 3 2 2 2 3 3 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT 1 15 30 55 100
CAT 2 15 30 55 100
CAT 3 15 30 55 100
ESE 15 30 55 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 107

 Kongu Engineering College, Perundurai, Erode – 638060, India

BIG DATA ANALYTICS

(Common to AI & DS and AI & ML branches)

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch

Prerequisites NIL 5 PC 3 0 2 4

Preamble This course focuses on the fundamentals of big data models , processing Frameworks , machine learning
models and stream processing using Spark
Unit - I Bigdata and Ingestion 9
Introduction to Bigdata and Analytics - Four vs of Big Data - Challenges of Traditional System Data Ingestion into Big Data
Systems: Introduction to data Ingestion -Tools for data Ingestion- Apache Sqoop -Sqoop Processing- Sqoop Import Process -
Sqoop Connectors -Importing and Exporting Data from MySQL to HDFS - Apache Flume - Components in Flume’s
Architecture -Configuring Flume Components - Ingest Twitter Data
Unit - II Distributed Processing Framework 9
Distributed Processing in Map reduce –-Distributed Systems - Word Count Example - Map Execution Phases -Map reduce Jobs
- Mapreduce Job Work Interaction – Data Types in Hadoop -Output formats in Map Reduce -Apache Hive -Hive Architecture -
Hive Queries- Hive Metastore -Hive DDL and DML - Table Data Types -Validation of Data -File Format Types -Data Serialization
-Hive Table and Avro Schema- Hive Optimization - Dynamic Partitioning in Hive Bucketing -Hive Analytics UDF and UDAF.
Unit - III SPARK RDD 9
Apache Spark – Introduction - Components of Spark -In-memory Processing - Spark Architecture -Spark Cluster - Spark RDD
Introduction -Creating Spark RDD - RDD Operations - transformation- Actions –Caching and Persistence -Storage Levels -
Lineage and DAG -Need for DAG -Debugging in Spark -Partitioning in Spark -Scheduling in Spark -Shuffling in Spark -Sort
Shuffle -Aggregating Data.
Unit - IV Machine Learning with MLib 9
Data Analytics using Spark - Spark SQL- Data Analysis Operations- Dataset ETL Process-Machine Learning Supervised
Learning -Classification of Linear SVM Linear Regression with Real World Case Studies - Unsupervised Learning K-means
clustering -Reinforcement Learning -Semi-supervised - Mlib Pipelines
Unit - V Spark Stream Processing 9
Apache Kafka – Introduction to Publish subscribe systems-Requirements of Kafka - Kafka architecture-Kafka Internals- Kafka
Development- Java/Scala Coding - Kafka Cluster -Kafka Streams - Kafka Connect -Encryption and Authentication using SSL --
Kafka – HDFS- Stream queries- stream processing- stream computing-Frequent item sets-Real Time Analytics platform -Graph
analytics with graphx platform
List of Exercises / Experiments:
1. Installing and Configuring Hadoop for single node and Multinode architecture
2. Implement Word count/frequency program using Map reduce
3. Perform ingestion of data from relational database to HDFS using Apache Sqoop/Flume
4. Installation of HIVE and apply Hive to create, alter, and drop databases, tables, views, functions and indexes
5. Implementation of supervised learning application using Spark Mlib
6. Implementation of unsupervised learning application using Spark Mlib
7. Implement producer consumer application using Kafka
8. Apply stream processing using Kafka in spark Environment
Lecture: 45, Practical:30, Total:75
TEXT BOOK:
1. Raj Kamal, PreetiSaxena, “Big Data Analytics, Introduction to Hadoop, Spark, and Machine-Learning”, 1st Edition, McGraw
Hill Education,2019. for Unit I, II, III, IV.
2. Neha Narkhede,Gwen shaper and Todd Palino, “Kafka The Definitive Guide-Real-Time Data and stream processing at
scale”, 1st Edition, Oreilly, 2019. for Unit V.

[Link] Artificial Intelligence and Data Science - R2020 Page 108

 Kongu Engineering College, Perundurai, Erode – 638060, India
REFERENCES:
1. Seema Acharya, SubhashiniChellappan, “Big Data and Analytics”, 2 nd Edition,Wiley, 2019.
2. DT Editorial Services, “Big Data, Black Book: Covers Hadoop 2, MapReduce, Hive, YARN, Pig, R and Data Visualization”,
1st Edition, Dreamtech Press; 2016.

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 apply various tools to extract value from data sources Applying (K3)
CO2 apply map reduce programming andHive queries to perform data analysis on real world datasets Applying (K3)
CO3 use Spark and Spark SQL environment for developing applications Applying (K3)
CO4 apply machine learning modelling on big data in spark Applying(K3)
CO5 apply stream processing on big data in spark Applying (K3)
CO6 apply map reduce programming for big data Applying (K3),
Precision (S3)
CO7 apply Hive queries to perform data analysis on real world datasets Applying (K3),
Precision (S3)
CO8 apply Machine Learning and stream processing using Kafka and Spark Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 1 3 2
CO2 3 2 2 1 3 2
CO3 3 2 2 1 3 2
CO4 3 2 2 1 3 2
CO5 3 2 2 1 3 2
CO6 3 2 2 1 2 3 2
CO7 3 2 2 1 2 3 2
CO8 3 2 2 1 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 30 50 100
CAT2 20 30 50 100
CAT3 20 30 50 100
ESE 20 30 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks

[Link] Artificial Intelligence and Data Science - R2020 Page 109

 Kongu Engineering College, Perundurai, Erode – 638060, India
DEEP LEARNING LABORATORY

Programme&
BTech - Artificial Intelligence and Machine Learning Sem. Category L T P Credit
Branch
Prerequisites Nil 5 PC 0 0 2 1
This course provides hands-on experience in applying deep learning algorithms for solving real world
Preamble
problems

List of Exercises / Experiments:

1. Create a multi-layer neural network and apply it to MNIST dataset.
2. Test the performance of multi-layer neural network with various activation and loss functions and tune the performance
with hyper parameters
3. Implement Logistic Regression.
4. Develop an application for outlier detection using autoencoder
5. Implement Convolutional neural networks and use them to classify images
6. Implement a movie recommender system using RBM
7. Implement Recurrent neural networks to generate new text.
8. Implement Stock Price prediction application using LSTM
9. Develop a image captioning application using RNN
10. Develop a image recognition application using CNN
11. Develop a hand written character recognition application using CNN
12. Implement GAN model to simulate realistic images

Total : 30
REFERENCES / MANUAS / SOFTWARE:
1. Operating System : Windows / Linux

2. Software : Python

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1: apply deep neural network for simple problems. Applying (K3),
Precision (S3)
CO2: apply CNN for image processing and RNN for text analysis. Applying (K3),
Precision (S3)
CO3 develop a real world application using suitable deep neural networks. Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

PO
COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
7
CO1 3 2 3 3 3 2 3
CO2 3 2 3 3 3 2 3
CO3 3 2 3 3 3 2 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

[Link] Artificial Intelligence and Data Science - R2020 Page 110

 Kongu Engineering College, Perundurai, Erode – 638060, India
THEORY OF COMPUTATION
(Common to CSE, AI & DS and AI & ML branches)

Programme &
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites NIL 5 PE 3 0 0 3

Preamble This course helps the learners to know the models of computation, along with their variants in the context of formal
languages and their recognizers and to familiarize students with the foundations and principles of computer science.
Unit - I Automata and Regular Expressions 9
Introduction to formal proof – Finite Automata (FA) – Deterministic Finite Automata (DFA) – Non-deterministic Finite Automata
(NFA) – Equivalence between NFA and DFA – Finite Automata with Epsilon transitions – Conversion of NFA into DFA –
Equivalence and minimization of automata.
Unit - II Regular Expressions and Languages 9
Regular expression – Equivalence of finite automata and regular expressions – Proving languages not to be regular (Pumping
Lemma) – Closure properties of regular languages.
Unit - III Context Free Grammar and Languages 9
Context-Free Grammar (CFG) – Parse trees – Ambiguity in grammars and languages – Definition of the pushdown automata
(PDA) – Languages of pushdown automata – Equivalence of pushdown automata and CFG – CFG to PDA-PDA to CFG –
Deterministic Pushdown Automata.
Unit - IV Context Free Languages and Turing Machines 9
Normal forms for CFG – Chomsky Normal Form and Greibach Normal Form – Pumping lemma for CFL – Closure properties of
Context Free Languages. Turing machines: Basic model – definition and representation – Instantaneous Description – Language
acceptance by TM – Variants of Turing Machine – TM as Computer of Integer functions – Programming techniques for Turing
machines (subroutines).
Unit - V Computational complexity theory 9
A language that is not Recursively Enumerable (RE) – An undecidable problem that is RE – Undecidable problems about Turing
machine – Post‘s correspondence problem – The classes P and NP – Kruskal‘s algorithm – Traveling Salesman Problem.

Lecture:45, Total:45

TEXT BOOK:
1. Hopcroft J.E., Motwani R. and Ullman J.D., “Introduction to Automata Theory, Languages and Computations”, 3 rd Edition,
Pearson Education, New Delhi, 2008. for Unit I, II, III, IV and V.
2. Martin J., “Introduction to Languages and the Theory of Computation”, 4 th Edition, Tata McGraw-Hill, New Delhi, 2010.
3. Linz P., “Introduction to Formal Language and Computation”, 4 th Edition, Narosa Publishing, 2007.

[Link] Artificial Intelligence and Data Science - R2020 Page 111

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 apply induction and contradiction methods for theorem proving. Applying (K3)
CO2 design finite automata and regular expression for regular languages. Applying (K3)
CO3 develop and normalize context free grammar for context free languages and demonstrate the Applying (K3)
recognition of context free languages using push down automata.
CO4 construct Turing Machine to accomplish specific task and argue formally about its correctness. Applying (K3)
CO5 make use of Turing machines to distinguish decidable / undecidable problems and compare Applying (K3)
different classes of problems.
Mapping of COs with POs and PSOs
COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Rememberin Understanding Applying Analyzing Evaluating Creating
Total %
Category* g (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 10 30 60 100
CAT2 10 30 60 100
CAT3 10 30 60 100
ESE 10 20 70 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 112

 Kongu Engineering College, Perundurai, Erode – 638060, India
MULTICORE ARCHITECTURE
(Common to CSE, AI & DS and AI & ML branches)

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Computer Organization 5 PE 3 0 0 3

Preamble This course focuses on performance improvement using instruction level, data level, thread level and request level
parallelism.
Unit - I Fundamentals of Quantitative Design and Analysis 9
Classes of Computers – Trends in Technology, Power, Energy and Cost – Dependability – Measuring, Reporting and
Summarizing Performance – Quantitative Principles of Computer Design – Classes of Parallelism ILP, DLP, TLP and RLP –
Multi Threading – SMT and CMP Architectures – Limitations of Single Core Processors – The Multicore era – Case Studies of
Multicore Architectures.
Unit - II Memory Hierarchy Design 9
Introduction – Basics of Memory Hierarchies – Memory Technology and Optimizations – Ten Advanced Optimizations of Cache
Performance – Virtual Memory and Virtual Machines – Design of Memory Hierarchies – Case Studies
Unit - III Data Level Parallelism 9
Introduction – Vector Architectures – SIMD Instruction Set Extensions for Multimedia – Graphics Processing Units – Detecting
and Enhancing Loop Level Parallelism – Comparison of a GPU and a MIMD With Multimedia SIMD – Case Studies
Unit - IV Thread Level Parallelism 9
Centralized Shared-Memory Architectures – Performance of Symmetric Shared-Memory Multiprocessors – Distributed Shared-
Memory and Directory-Based Coherence – Synchronization basics – Models of Memory Consistency introduction – Inter
Connection Networks – Buses, Crossbar and Multi-stage interconnection networks – Performance and Energy Efficiency of the
Intel i7 920 Multicore – Shared Memory Programming with OpenMP
Unit - V RLP and DLP in Warehouse Scale Computers 9
Programming Models and Workloads for Warehouse scale Computers – Computer Architecture of Warehouse-Scale Computers
– Domain Specific Architectures: Introduction – Guidelines for DSAs – Example Domain: Deep Neural Network – Google’s
Tensor Processing Unit, an interface Data Center Accelerator

Lecture: 45, Total:45

TEXT BOOK:
1. John L. Hennessey and David A. Patterson, “Computer Architecture – A Quantitative Approach”, 6th Edition, Morgan
Kaufmann, Elsevier, 2019. for Unit I, II, III, IV and V.

REFERENCE
1. Richard Y. Kain, “Advanced Computer Architecture: A Systems Design Approach”, 1 st Edition, Prentice Hall, 2015.

[Link] Artificial Intelligence and Data Science - R2020 Page 113

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 interpret the limitations of ILP and the need for multicore architectures Applying (K3)
CO2 know the importance of memory hierarchy and benefits of cache memory Applying (K3)
CO3 achieve data level parallelism by applying loop level parallelism and understand the architecture of Applying (K3)
Vector/GPU processor
CO4 explore the cache coherence issues using different memory architectures and different types of inter Applying (K3)
connection networks
CO5 interpret the architectures of GPUs, warehouse scale computers and choose an appropriate model for a Applying (K3)
given problem

Mapping of COs with POs and PSOs

COs/PO PSO1 PSO2
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12
s
CO1 3 3 2 3 2
CO2 3 3 2 3 2
CO3 3 2 1 3 2
CO4 3 3 2 3 2
CO5 3 3 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 20 40 40 20 100
CAT2 20 40 40 100
CAT3 20 45 35 20 100
ESE 20 40 40 30 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 114

 Kongu Engineering College, Perundurai, Erode – 638060, India
DESIGN PATTERNS AND PRINCIPLES
(Common to AI & DS and AI & ML branches)

Programme&
BTech. & Artificial Intelligence and Machine Learning Sem. Category L T P Credit
Branch
Prerequisites Nil 5 PC 2 0 2 3

This course focuses on the principles and patterns to be applied for building reusable solutions in solving the real
Preamble
world problems
Unit - I Introduction To UML 9
Overview of UML : Basics and Details : Diagram Types – Class Diagrams – Sequence Diagram – Use Cases – Object Diagrams
– State Diagrams - Examples
Unit - II Design Principles 9
Principles of OOD: SOLID Principles: The Single Responsibility Principle - The Open-Closed Principle -The Liskov Substitution
Principle - The Interface Segregation Principle - The Dependency Inversion Principle – Implementation in Java
Unit - III Creational Design Pattern : 9
Design Pattern – Introduction - Classification of Design Patterns ; Creational Design Patterns – Factory Method – Abstract
Factory – Builder – Prototype - Singleton
Unit - IV Structural Design Pattern 9
Use and Solution of Structural Design Pattern : Adapter – Bridge – Composite – Decorator – Façade – Flyweight – Proxy –
Examples - Implementations
Unit - V Behavioral Design Patterns 9
Use and Solutions of Behavioral Patterns: Chain of Responsibility – Command – Iterator – Mediator – Memento – Observer –
State – Strategy – Template Method – Visitor – Examples – Implementations
Lecture: 45, Practical:30, Total:75

List of Exercises / Experiments:

Write a program to implement the following concepts in java.
1. a. Method overriding. b. Interface. c. Abstract class.
2. Write programs to implement SOLID principles
3. a. Write a Program to implement Factory pattern.
b. Write a program to implement abstract factory.
4. a. Write a Program to implement Singleton pattern.
b. Write a Program to implement Composite design pattern.
5. a. Write a program to implement decorator pattern.
b. Write a Program to implement proxy design pattern.
6. a. Write a Program to design chain of responsibility pattern.
b. Write a Program to design mediator pattern
7. Write a program to implement iterator pattern.
8. Write a program to implement visitor pattern.
9. Case Study Draw UML diagrams and implement Railway Reservation System
10 Case Study : Draw UML diagrams and implement Inventory Management System

TEXT BOOK:
1. Martin, Robert C. UML for Java programmers. Prentice Hall PTR, 2003.( Units I and II)
2. Vaskaran Sarkar, Java Design Patterns, Apress, 2016 (Units III, IV and V)

[Link] Artificial Intelligence and Data Science - R2020 Page 115

 Kongu Engineering College, Perundurai, Erode – 638060, India
REFERENCES:
1. Rohit Joshi, Java Design Patterns: Reusable Solutions to Common Problems, Java Code Geeks, 2021
2. [Link]

REFERENCES / MANUAS / SOFTWARE:

1. Operating System : Windows

2. Software : IBM Rational Suite, Java SDK

Rational R

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 design UML diagrams for a specified problem. Applying (K3)
CO2 apply design principles for designing the code for a problem Applying (K3)
CO3 use creational pattern to design the instantiation process Applying (K3)
CO4 use structural pattern to compose interfaces Applying (K3)
CO5 apply behavioral patterns to show communication between classes Applying (K3)
CO6: select and Implement appropriate SOLID principles for a given problem Applying (K3)
Precision(S3)
CO7: implement Creational, Structural and Behavioral design patterns for real world Applying (K3)
problems Precision(S3)
CO8 design and implement solutions for real world problems using UML and design Applying (K3)
patterns Precision(S3)

Mapping of COs with POs and PSOs

PO
COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
7
CO1 3 2 3 2 2 3
CO2 3 2 3 2 2 3
CO3 3 2 3 2 2 3
CO4 3 2 3 2 2 3
CO5 3 2 3 2 2 3
CO6 3 2 3 2 3 2 3
CO7 3 2 3 3 3 2 3
CO8 3 2 3 3 3 2 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating (K5) Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % % (K6) %
CAT1 10 30 60 100
CAT2 10 30 60 100
CAT3 10 30 60 100
ESE 10 20 70 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 116

 Kongu Engineering College, Perundurai, Erode – 638060, India
COMPUTER NETWORKS
(Common to CSE, IT, AI & DS and AI & ML branches)

Programme&
B. Tech. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 5 PE 3 0 0 3

Preamble This course deals with the fundamental concepts of computer networks. It presents bottomup approach of different
layers along with their concepts and protocols.
Unit - I Network Models and Physical Layer 9
Data Communications – Networks – Networks Types. Network Models: TCP/IP Protocol model - The OSI Model. Digital-to-digital
conversion: Line coding – Line Coding Schemes – Transmission Modes – Transmission media: Guided – Unguided media.
Unit - II Data Link Layer 9
Introduction – Link Layer Addressing – Error Detection and Correction: Introduction – Block Coding – CRC – Checksum–
Framing – HDLC - Point-to-point protocol. Media Access Control Protocols: Random Access Protocols – Channelization - Wired
LAN: Standard Ethernet – Connecting Devices – Virtual LANs.
Unit - III Network Layer 9
Network Layer Services- Network layer performance - IPV4 addresses – Internet Protocol (IP) - ICMPv4. Unicast Routing
Algorithms: Distance Vector and Link-state routing – Routing Protocols: RIP and OSPF - IPV6 addressing- IPV6 protocol.
Unit - IV Transport Layer 9
Introduction – Transport layer protocols: Simple – Stop-and-wait - Go-back-N – Selective Repeat - Piggybacking – UDP – TCP.
Quality of Service: Data Flow Characteristics -Techniques to improve QoS.
Unit - V Application Layer 9
WWW - HTTP- FTP - Electronic mail –Telnet - SSH, DNS. Network Management: Introduction - SNMP.

Lecture: 45, Total: 45

TEXT BOOK:
1. Behrouz A. Forouzan, “Data Communications and Networking”, McGraw-Hill, 5th Edition, 2013. for Unit I, II, III, IV and V.

REFERENCES:
1. Kurose James F. and Ross Keith W., “Computer Networking: A Top-Down Approach”, 6th Edition, Pearson Education, New
Delhi, 2017.
2. Stallings, “Data and Computer Communications”, PHI, 10th Edition, New Delhi, 2015.

[Link] Artificial Intelligence and Data Science - R2020 Page 117

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 explain the basic fundamentals of networks for data communication and apply the different line
Applying (K3)
coding schemes for digital-to-digital conversion
CO2 demonstrate the knowledge of error detection and correction methods and protocols at data link
Applying (K3)
layer
CO3 interpret the different addressing schemes and apply various routing protocols at network layer Applying (K3)
CO4 illustrate the different transport layer protocols and employ suitable flow control and QoS
Applying (K3)
techniques
CO5 generalize the various protocols and their working principles at application layer Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 1 3 2

CO2 3 2 1 1 3 2

CO3 3 2 1 1 3 2

CO4 3 2 1 1 3 2

CO5 3 2 1 1 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 30 50 20 100
CAT2 20 50 30 100
CAT3 30 50 20 100
ESE 20 50 30 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 118

 Kongu Engineering College, Perundurai, Erode – 638060, India
SEMESTER VI

ARTIFICIAL INTELLIGENCE AND ROBOTICS

(Common to AI & DS and AI & ML branches)

Programme &
BTech. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch

Prerequisites Nil 6 PC 3 0 0 3

Preamble This course describes the fundamental concepts of AI in robotics and the major paradigms for achieving [Link] also
provides the knowledge aboutRobot Kinematics, Dynamics, sensor and vision system.
Unit - I Introduction to Robotics 9
Types and components of a robot- Classification of robots - Closed loop and open loop control systems. Kinematics systems:
Definition of mechanisms and manipulators- Social issues and safety.
Unit - II Autonomy Robot and Hierarchical Paradigm 9
Overview –Use of Robots – Teleoperation - Areas of AI. Hierarchical Paradigm:Attributes of the Hierarchical Paradigm - Closed
World Assumption - Representative Architectures - Advantages and Disadvantages.
Unit - III Reactive Paradigm 9
Overview - Reflexive behaviors - Coordination and Control of Behaviors - Perception in Behaviors - Schema Theory - Principles
and Issues in Transferring Insights to Robots - Attributes of Reactive Paradigm - Subsumption Architecture - Potential Fields
Methodologies - Evaluation of Reactive Architectures.
Unit - IV Robot Kinematics and Dynamics 9
Kinematic Modelling: Translation and rotation representation- Coordinate transformation- DH parameters- Jacobian-Singularity
and Statics. Dynamic Modelling: Equations of motion- Euler-Lagrange formulation.
Unit - V Sensors and Vision System 9
Sensor: Contact and Proximity, Position, Velocity, Force, Tactile. Introduction to Cameras- Camera calibration- Geometry of
image formation- Euclidean/Similarity/Affine/Projective transformations- Vision applications in robotics.

Theory:45,Total: 45
TEXT BOOK:
1. Ronald C. Arkin, Robin R. Murphy, “An Introduction to AI Robotics”, 1st edition, MIT Press, USA, 2001 for Unit I, II.
2 Saha S.K., "Introduction to Robotics", 2nd Edition, McGraw-Hill Higher Education, New Delhi, 2014. for Unit III, IV and V.

REFERENCES:
1. Niku Saeed B., "Introduction to Robotics: Analysis", PHI Learning, New Delhi, 2011.
2. Ghosal A., "Robotics", Oxford, New Delhi, 2006.

[Link] Artificial Intelligence and Data Science - R2020 Page 119

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 interpret the features of an industrial robots with end effectors Applying (K3)
CO2 identify the characteristics of Autonomy Robot and use Hierarchical Paradigm for organizing Applying (K3)
intelligence in Robots.
CO3 apply reactive paradigm for AI Robots Applying (K3)
CO4 perform kinematic and dynamic analyses with simulation Applying (K3)
CO5 design sensor and vision system for robots Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 25 50 25 100

CAT2 25 45 30 100

CAT3 25 45 30 100

ESE 20 40 40 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 120

 Kongu Engineering College, Perundurai, Erode – 638060, India

TEXT AND SPEECH ANALYTICS

Programme & [Link]. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science
Prerequisites Nil 6 PC 2 0 2 3

Preamble This course explores text extraction, text data analysis and speech processing and modeling
Unit - I Text Extraction 6
Introduction- Rapid automatic keyword extraction: candidate keywords - keyword scores - adjoining keywords - extracted
keywords - Benchmark evaluation: precision and recall – efficiency - stoplist generation - Evaluation on new articles

Unit - II Anomaly and Trend Detection 6

Text visualization techniques: Visualization in text analysis - Tag clouds - authorship and change tracking - Data Exploration and
the search for noval patterns - sentiment tracking, visual analytics and FutureLen - scenario discovery - adaptive threshold
setting for novelty mining: Introduction - adaptive threshold for anomaly - Experimental study.

Unit - III Text Streams 6

Events and trends in text streams: Introduction - Text streams - Feature extraction and data reduction - Event detection - Trend
detection - Event and trend descriptions - Embedding semantics in LDA topic models: Introduction - vector space modeling -
latent semantic analysis - probabilistic latent semantic analysis - Latent Dirichlet allocation - embedding external semantics from
Wikipedia - data-driven semantic embedding
Unit - IV Speech processing 6
Phonetics - Articulatory Phonetics - Phonological Categories - Acoustic Phonetics and Signals - Speech Synthesis - Text
Normalization - Phonetic and Acoustic Analysis - Diphone Waveform synthesis – Evaluation - Automatic Speech Recognition
- Architecture - Hidden Markov Model to Speech - MFCC vectors - Acoustic Likelihood Computation - Evaluation.

Unit - V Speech modeling 6

Hidden Markov Models: Markov Processes - HMMs - Evaluation, Optimal State Sequence - Viterbi Search, Baum-Welch
Parameter Re-estimation - Implementation issues

Lecture: 30;Practical: 30 Total: 60

List of Exercises / Experiments:
1. Perform stop word removal process from technical abstract dataset.
2. Apply rapid automatic keyword extraction for news articles and evaluate the performance.
3. Implement various text visualization techniques.
4. Perform sentiment analysis on movie review dataset and track the sentiment.
5. Implement event detection process for short text message.
6. Apply word embedding into sample text dataset and represent it using vector space model.
7. Apply word embedding into sample text dataset and represent it using latent semantic analysis.
8. Apply word embedding into sample text dataset and represent it using latent dirichlet allocation.
9. Develop HMM based speech recognition system.
10. Apply Viterbi approach to develop enhanced speech recognition system.

TEXT BOOK:
1. Michael W. Berry & Jacob Kogan,"Text Mining Applications and Theory", Wiley publications, 2010. for Unit I, II, III.
2. Jurafsky and Martin, “Speech and Language Processing”, Pearson Prentice Hall, Second Edition,2008. for Unit IV and V.

[Link] Artificial Intelligence and Data Science - R2020 Page 121

 Kongu Engineering College, Perundurai, Erode – 638060, India
REFERENCES:
1. Aggarwal, Charu C., and ChengXiangZhai, eds., “Mining text data”, Springer Science & Business Media, 2012.
2. Miner, Gary, et al., “Practical text mining and statistical analysis for non-structured text data applications”, Academic Press,
2012.
3. Lawrence RabinerandBiing-Hwang Juang, “Fundamentals of Speech Recognition”, Pearson Education,2003
Total: 30
REFERENCES/MANUAL/SOFTWARE:
1. ABB Robot Studio Manual
2. Fire Bird – V Software and Hardware manual
3. Laboratory Manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 explore various text extraction techniques Applying (K3)

CO2 apply visualization techniques and perform anomaly & trend detection Applying (K3)
CO3 perform event operations in Text streams Applying (K3)
CO4 identify the different linguistic components of natural language Applying (K3)
CO5 decide on the appropriate modeling technique necessary for a given language and application Applying (K3)
CO6 work with text extraction process. Applying (K3),
Precision (S3)
CO7 detect anomaly, trend and perform sentiment analysis. Applying (K3),
Precision (S3)
CO8 work with speech data analysis. Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 3 2

CO2 3 2 2 3 2
CO3 3 2 2 3 2
CO4 3 2 2 3 2
CO5 3 2 2 3 2
CO6 3 2 2 2 2 3 2
CO7 3 2 2 2 2 3 2

CO8 3 2 2 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 5 20 75 100
CAT2 10 20 70 100
CAT3 10 20 70 100
ESE 10 20 70 100

[Link] Artificial Intelligence and Data Science - R2020 Page 122

 Kongu Engineering College, Perundurai, Erode – 638060, India
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

REGRESSION ANALYSIS

Programme &
BTech. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 6 PC 3 1 0 4

Preamble This course bring together many of the important new ideas in regression analysis and explain them in a statistical
framework. Also, emphasize the mathematical methods and their conceptual under pinnings.
Unit - I Fitting a straight by least square 9+3
Distributions – Confidence Intervals and t-Test – Elements of matrix algebra. Straight Line: Introduction – Relationship between
two variables – linear regression – Analysis of variance – confidence intervals – F-Test - Correlation. Checking the straight line
fit: Lack of fit and pure error – Testing homogeneity of pure error – examining residuals – non-normality checks – checks for time
effects, Non-sconstant variance.
Unit - II Regression in Matrix Term 9+3
Fitting a straight line in matrix term – Singularity – Analysis of variance in matrix – variance of Y using matrix development - non-
singular case. General linear regressing - least square properties – confidence intervals verses regions.
Unit - III Sum of Squares 9+3
Polynomial Models – Two alternative forms of extra SS -Sequential sum of squares – problem with polynomial models – partial
sum of squares - Two predictor variable example – sum of squares of set of linear functions.
Unit - IV Serial Correlations in residuals and Durbin-Watson test 9+3
Serial Correlation in residuals –Durbin-Watson test for serial correlation – Primary test -simplified test – Width of the primary test
– mean square successive difference – Examining the runs in the time sequence plot of residuals.
Unit - V Checking fitted models 9+3
Hat matrix and various types of residuals – Added variable plot and partial residuals – detection of influential observation –
statistical measuring influence. Multiple Regression – Testing general linear hypothesis – Generalize and weighted least square –
example of weighted least square – restricted least square – inverse regression – planar regression.

Lecture: 45, Tutorial: 15, Total: 60

TEXT BOOK:
1. Norman R. Draper, Harry Smith,“Applied Regression Analysis”, 3rdedition, John Wiley & Sons,USA, 2014. for Unit I, II, III, IV
and V.

REFERENCES:
1. Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani,“An Introduction to Statistical Learning: with Applications in
R”, 2ndedition, Springe, Germany,2021.
2. Shai Shalev-Shwartz, Shai Ben-David,“Understanding Machine Learning: From Theory to Algorithms”, Cambridge University
Press , United Kingdom, 2014.

[Link] Artificial Intelligence and Data Science - R2020 Page 123

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 illustrate the fitting of straight line by least square Applying (K3)
CO2 make use of matrix for fitting as straight line Applying (K3)
CO3 apply sum of square and tests for parameters being zero Applying (K3)
CO4 illustrate Serial Correlations in residuals and Durbin-Watson test Applying (K3)
CO5 analysis the model for checking fitness. Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 60 20 100
CAT2 20 50 30 100
CAT3 20 55 25 100
ESE 20 50 30 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 124

 Kongu Engineering College, Perundurai, Erode – 638060, India

ARTIFICIAL INTELLIGENCE AND ROBOTICS LABORATORY

Programme&
BTech. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 6 PC 0 0 2 1
The laboratory course on AI and Robotics is intended to provide a practical realization of industrial robotand
Preamble
mobile robot for real time applications.

List of Exercises / Experiments:

1. Study the functions of ABB IRB 1410 industrial robot- components, drive system and end effectors.
2. Virtual reality robot programming for different tasks.
3. Creation of Tool Centre Point (TCP) and Work Object using ABB IRB 1410 industrial robot.
4. Robot programming exercises: Point-to-point and Continuous path programming.
5. Pick and place operation in teach mode using ABB IRB 1410 industrial robot.
6. Vision based on line Inspection and sorting of components using ABB IRB 1410 industrial robot.
7. Development of embedded programming for motion control using Fire Bird – V robot.
8. Development of embedded programming for velocity control using Fire Bird – V robot.
9. Development of embedded programming for path planning using Fire Bird – V robot.
10. Development of embedded programming for obstacle avoidance using Fire Bird – V robot.
Total: 30
REFERENCES/MANUAL/SOFTWARE:
1. ABB Robot Studio Manual
2. Fire Bird – V Software and Hardware manual
3. Laboratory Manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 analyze the industrial robot work cell problems and develop robot programming through ON/OFF line Applying (K3),
mode Precision (S3)
CO2 develop an embedded programming for autonomous mobile robot Applying (K3),
Precision (S3)
CO3 develop an on line inspection system using machine vision techniques Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 2 1 3 2
CO2 3 2 1 2 1 3 2
CO3 3 2 1 2 1 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

[Link] Artificial Intelligence and Data Science - R2020 Page 125

 Kongu Engineering College, Perundurai, Erode – 638060, India

SEMESTER VII

ENGINEERING ECONOMICS AND MANAGEMENT

(Common to All Engineering And Technology Branches except Chemical Engineering)

Programme&
BTech. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites NIL 7 HS 3 0 0 3

Preamble The aim of the course is to create fundamental knowledge on management by introducing concepts like economics,
national income, marketing, operations management, accounting principles etc.
Unit - I Micro Economics: 9
Economics – Basics Concepts and Principles – Demand and Supply – Law of demand and Supply – Determinants – Market
Equilibrium – Circular Flow of Economic activities and Income.
Unit - II Macro Economics, Business Ownership and Management concepts: 9
National Income and its measurement techniques. Inflation - Causes of Inflation – Controlling Inflation – Business Cycle. Forms of
business – Ownership types. Management concepts: Taylor and Fayol’s Principles – Functions of Management - Managerial
Skills - Levels of Management - Roles of manager.
Unit - III Marketing Management: 9
Marketing - Core Concepts of Marketing - Four P‘s of Marketing - New product development – Intellectual Property rights (IPR),
Product Life Cycle - Pricing Strategies and Decisions.
Unit - IV Operations Management: 9
Operations Management - Resources - Types of Production system - Site selection, Plant Layout, Steps in Production Planning
and Control - Inventory - EOQ Determination.
Unit - V Financial Management: 9
Accounting Principles – Financial Statements and its uses – Depreciation: Straight Line and Diminishing Balance Method – Break
Even Analysis – Capital Budgeting: Significance –Traditional and discounted cash flow methods.

Total:45
TEXT BOOK:
1. Compiled by Department of Management Studies, Kongu Engineering College, "Economics and Management for Engineers",
1st Edition, McGraw Hill Education, Noida, 2013. for Unit I, II, III, IV and V.

REFERENCES:
1. Geetika, Piyali Ghosh and Purba Roy Choudhury, “Managerial Economics”, 3rd Edition, McGraw-Hill, New Delhi, 2018.
2. William J. Stevenson, “Operations Management”, 14th Edition, McGraw-Hill Education, 2021.
3. William G. Nickels, James M. McHugh, Susan M. McHugh, “Understanding Business”, 12th Edition, McGraw-Hill Education,
New York, 2019.

[Link] Artificial Intelligence and Data Science - R2020 Page 126

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 identify market equilibrium and interpret national income calculations and inflation issues Applying (K3)
CO2 choose a suitable business ownership for their enterprise and illustrate managerial functions Applying (K3)
CO3 infer marketing management decisions Understanding (K2)
CO4 apply appropriate operation management concept in business situations Applying (K3)
CO5 interpret financial and accounting statements and evaluate new proposals Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 1 1 2 3 2 2 2 3 2 1 2
CO2 1 2 2 2 2 2 2 3 2 1 2
CO3 1 2 1 2 2 2 2 3 2 2 2
CO4 1 2 1 2 2 2 2 3 2 1 2
CO5 2 2 2 2 2 2 3 2 2 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 40 40 100
CAT2 20 40 40 100
CAT3 20 40 40 100
ESE 20 40 40 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 127

 Kongu Engineering College, Perundurai, Erode – 638060, India

IMAGE AND VIDEO ANALYTICS

Programme& [Link]. & Artificial Intelligence and Machine

Sem. Category L T P Credit
Branch Learning
Prerequisites Nil 7 PC 3 0 2 4

Preamble This course aims to provide a broad view on processing and analyzing images and video.
Unit - I Introduction 9
Deep Neural Networks – Introduction to Tensor flow – Keras Deep Learning library – OpenCV Libratry - Hand Written Number
Recognition with Keras and OpenCV
Unit - II Convolutional Neural Network for Computer Vision 9
Convolution Neural Network – CNN architectures and drawbacks of DNN- convolution and pooling operations in tensor flow –
training and evaluating CNN – model performance optimization – ImageNet – LeNet – AlexNet – VGGNet – GoogleLENet -
TesNet.
Unit - III Feature extraction, object detection and segmentation 9
Feature extraction approach – transfer learning example – multi-task learning – Auto encoders of CNN – difference between
object detection and image classification - Traditional, nonCNN approaches to object detection - R-CNN – Regions with CNN
features - Fast R-CNN – fast region-based CNN - Faster R-CNN – faster region proposal network-based CNN -Mask R-CNN –
Instance segmentation with CNN
Unit - IV Generative Models 9
Pix2pix - Image-to-Image translation - GAN – code example – feature matching – applications of generative models – neural
artistic style transfer – generative adversarial networks – visual dialogue model.
Unit - V Video Classification 9
Understanding and classifying videos – exploring video classification dataset – splitting videos in to frames – approaches for
classifying videos – extending image based approaches to videos: Regressing the human pose- segmenting videos – generating
videos.
List of Exercises / Experiments:
1. Build a CNN model to perform Handwritten Number Recognition using Tesnsorflow
2. Build a CNN model to perform Handwritten Number Recognition using Keras
3 Experiment the model performance using the available CNN models.
4 Develop a CNN model to perform object detection
5 Apply and segmentation procedures and design a model for image classification
6 Experiment image to image translation using GAN
7 Explore generative adversarial networks and its features on simple data set
8 Perform video classification using deep learning techniques.
Lecture:45, Practical:30, Total:75
TEXT BOOK:
1. Mohit Sewak, Md. Rezaul Karim and Pradeep Pujari, “Practical Convolutional Neural
Networks, Packt Publishing, 2018. for Unit I, II, III.
2. Rajalingappaa Shanmugamani, “Deep Learning for Computer Vision”, Packt Publishing, 2018, for Unit IV and V.

REFERENCES/MANUAL/SOFTWARE:
1. D. L. Baggio et al., “Mastering OpenCV with Practical Computer Vision Projects”, Packt Publishing, 2012.

[Link] Artificial Intelligence and Data Science - R2020 Page 128

 Kongu Engineering College, Perundurai, Erode – 638060, India

2. Jan Erik Solem, “Programming Computer Vision with Python: Tools and algorithms for analyzing images”, O'Reilly Media,
2012.
3. Windows/Linux
4 Tensorflow/OpenCV

5. Matlab/Python
6. Lab Manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 make use of the basic concepts of image processing and its libraries Applying (K3)
CO2 interpret the various CNN models used for image analytics Applying (K3)
CO3 apply the various levels of segmentation and interpret the results for object detection and feature
Applying (K3)
extraction.
CO4 make use of the GAN model to solve the real world problems. Applying (K3)
CO5 predict the more reliable video analytic solutions for real time problems. Applying (K3)
CO6 experiment the basic features of Keras and Tensorflow to implement CNN model. Applying (K3)
Precision (S3)
CO7 implement image segmentation and GAN to provide more effective solutions. Applying (K3)
Precision (S3)
CO8 develop a real time model for video analytics using deep learning techniques Applying (K3)
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 1 3 2
CO2 3 2 2 1 3 2
CO3 3 2 2 1 3 2
CO4 3 2 2 1 3 2
CO5 3 2 2 1 3 2
CO6 3 2 2 1 1 3 2
CO7 3 2 2 1 1 3 2
CO8 3 2 2 1 1 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 30 50 100
CAT2 20 30 50 100
CAT3 20 30 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 129

 Kongu Engineering College, Perundurai, Erode – 638060, India

WIRELESS SENSOR NETWORKS

(Common to AI & DS and AI & ML branches)

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Computer Networks 7 PE 3 0 0 3

Preamble This course provides the fundamental concepts of wireless sensor networks and explains functionalities of different
layers. It also helps to devise appropriate node and network management strategies and throws light on sensor
networks security.
Unit - I Introduction 9
Introduction-Motivation and Wireless Sensor Nodes: Definitions and Background, Challenges and Constraints - Applications:
Structural Health Monitoring, Traffic Control, Health Care, Pipeline Monitoring, Precision Agriculture, Active Volcano,
Underground Mining - Node Architecture: The Sensing Subsystem, The Processor Subsystem, Communication Interfaces,
Prototypes - Operating Systems: Functional Aspects, Nonfunctional Aspects, Prototypes, Evaluation.
Unit - II Basic Architectural Framework and Medium Access Control 9
Physical Layer: Basic Components, Source Encoding, Channel Encoding, Modulation, Signal Propagation. Medium Access
Control: Overview, Wireless MAC Protocols, Characteristics of MAC Protocols in Sensor Networks, Contention-Free MAC
Protocols, Contention-Based MAC Protocols, Hybrid MAC Protocols.
Unit - III Routing Protocols and Power Management 9
Network Layer: Overview, Routing Metrics, Flooding and Gossiping, Proactive Routing, On-Demand Routing, Hierarchical
Routing, Location-Based Routing, QoS-Based Routing Protocols. Power Management: Local Power Management Aspects,
Dynamic Power Management, Conceptual Architecture.
Unit - IV Node and Network Management, Localization 9
Node and Network Management: Time Synchronization: Clocks and the Synchronization Problem, Time Synchronization in
Wireless Sensor Networks, Basics of Time Synchronization, Time Synchronization Protocols. Localization: Overview, Ranging
Techniques, Range-Based Localization, Range-Free Localization, Event-Driven Localization.
Unit - V Security and Sensor Network Programming 9
Security: Fundamentals of Network Security, Challenges of Security in Wireless Sensor Networks, Security Attacks in Sensor
Networks, Protocols and Mechanisms for Security, IEEE 802.15.4 and ZigBee Security. Sensor Network Programming:
Challenges in Sensor Network Programming, Macro programming, Dynamic Reprogramming, Sensor Network Simulators.

Total: 45

TEXT BOOK:
1. WaltenegusDargie, Christian Poellabauer, "Fundamentals of Wireless Sensor Networks: Theory and Practice", 1 st Edition,
John Wiley & Sons, 2011. for Unit I, II, III, IV and V.

REFERENCES:
1. Mohammad S. Obaidat, SudipMisra, "Principles of Wireless Sensor Networks", 1 st Edition, Cambridge University Press,
London, 2014.
‘2. Feng Zhao, Leonidas Guibas, "Wireless Sensor Networks", 1st Edition, Elsevier, 2004.

[Link] Artificial Intelligence and Data Science - R2020 Page 130

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 apply the basic concepts of wireless sensor networks in real life applications Applying (K3)
CO2 illustrate the basic architectural framework using physical and MAC layer protocols Applying (K3)
CO3 utilize various network layer protocols for inter and intra communication patterns Applying (K3)
CO4 apply different synchronization and localization algorithms for managing node and network level
Applying (K3)
functions
CO5 develop software and hardware components required for a sensor network application Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 1 3 2

CO2 3 2 1 1 3 2

CO3 3 2 1 1 3 2

CO4 3 2 1 1 3 2

CO5 3 2 1 1 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 30 50 20 100
CAT2 30 50 20 100
CAT3 30 30 40 100
ESE 25 35 40 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 131

 Kongu Engineering College, Perundurai, Erode – 638060, India
CLOUD COMPUTING
(Common to AI & DS and AI & ML branches)

Programme &
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Operating Systems 7 PE 2 0 2 3

Preamble This course provides cloud computing evolution and its services, along with design and development. It also focuses
on key challenges and issues in cloud computing.
Unit - I Distributed System Models 6
Scalable computing – Network Based Systems – System Models – Software Environment for Distributed and Cloud computing –
Performance – Security – Energy Efficiency.
Unit - II Virtualization 6
Implementation levels of Virtualization – Virtualization Structures – Tools and Mechanisms – CPU, Memory, I/O devices
Virtualization – Virtual Clusters and Resource Management – Virtualization for Data-Center Automation.
Unit - III Cloud Platform Architecture over Virtualized Data Centers 6
Cloud computing Service models – Data-Center Design and Interconnection Networks – Architectural Design of Compute and
Storage Clouds – Public Cloud Platforms: Google App Engine – AWS – Azure – Inter-cloud Resource Management – Cloud
Security – Trust Management.
Unit - IV Cloud Programming and Software Environments 6
Cloud and Grid Platforms – Parallel and Distributed Programming Paradigms – Programming Support : Google App Engine –
Amazon AWS – Microsoft Azure – Cloud Frameworks: Eucalyptus – Nimbus – OpenNebula – Sector – Sphere – OpenStack –
Manjrasoft Aneka Cloud and Appliances.
Unit - V Ubiquitous Clouds and the Internet of Things 6
Cloud Trends in supporting Ubiquitous Computing – Performance of Distributed Systems and the Cloud – Enabling technologies
for the Internet of Things – Innovative Applications of the Internet of Things – Online Social and Professional Networking.

List of Exercises / Experiments:

1. Find procedure to run the virtual machine of different configuration. Check how many virtual machines can be utilized at
particular time in host machine. (Virtual Box or VM Ware or Hyper-V)
2. Install a C compiler in the virtual machine and execute a sample program.
3. Show the virtual machine migration from one node to another.
4. Develop a web application to provide Storage as a Service that offers a simple interface which allows users to manage file
systems quickly and easily.
5. Explore public cloud services like Amazon, Google and Azure.
6. Configure IaaS architecture for installing guest operating system using OpenNebula.
7. Configure IaaS architecture in Nimbus for installing multiple operating systems in same host machine by sharing different
core in the same processor.
8. Implement PaaS-Mobile sensor based IoT application hosted via PaaS environment

Lecture:30, Practical:30, Total:60

TEXT BOOK:

1. Kai Hwang, Geoffrey C Fox & Jack G Dongarra, "Distributed and Cloud Computing, From Parallel Processing to the Internet
of Things", 1st Edition, (Reprint) Morgan Kauffmann, 2017. for Unit I, II, III, IV and V.

REFERENCES/MANUAL/SOFTWARE:

1. VMware, Google App Engine

2. C/Python/Java

[Link] Artificial Intelligence and Data Science - R2020 Page 132

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 explain the concepts, characteristics and benefits of Distributed System Models and apply the Applying (K3)
same for internet computing
CO2 describe the importance of virtualization along with their technologies and apply in virtual resource Applying (K3)
management
CO3 use and examine different cloud computing services Applying (K3)
CO4 analyze the components of Cloud Programming and Software Environments Applying (K3)
CO5 develop strategies for Ubiquitous Clouds and the Internet of Things Applying (K3)
CO6 demonstrate the use of cloud computing in various applications Applying (K3),
Precision (S3)
CO7 apply different cloud programming model for the real world problems Applying (K3),
Precision (S3)
CO8 develop and deploy cloud architecture and model Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
CO6 3 2 1 1 1 3 2
CO7 3 2 1 1 1 3 2
CO8 3 2 1 1 1 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 10 60 30 100
CAT2 10 60 30 100
CAT3 10 60 30 100
ESE 10 50 40 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 133

 Kongu Engineering College, Perundurai, Erode – 638060, India
NATURE INSPIRED OPTIMIZATION TECHNIQUES
(Common to AI & DS and AI & ML branches)

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites NIL 7 PE 3 0 0 3

Preamble This course provides an introduction to nature inspired techniques and applications.
Unit - I Introduction 9
Philosophy of Natural Computing - Three Branches: A Brief Overview - Conceptualization -Individuals- Entities and agents -
Parallelism and Distributivity - Interactivity – Adaptation - Feedback-Self-Organization-Complexity- Emergence and Reductionism-
Bottom-up Vs Top-Down - Determination- Chaos and Fractals.
Unit - II Computing Inspired By Nature 9
Evolutionary Computing- Hill Climbing and Simulated Annealing- Evolutionary biology - Darwin's Dangerous Idea- Genetics
Principles- Standard Evolutionary Algorithm - Genetic Algorithms - Selection-Crossover- Mutation- Neurocomputing- Artificial
neurons - network architectures- learning approaches - Hebbian learning- Single layer perceptron- Multi-layer perceptron - Self
organization maps- discrete Hopfield network.
Unit - III Swarm Intelligence 9
Introduction - Ant Colonies- Ant Foraging Behavior- Ant Colony Optimization- Simple ACO and scope of ACO algorithms- Ant
Clustering Algorithm (ACA)- Swarm Robotics- Foraging for food- Social Adaptation of Knowledge - Particle Swarm Optimization
(PSO) - Scope of PSO- social systems to particle swarm.
Unit - IV Immuno Computing 9
Introduction- Immune System - Physiology and main components- Pattern Recognition and Binding -adaptive immune response-
Self/Non-self discrimination- Immune Network Theory- Danger Theory- artificial immune systems- Evaluating Interaction -
Immune Algorithms- Bone Marrow Models - Negative selection algorithms- Clonal selection and affinity maturation- Artificial
Immune Networks.
Unit - V Computing With New Natural Materials 9
DNA Computing - Basic concepts - DNA Molecule - Filtering models- Adleman's experiment - Test tube programming language-
Formal models - Universal DNA Computers - Scope of DNA Computing - From Classical to DNA Computing - Quantum
computing- Introduction- basic concepts from quantum theory- principles from quantum mechanics.

Lecture:45, Total: 45
TEXT BOOK:
1. Leandro Nunes de Castro, "Fundamentals of Natural Computing, Basic Concepts, Algorithms and Applications", Chapman &
Hall/ CRC, Taylor and Francis Group, 1st Edition, 2007. for Unit I, II, III, IV and V.
2. Floreano D. and Mattiussi C., "Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies", MIT Press,
Cambridge, 1st Edition, 2008.

[Link] Artificial Intelligence and Data Science - R2020 Page 134

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 apply fundamental concepts in Nature Inspired Systems to solve computational problems. Applying (K3)
CO2 manipulate the evolutionary and neuro Computing techniques inspired by nature. Applying (K3)
CO3 implement collective intelligence of biological systems to computing. Applying (K3)
CO4 develop immune systems behavior to computing and optimization. Applying (K3)
CO5 make use of the characteristics of DNA computing and Quantum Computing. Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 2 3
CO2 3 2 1 2 3
CO3 3 2 1 2 3
CO4 3 2 1 2 3
CO5 3 2 1 2 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 45 35 100
CAT2 20 30 50 100
CAT3 20 30 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 135

 Kongu Engineering College, Perundurai, Erode – 638060, India
MODELING AND SIMULATION
(Common to AI & DS and AI & ML branches)

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 7 PE 3 0 0 3

Preamble This course focuses on applications of computer simulation and modelling to real world simple and complex
problems.
Unit - I Modeling Process 9
Classification of modeling – Steps of modeling – System Dynamics: Unconstrained Growth and Decay - Constrained Growth –
Drug Dosage – Force and Motion: Modeling Falling and Skydiving
Unit - II System Dynamics Models 9
Competition – Modeling of Competition – Predator – Prey Model – Modeling the spread of SARS – SIR Model– SAR Model –
Enzyme Kinetics – Enzymatic Reactions
Unit - III Data Driven Models 9
Functions – Empirical Models – Simulating with Randomness: Simulations – Random numbers from various distributions –
Random Walk
Unit - IV Cellular Automation 9
Diffusion – Spreading of Fire – Periodic Boundary Conditions – Movement of Ants – Formulating a Model - -High Performance
Computing: Concurrent Processing – Parallel Algorithms
Unit - V Matrix Models 9
Matrices for Population Studies – Population Matrices and High-Performance Computing -Time after Time – Age-Structured
Model- Modeling with Markov Chains- Problems from Psychology to Genetics

Lecture:45, Total:45

TEXT BOOK:
1. Angela B. Shiflet, George W. Shiflet, “Introduction to Computational Science: Modelling and Simulation for the Sciences”, 2 nd
Edition, Princeton University Press, 2014. for Unit I, II, III, IV and V.

[Link] Artificial Intelligence and Data Science - R2020 Page 136

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 model system dynamics with and without constraints Applying (K3)
CO2 construct models for systems with interactions Applying (K3)
CO3 make use of randomness and data for modelling Applying (K3)
CO4 utilize cellular automation for modelling natural processes and explain concurrent processing Applying (K3)
and parallel algorithms
CO5 apply matrix theory in problem solving Applying (K3)
Mapping of COs with POs and PSOs
COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 30 45 25 100
CAT2 10 45 45 100
CAT3 25 45 30 100
ESE 20 40 40 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 137

 Kongu Engineering College, Perundurai, Erode – 638060, India
INFORMATION SECURITY

Programme&
BTech – Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Computer Networks 7 PE 3 0 0 3

Preamble This course focuses on wide spectrum of topics from legal and ethical issue, risk management, and implementation
in the context of information security.
Unit - I Information Security and The Need for Security 9
The history of Information Security – CNSS Security model-Components of an Information System – Security in the system life
cycle – Security professionals and the organization – Communities of interest – Information Security: Threat and Attacks –
Compromises to intellectual property – Deviations in Quality of Service-Espionage – Force of nature – Human Error – Information
Extortion – Sabotage-Software attacks – Technical hardware failures – Technical software failures
Unit - II Issues in Information Security and Planning for Security 9
Law and ethics in information Security – Relevant U.S. Laws-International laws and legal bodies – Ethics and Information security
– Codes of ethics of professional organizations – Key U.S. Federal agencies – Planning for Security: Information security policy,
standards, and practices – The Information security blueprint – Security education, training, and awareness program
Unit - III Risk Management 9
Risk Identification: Planning and organizing the process – Identifying, inventorying and categorizing assets- Classifying and
prioritizing threats – Specifying asset vulnerabilities; Risk assessment : Planning and organizing risk assessment- Determining the
loss frequency – Calculating risk – Assessing risk acceptability – The FAIR approach to risk assessment – Risk control-
Quantitative versus qualitative risk management practices-Recommended risk control practices
Unit - IV Security Technology 9
Access Control: Access control mechanisms – Biometrics – Access control architecture models – Firewalls: Firewall processing
modes – Firewall architecture – Selecting the right firewalls – Configuring and managing firewalls – Content filters – Protecting
remote connections – Intrusion detection and prevention systems –Honeypots, Honeynets, and padded cell systems – Scanning
and analysis tools.
Unit - V Implementing Information Security and Security &Personnel 9
Information security project management – Technical aspects of implementation-Nontechnical aspect of implementation-
Information security certification and accreditation-Credentials for information security professionals-Employment policies and
practices-Security considerations for temporary employees, consultants, and other workers-Internal control strategies – Privacy
and the security of personnel data.

Lecture:45, Total:45

TEXT BOOK:

1. Michael E. Whitman and Herbert J. Mattord, “Principles of Information Security”, 6 th Edition, Cengage Learning, India, 2018.
for Unit I, II, III, IV and V.

REFERENCES:
1. Charles P. Pfleeger and Shari Lawrence Pfleeger, “Security in Computing”, 5 th Edition, Prentice Hall, 2018.
2 Micki Krause, Harold F. Tipton, “Handbook of Information Security Management”, Vol. 6, 6 th Edition, CRC Press, 2012.

[Link] Artificial Intelligence and Data Science - R2020 Page 138

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1: explore the basic concepts in information security and determine the type of attacks in a security Applying (K3)
breach
CO2: identify the legal, ethical, professional issues in information security and apply security policies, Applying (K3)
standards and practices
CO3: identify the risks involved in information security and carry out risk assessment Applying (K3)
CO4: utilize security technologies for protecting information Applying (K3)
CO5: make use of various aspects of implementing information security and, paraphrase the issues Applying (K3)
and concerns related to staffing the information security

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 2 1
CO2 3 2 1 2 1
CO3 3 2 1 2 1
CO4 3 2 1 2 1
CO5 3 2 1 2 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 60 20 100
CAT2 20 60 20 100
CAT3 20 60 20 100
ESE 20 60 20 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 139

 Kongu Engineering College, Perundurai, Erode – 638060, India
INFORMATION RETRIEVAL TECHNIQUES

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Applied Machine Learning 7 PC 3 0 0 3

Preamble This course discusses the basics of information retrieval, search engine operations and multimedia information
retrieval techniques.
Unit - I Introduction 9
Information Retrieval - The IR Problem - The users task - Information versus data retrieval - The IR System - Software
architecture of IR system - Retrieval and ranking processes - The web - Web changed search - Practical issues on the web - How
people search - Search interfaces today - Visualization in Search Interfaces
Unit - II Modeling and Retrieval Evaluation 9
Basic IR Models – Boolean Model – TF-IDF (Term Frequency/Inverse Document Frequency) Weighting – Vector Model –
Probabilistic Model – Latent Semantic Indexing Model – Neural Network Model – Retrieval Evaluation – Retrieval Metrics –
Precision and Recall – Reference Collection – User-based Evaluation
Unit - III Text Operations, Indexing and Searching 9
Text Properties - Document Preprocessing - Text Compression – Text Classification – Characterization of Text Classification –
Unsupervised Algorithms – Supervised Algorithms – Decision Tree – K-NN Classifier – SVM Classifier – Feature Selection or
Dimensionality Reduction – Evaluation Metrics – Accuracy and Error – Indexing and Searching – Inverted Indexes – Sequential
Searching – Multidimensional Indexing.
Unit - IV Web Retrieval and Web Crawling 9
The Web – Search Engine Architectures – Cluster Based Architecture – Distributed Architectures – Search Engine Ranking –
User Interaction –Browsing – Web Crawling – Applications of a Web Crawler – Taxonomy – Architecture and Implementation –
Scheduling Algorithms – Evaluation.
Unit - V Multimedia Information Retrieval 9
Content-based image retrieval – Audio and music retrieval – Retrieving and browsing video – Fusion models – Segmentation –
Compression and MPEG standards –Case study: Digital Library

Lecture:45;Total: 45
TEXT BOOK:

1. Ricardo Baeza-Yate, Berthier Ribeiro-Neto, “Modern Information Retrieval”, 2nd Edition, Pearson Education Asia, 2011 for
Unit I, II, III, IV and V.

REFERENCE:

1. Chowdhury G.G., “Introduction to Modern Information Retrieval”, 2 nd Edition, Neal-Schuman Publishers, 2003.

[Link] Artificial Intelligence and Data Science - R2020 Page 140

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 describe the basic concepts of information retrieval Applying (K3)
CO2 apply the various modeling techniques Applying (K3)
CO3 discuss the concepts of text operations, indexing and searching Applying (K3)
CO4 learn about web information retrieval and web crawling Applying (K3)
CO5 explore audio, music and video information retrieval techniques Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy
ASSESSMENT PATTERN - THEORY
Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 15 35 50 100
CAT2 15 35 50 100
CAT3 15 35 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 141

 Kongu Engineering College, Perundurai, Erode – 638060, India
REINFORCEMENT LEARNING
(Common to AI & DS and AI & ML branches)

Programme& Branch [Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Prerequisites NIL 7 PE 3 0 0 3

Preamble This course deals with modeling, analysis tools and techniques for problems of dynamic decision making under
uncertainty. It also deals with convergence and accuracy of such algorithms.

Unit - I Introduction and Basics of RL 9

Reinforcement Learning- Examples- Elements of Reinforcement Learning- Limitations and Scope- An Extended Example: Tic-Tac-
Toe- History of Reinforcement Learning.
Unit - II Tabular Solution Methods 9
Multi-arm Bandits - An n-Armed Bandit Problem- Action-Value Methods- Incremental Implementation- Tracking a Nonstationary
Problem- Optimistic Initial Values- Upper-Confidence-Bound Action Selection- Gradient Bandit- Associative Search.
Unit - III Finite Markov Decision Processes 9
The Agent–Environment Interface- Goals and Rewards- Returns- Unified Notation for Episodic and Continuing Tasks- The Markov
Property- Markov Decision Processes- Value Functions- Optimal Value Functions- Optimality and Approximation.
Unit - IV Dynamic Programming and Monte Carlo Methods 9
Dynamic Programming - Policy Evaluation- Policy Improvement- Policy Iteration- Value Iteration- Generalized Policy Iteration.
Monte Carlo Methods: Monte Carlo Prediction- Monte Carlo Estimation of Action Values- Monte Carlo Control- Monte Carlo Control
without Exploring Starts.
Unit - V Temporal-Difference Learning 9
TD Prediction- Advantages of TD Prediction Methods- Optimality of TD(0) -Sarsa: On-Policy TD Control- Q-Learning: Off-Policy TD
Control- Games, After states, and Other Special Cases

Lecture: 45, Total: 45

TEXT BOOK:
1 Richard S. Sutton and Andrew G. Barto, “Reinforcement Learning: An Introduction", 2 nd Edition, MIT Press, London, 2018. for
Unit I, II, III, IV and V.

REFERENCES:
1 Phill winder, “Reinforcement Learning: Industrial applications of intelligent agents", 1st Edition, O'Reilly Media, 2020.

[Link] Artificial Intelligence and Data Science - R2020 Page 142

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 illustrate RL tasks and the core principles behind the RL Applying (K3)
CO2 apply tabular methods to solve classical control problems Applying (K3)
CO3 utilize Markov decision process in optimization of complex problems Applying (K3)
CO4 solve problems using dynamic programming and Monte-Carlo methods Applying (K3)
CO5 outline temporal-difference learning and Q-learning Applying (K3)
Mapping of COs with POs and PSOs
COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 1 3 2
CO2 3 2 1 1 2 2
CO3 3 2 1 1 2 2
CO4 3 2 1 1 3 2
CO5 3 2 1 1 2 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 20 40 40 100
CAT2 20 50 30 100
CAT3 20 40 40 100
ESE 30 40 30 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 143

 Kongu Engineering College, Perundurai, Erode – 638060, India

HEALTH CARE ANALYTICS

Programme & [Link]. & Artificial Intelligence & Data

Sem. Category L T P Credit
Branch Science

Prerequisites Deep learning 7 PE 3 0 0 3

Preamble This course enables the students to learn and understand health data formats, frameworks and apply health care
analytics through machine learning and deep learning algorithms

Unit - I Introduction to healthcare analysis 9

Overview - History of Healthcare Analysis Parameters on medical care systems- Health care policy- Standardized code sets –
Data Formats – Machine Learning Foundations: Tree Like reasoning , Probabilistic reasoning and Bayes Theorem, Weighted sum
approach.
Unit - II Analytics on machine learnin 9

Machine Learning Pipeline – Pre-processing –Visualization – Feature Selection – Training model parameter – Evaluation model :
Sensitivity , Specificity , PPV ,NPV, FPR ,Accuracy , ROC , Precision Recall Curves , Valued target variables –Python: Variables
and types, Data Structures and containers , Pandas Data Frame :Operations – Scikit –Learn : Pre-processing , Feature Selection.

Unit – III Health care management 9

IOT- Smart Sensors – Migration of Healthcare Relational database to NoSQL Cloud Database – Decision Support System –
Matrix block Cipher System – Semantic Framework Analysis – Histogram bin Shifting and Rc6 Encryption – Clinical Prediction
Models – Visual Analytics for Healthcare.
Unit – IV Healthcare and deep learning 9

Introduction on Deep Learning – DFF network CNN- RNN for Sequences – Biomedical Image and Signal Analysis – Natural
Language Processing and Data Mining for Clinical Data – Mobile Imaging and Analytics – Clinical Decision Support System.

Unit – V Case studies 9

Predicting Mortality for cardiology Practice –Smart Ambulance System using IOT –Hospital Acquired Conditions (HAC) program-
Healthcare and Emerging Technologies – ECG Data Analysis.

Lecture:45;Total:45
TEXT BOOK
1. Chandan [Link], Charu C. Aggarwal, “Health Care data Analysis”, First edition, CRC, 2015. for Unit I, II, III, IV and V.

REFERENCE BOOKS
1. Vikas Kumar, “Health Care Analysis Made Simple”, Packt Publishing, 2018.
2. Nilanjan Dey, Amira Ashour , Simon James Fong, Chintan Bhatl, “Health Care Data Analysis and management, First Edition,
Academic Press, 2018.
3. Hui Jang, Eva [Link], “HealthCare Analysis : From Data to Knowledge to Healthcare Improvement”, First Edition, Wiley,
2016.
4. Kulkarni , Siarry, Singh ,Abraham, Zhang, Zomaya , Baki, “Big Data Analytics in HealthCare”, Springer, 2020.

[Link] Artificial Intelligence and Data Science - R2020 Page 144

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest
Level)
CO1 use machine learning and deep learning algorithms for health data analysis Applying (K3)
CO2 apply the data management techniques for healthcare data Applying (K3)
CO3 evaluate the need of healthcare data analysis in e-healthcare, telemedicine and other critical care
applications Applying (K3)

CO4 apply health data analytics for real time applications Applying (K3)
CO5 discuss about case studies in health data analysis Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 3 2
CO2 3 2 2 3 2
CO3 3 2 2 3 2
CO4 3 2 2 3 2
CO5 3 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating (K6)
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % %
CAT1 20 30 50 100
CAT2 20 30 50 100
CAT3 20 30 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 145

 Kongu Engineering College, Perundurai, Erode – 638060, India

TIME SERIES ANALYSIS AND FORECASTING

(Common to AI & DS and AI & ML branches)

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 7 PE 2 0 2 3

Preamble The course familiarizes students with various forecasting approaches and new statistical methods for analyzing
and evaluating time-series data.
Unit - I Exploratory analysis 6
Graphical displays – Numerical description of Time Series Data – Use of Data transformations and Adjustments –General
Approach to Time Series Modeling and Forecasting – Evaluating and Monitoring Forecasting Model Performance.

Unit - II Smoothing methods 6

First-Order Exponential Smoothing – Modeling Time Series data – Second-Order Exponential Smoothing – Higher- Order
Exponential Smoothing – Forecasting – Exponential Smoothing for Seasonal Data – Exponential Smoothing of Biosurveillance
data – Exponential Smoothers and ARIMA models.
Unit - III ARIMA models 6
Linear Models for Stationary Time Series – Finite Order Moving Average Processes – Finite Order Autoregressive Processes –
Mixed Autoregressive-Moving Average Processes – Nonstationary Processes – Time Series Model building – Forecasting ARIMA
Processes – Seasonal Processes – ARIMA Modeling of Biosurveillance data.
Unit - IV Transfer Functions and Intervention Models 6
Transfer Function Models – Transfer Function-Noise Models – Cross Validation Function – Model Specification – Forecasting with
Transfer Function-Noise Models – Intervention Analysis.
Unit - V Other Forecasting Methods 6
Multivariate Time Series Models and Forecasting – State Space Models – Arch and Garch models – Direct Forecasting of
Percentiles – Combining Forecasts to improve Prediction Performance – Aggregation and Disaggregation of Forecasts – Neural
Networks and Forecasting – Spectral Analysis – Bayesian Methods in Forecasting.

List of Exercises / Experiments:

1. Visualization of Stationary and Non-stationary time series data.
2. Implement Moving Average Time Series Model and Differencing.
3. Implement Exponential smoothing technique (Single, double and triple).
4. Implement Auto-Regressive Model for Stationary Time Series.
5. Implement Auto-Regressive Integrated Moving Average for Non-Stationary Time Series.
6. Apply Univariate Models to forecast data
7. Implement Transfer Functions and Autoregressive Distributed Lag Modeling.
8. Apply Spectral density function to forecast data.
Lecture: 30, Practical:30, Total:60

TEXT BOOK:
1. Douglas C. Montgomery, Cheryl L. Jennings, Murat Kulahci, “Introduction to Time Series Analysis and Forecasting”, 2 nd
Edition, Wiley, 2016. for Unit I, II, III, IV and V.

REFERENCE:
1. George E. P. Box, Gwilym M. Jenkins, Gregory C. Reinsel, Greta M. Ljung, “Time Series Analysis: Forecasting and Control”,
5th Edition, Wiley, 2016.

[Link] Artificial Intelligence and Data Science - R2020 Page 146

 Kongu Engineering College, Perundurai, Erode – 638060, India

REFERENCES/MANUAL/SOFTWARE:
1. Python

2. Laboratory Manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 understand the necessity of forecasting and apply in a given situation Applying (K3)
CO2 apply smoothing methods in time series data Applying (K3)
CO3 perform Stationary and Non-Stationary time series analysis Applying (K3)
CO4 make use of variance transformation techniques for time series analysis and forecasting Applying (K3)

CO5 understand and apply frequency-domain time series analysis Applying (K3)
CO6 implement models for stationary and non-stationary time series analysis Applying (K3),
Precision (S3)
CO7 make use of various smoothing methods for time series data analysis Applying (K3),
Precision (S3)
CO8 implement models for frequency-domain time series analysis Applying (K3),
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 3 2
CO2 3 2 2 3 2
CO3 3 2 2 3 2
CO4 3 2 2 3 2
CO5 3 2 2 3 2
CO6 3 2 2 2 2 3 2
CO7 3 2 2 2 2 3 2
CO8 3 2 2 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 10 50 40 100
CAT2 10 40 50 100
CAT3 10 40 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 147

 Kongu Engineering College, Perundurai, Erode – 638060, India

SOCIAL MEDIA ANALYTICS

(Common to AI & DS and AI & ML branches)

[Link]. & Artificial Intelligence and Data

Sem. Category L T P Credit
Programme & Science
Branch
Prerequisites Nil 7 PE 3 0 0 3

Preamble The course gives exposure to perform analytical operations on different types of data in social media
Unit - I Foundations of social media analytics 9
Creating value with Social media analytics – Understanding social media: Core characteristics – Understanding Social media
analytics: Emergence – layers – types – social media analytics value creation cycle – challenges – social media analytics
industry.
Unit - II Analytics Business Alignment and social media network analytics 9
Analytics Business Alignment : Digital analytics maturity model – Role of CIO and its management – Formulation of strategy.
Social media network analytics: Social network terms – network structures – network topologies – types of networks – network
strategies - Network analysis tools.
Unit - III Text and Social media actions analytics 9
Text Analytics : Types of social media text – deployment models – purpose – social media text analytics for Business
Intelligence – text analytics value creation cycle – common terms – issues – Case studies. Social media actions analytics:
Common social media actions - actions analytics tools -
Unit - IV Search Engine, location and hyperlink analytics 9
Search Engine analytics: types of search engines - working - analytics – developing search engine optimization strategy and
implementing – search engine data analytics - Location analytics: Sources of location data – data collection – location metrics –
tools. Social media hyperlink analytics: types – hyperlink analytics – tools.
Unit - V Mobile and multimedia analytics 9
Mobile analytics: types of apps- development perspective – classifying apps by their purpose – characteristics of mobile apps –
tools. Multimedia analytics: Types – image analytics tools - video analytics. Social media legal, privacy and security issues.

Lecture:45;Total:45
TEXT BOOK:
1. Gohar F. Khan. Creating Value With Social Media Analytics. 1st edition, Create space, 2018. for Unit I, II, III, IV and V.

REFERENCES:
1 Marshall Sponder. Social Media Analytics: Effective Tools for Building, Interpreting, and Using Metrics. 1 st edition,
McGrawHill, 2011.

[Link] Artificial Intelligence and Data Science - R2020 Page 148

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1: get familiar with basic foundations of social media analytics Understanding (K2)
CO2: recall concepts Analytics Business Alignment and social media network analytics Understanding (K2)
CO3: implement techniques for Text and Social media actions analytics Applying (K3)
CO4: demonstrate different methods for Search Engine, location and hyperlink analytics Applying (K3)
CO5: use Mobile and multimedia analytics for various real life social media applications Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 3 3 3 2
CO2 3 3 2 3 2
CO3 3 2 3 3 3
CO4 3 2 3 3 3
CO5 3 2 2 3 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT 1 15 30 55 100
CAT 2 15 30 55 100
CAT 3 15 30 55 100
ESE 15 30 55 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 149

 Kongu Engineering College, Perundurai, Erode – 638060, India

REAL TIME ANALYTICS

(Common to AI & DS and AI & ML branches)

[Link]. & Artificial Intelligence and Data

Programme &
Science Sem. Category L T P Credit
Branch

Prerequisites NIL 7 PE 3 0 0 3

Preamble This course provides a comprehensive knowledge about data analysis technologies to build an effective real-time
analytics platform.
Unit - I Streaming Data and analytics 9
Introduction to Streaming Data: Sources – Why Streaming Data is Different – Infrastructures and Algorithms. Streaming Analytics
Architecture: Real-Time Architecture Components – Feature of Real-Time Architecture – Languages for Real-Time programming
– A Real-Time Architecture Checklist.
Unit - II Processing and Storing Streaming Data 9

Processing Streaming Data: Distributed Streaming Data Processing – Processing Data with Storm: Components, Configuring of a
Storm Cluster – Distributed Clusters – Local Clusters – Storm Topologies. Storing Streaming Data : Consistent Hashing – No SQL
Storage Systems – Other Storage Technologies – Choosing a Technology – Warehousing.

Unit - III Visualization and Aggregation 9

Visualization: Visualizing Data – Mobile Streaming Applications – Exact Aggregation and Delivery: Timed Counting and
Summation – Multi –Resolution Time-Series Aggregation – Stochastic Optimization
Unit - IV Statistical Approximation of Streaming Data and Sketching 9
Statistical Approximation of Streaming Data: Sampling from a streaming Population – Biased Streaming Sampling. Sketching :
Registers and Hash Functions – Working with Sets – The Bloom Filter – Distinct Value Sketches – The Count-Min Sketch – Other
Applications
Unit - V Real-Time Models, Monitoring and Forecasting 9
Real-Time Models and Monitoring: Simple Time-Series Models – Linear Models – Logistic Regression – Neural Network Models
– Forecasting: Exponential Smoothing Methods – Regression Methods - Neural Network Methods. Monitoring: Outlier Detection -
Change Detection

Lecture: 45, Total: 45

TEXT BOOK:
1. Ellis, Byron. “Real-time analytics: Techniques to analyze and visualize streaming data”, John Wiley & Sons, 1st Edition, 2014
for Unit I, II, III, IV and V.

REFERENCE:

1. Goetz, P. Taylor, and Brian O'Neill, “Storm blueprints: patterns for distributed real-time computation”, Packt Publishing Ltd,
1st Edition, 2014.

[Link] Artificial Intelligence and Data Science - R2020 Page 150

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 describe the concepts of streaming data and analyze various architectures for streaming data Applying (K3)
CO2 make use of processing and storage techniques to build real time analytics applications Applying (K3)
CO3 apply visualization and aggregation techniques for real time analytics Applying (K3)
CO4 employ statistical approximation and sketching techniques for solving the real world problems Applying (K3)

CO5 develop models and use it for forecasting and monitoring to solve real time problems Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 3 2
CO2 3 2 1 2 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 2 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 10 20 30 40 100

CAT2 15 35 50 100

CAT3 20 40 40 100

ESE 20 20 40 20 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 151

 Kongu Engineering College, Perundurai, Erode – 638060, India

ETHICS OF AI

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 7 PE 3 0 0 3

Preamble
This course locates ethical analysis of artificial intelligence. It also interrogates artificial intelligence within the
context of related modes of technological innovation, including machine learning, Big Data, and robotics.

Unit - I Introduction 9
The Artificial Intelligence of the Ethics of Artificial Intelligence - The Ethics of the Ethics of AI - Ethical Issues in Our Relationship
with Artificial Entities.
Unit - II Frameworks and Modes 9
AI Governance by Human Rights - The Incompatible Incentives of Private-Sector AI - Normative Modes: Codes and Standards -
The Role of Professional Norms in the Governance of Artificial Intelligence
Unit - III Concepts and Issues 9
Moral Framework of Justice in Artificial Intelligence - Accountability in Computer Systems – Transparency - Responsibility and
Artificial Intelligence - The Concept of Handoff as a Model for Ethical Analysis.
Unit - IV Perspectives and Approaches 9
Perspectives on Ethics of AI - Social Failure Modes in Technology and the Ethics of AI - Social Failure Modes in Technology and
the Ethics of AI - Integrating Ethical Values and Economic Value.
Unit - V Cases and Applications 9
Ethics of Artificial Intelligence in Transport - The Case for Ethical AI in the Military - The Ethics of AI in Biomedical Research,
Patient Care, and Public Health - Ethics of AI in Law - Ethical AI in Criminal Law
Lecture: 45, Total: 45

TEXT BOOK:
1. Markus D. Dubber, Frank Pasquale, and Sunit Das, “Ethics of AI”, 1 st edition, Oxford University Press, USA, 2020. for Unit I,
II, III, IV and V.

REFERENCES:
1. S. Matthew Liao, “Ethics of Artificial Intelligence”, 1st edition, Oxford University Press, USA, 2020.
2. Mark Coeckelbergh, “AI Ethics”, 1st edition, MIT Press, USA, 2020.

[Link] Artificial Intelligence and Data Science - R2020 Page 152

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest
Level)
CO1 describe the Ethics of artificial intelligence in relation to cognitive fields of ethical inquiry Applying (K3)
CO2 articulates the AI ethics, in the context of different normative evaluation and governance frameworks. Applying (K3)

CO3 tackles central concepts and issues that may serve as points of departure for reflecting on the ethical Applying (K3)
dimensions and challenges of artificial intelligence
CO4 illustrates various perspectives and approaches of AI Ethics Applying (K3)
CO5 demonstrate the ethics of artificial intelligence in various cases and its applications Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 3 3 1
CO2 3 2 1 3 3 3 1
CO3 3 2 1 3 3 3 1
CO4 3 2 1 3 3 3 1
CO5 3 2 1 3 3 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total

Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %

CAT1 20 65 15 100

CAT2 20 65 15 100

CAT3 20 65 15 100

ESE 20 60 20 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 153

 Kongu Engineering College, Perundurai, Erode – 638060, India

NEURAL MACHINE TRANSLATION

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 7 PE 3 0 0 3

Preamble This course provides knowledge on basics of computer organization, introduces various arithmetic operations and
discusses the performance issues of processor, memory and I/O units.
Unit – I Introduction 9
Regular Expressions – Words - Corpora - Text Normalization - Minimum Edit Distance. N-gram Language Models: N-Grams -
Evaluating Language Models - Generalization and Zeros – Smoothing - Kneser-Ney Smoothing - The Web and Stupid Backoff -
Advanced: Perplexity’s Relation to Entropy
Unit – II Classification 9
Naive Bayes Classifiers - Training the Naive Bayes Classifier - Worked example - Optimizing for Sentiment Analysis - Naive
Bayes for other text classification tasks - Naive Bayes as a Language Model - Evaluation: Precision, Recall, F-measure - Test sets
and Cross-validation - Statistical Significance Testing
Unit - III Regression 9
Classification: the sigmoid - Learning in Logistic Regression - The cross-entropy loss function - Gradient Descent – Regularization
- Multinomial logistic regression - Interpreting models - Advanced: Deriving the Gradient Equation.
Unit - IV Vector Semantics and Embeddings 9
Lexical Semantics - Vector Semantics - Words and Vectors - Cosine for measuring similarity - TF-IDF: Weighing terms in the
vector - Applications of the tf-idf vector model - Optional: Pointwise Mutual Information (PMI) - Word2vec - Visualizing
Embeddings .- Semantic properties of embeddings - Bias and Embeddings - Evaluating Vector Models
Unit - V Models and Speech Tagging 9
Units - The XOR problem - Feed-Forward Neural Networks - Training Neural Nets - Neural Language Models. Parts of Speech
Tagging: English Word Classes - The Penn Treebank Part-of-Speech Tagset - Part-of-Speech Tagging - HMM Part-of-Speech
Tagging - Maximum Entropy Markov Models – Bidirectionality - Part-of-Speech Tagging for Morphological Rich Languages,

Lecture: 45, Total: 45

TEXT BOOK:

1. Daniel Jurafsky, and James H. Martin “Speech and Language Processing An Introduction to Natural Language Processing,
Computational Linguistics, and Speech Recognition”, 2nd Edition, Pearson Education India;, 2013. for Unit I, II, III, IV and V.

REFERENCES:

1. Philipp Koehn, “Neural Machine Translation”, 1st edition, Cambridge University Press, United Kingdom, 2020.
2. Cyril Goutte, Nicola Cancedda, Marc Dymetman, George Foster, Masao Utiyama,“Learning Machine Translation”, MIT Press
, United States, 2009

[Link] Artificial Intelligence and Data Science - R2020 Page 154

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 describe the regular expression and n-gram models Applying (K3)
CO2 make use of Classification to solve the problem Applying (K3)
CO3 make use of Regression to solve the problem Applying (K3)
CO4 create Vector Semantics by learning representations of the meaning of words Applying (K3)
CO5 apply the Neural language models to the simple task of language modeling: Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 60 20 100
CAT2 20 50 30 100
CAT3 20 55 25 100
ESE 20 40 40 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 155

 Kongu Engineering College, Perundurai, Erode – 638060, India

MULTI VARIATE DATA ANALYSIS

Programme & [Link]. & Artificial Intelligence & Machine Learning Sem. Category L T P Credit
Branch
Prerequisites Multivariate Data Analysis 7 PE 3 0 0 3

Preamble This course enables the students to learn various multivariate data analysis

Unit - I Introduction to Multivariate Methods 9

Multivariate Analysis - Basic Concepts – Managing the Multivariate model – Classification of multivariate techniques – Types of
multivariate techniques – Guidelines for multivariate analyses and interpretation – Approach to multivariate modeling
Unit - II Preparing for Multivariate Analysis 9
Introduction – Examination of the Data : Univariate – Bivariate – Multivariate – Missing Data : Impact – Missing Data Analysis –
Process for identifying missing data and remedies – Outliers: Contexts for defining outliers – impact – classifying outliers –
detecting and handling outliers – example – Testing the assumptions of multivariate Analysis – Data transformations – Illustrating
of testing the assumptions
Unit – III Interdependence Techniques 9
Exploratory Factor Analysis : Introduction- Examples – Factor analysis decision process – Stages – Illustration -Cluster
Analysis : Introduction to cluster analysis – working - Cluster analysis decision process : Stages - Illustration
Unit – IV Dependence Technique 9
Introduction to Multiple Regression Analysis – Simple and Multiple Regression – Decision process for multiple regression analysis
– Stages – Illustration
Unit – V MANOVA 9
Introduction to MANOVA – Illustration – Decision process for MANOVA – Stages : Objectives – Issues – Assumptions of ANOVA
and MANOVA – Estimation of MANOVA model and Assessing overall Fit – Interpretation of MANOVA results - Validation

Lecture: 45, Total: 45

TEXT BOOK:

1. Joesph F. Hair Jr., William C. Black, Barry J. Babin, Rolph [Link] “Multivariate Data Analysis”, Annabel Ainscow, Eigth
Edition (2019). for Unit I, II, III, IV and V.

REFERENCES:

1. Spencer, N. H. Essentials of multivariate data analysis. CRC press, (2013).

[Link] Artificial Intelligence and Data Science - R2020 Page 156

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 perform multivariate modeling by classifying and Interpreting multivariate data Applying (K3)
CO2 examine multivariate data for missing data and outliers to perform multivariate Applying (K3)
analysis
CO3 assess the interdependence using factor and cluster analysis Applying (K3)
CO4 explore the dependence relationship between variables using multiple Applying (K3)
regression analysis
CO5 test the statistical significance of the effect of one or more independent Applying (K3)
variables on a set of two or more dependent variables, using MANOVA
Mapping of COs with POs and PSOs
COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 3 2
CO2 3 2 2 3 2
CO3 3 2 2 3 2
CO4 3 2 2 3 2
CO5 3 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 40 40 20
CAT2 20 30 50
CAT3 30 30 40
ESE 20 30 50
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 157

 Kongu Engineering College, Perundurai, Erode – 638060, India
COGNITIVE SCIENCE AND ANALYTICS

Programme &
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Data analytics 7 PE 3 0 0 3

Preamble To impart knowledge on cognitive science and various analytical methods

Unit – I Introduction to Cognitive Science 9
The Foundation of Cognitive Computing - Design Principles for Cognitive Systems: Components of a Cognitive System - Building
the Corpus- Bringing Data into the Cognitive System - Machine Learning - Hypotheses -Generation and Scoring - Presentation
and Visualization Services.
1.
Unit - II Natural Language Processing, Big Data and Cognitive Computing 9
Natural Language Processing in Support of a Cognitive System - The Relationship Between Big Data and Cognitive Computing:
Dealing with Human-Generated Data - Defining Big Data - The Architectural Foundation for Big Data - Analytical Data
Warehouses - Hadoop - Data in Motion and Streaming Data - Integration of Big Data with Traditional Data.
Unit - III Taxonomies and Ontologies, Cloud and Distributed Computing 9
Representing Knowledge in Taxonomies and Ontologies - Applying Advanced Analytics to Cognitive Computing - The Role of
Cloud and Distributed Computing in Cognitive Computing.
Unit - IV 1. The Process of Building Cognitive Applications 9
The Business Implications of Cognitive Computing - IBM’s Watson as a Cognitive System - The Process of Building a Cognitive
Application - Smarter Cities: Cognitive Computing in Government.
Unit - V Applications and case studies 9

Building a Cognitive Healthcare Application -Emerging Cognitive Computing Areas - Future Applications for Cognitive Computing.

Lecture: 45, Total: 45

TEXT BOOK:

Judith S. Hurwitz, Marcia Kaufman, Adrian Bowles. Cognitive Computing and Big Data Analytics. 1 st edition, Wiley, 2015. for
1.
Unit I, II, III, IV and V.

[Link] Artificial Intelligence and Data Science - R2020 Page 158

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1: describe the basic concepts of cognitive science Understanding (K2)
CO2: interpret the principles of Natural Language Processing and Big Data with Cognitive Understanding (K2)
Computing
CO3: exploreTaxonomies and Ontologies and Cloud and Distributed Computing in cognitive Understanding (K2)
environment
CO4: implement Watson for Cognitive system and develop applications Applying (K3)

CO5: demonstrate case studies of applying cognitive computing for various real life Applying (K3)
problems

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 3 3 3 2
CO2 3 3 2 3 2
CO3 3 2 3 3 3
CO4 3 2 3 3 3
CO5 3 2 2 3 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying (K3) Analyzing Evaluating Creating (K6) Total
Category* (K1) % (K2) % % (K4) % (K5) % % %
CAT 1 40 60 100
CAT 2 40 45 15 100
CAT 3 40 45 15 100
ESE 40 45 15 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 159

 Kongu Engineering College, Perundurai, Erode – 638060, India
GRAPH THEORY AND ITS APPLICATIONS
(Common to AI & DS and AI & ML branches)

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites NIL 7 PE 3 0 0 3

Preamble To develop rigorous logical thinking and analytical skills by graph theoretic concepts which helps for solving real time
engineering problems in networks, computer architecture, compiling techniques, model checking, artificial
intelligence, software engineering, expert systems, software/hardware correctness problem.
Unit - I Graphs: 9
Introduction – Definition – Types of graphs – Degree of vertex – Walk, path and cycle – Isomorphism – Connected graph –
Hamiltonian graph – Euler graph – Digraph – Representations of graphs: Adjacency matrix – Incidence matrix.
Unit - II Trees: 9
Introduction – Properties of trees – Pendant vertices in a tree – Distances and centers in a tree – Rooted and binary trees –
Spanning tree – Construction of spanning tree: BFS algorithm – DFS algorithm – Tree traversal.
Unit - III Graph Coloring: 9
Vertex coloring – Chromatic number – Chromatic partitioning – Independent sets – Chromatic polynomial – Matching – Covering –
Four color problem (statement only) – Simple applications.
Unit - IV Basic Algorithms: 9
Shortest paths – Shortest path algorithms: Dijkstra's algorithm – Warshall's algorithm – Minimum Spanning tree – Minimal
spanning tree algorithms: Prim’s algorithm – Krushkal's algorithm – Optimal assignment – Kuhn and Munkres algorithm –
Travelling salesman problem: Two optimal algorithm – Closest Insertion Algorithm.
Unit - V Network Flows and Applications: 9
Flows and cuts in networks - Max-flow Min-cut Theorem – Algorithms: Flow Augmenting Path – Ford-Fulkerson Algorithm for
Maximum Flow – Edmonds and Karp algorithm.

Lecture:45, Total:45
TEXT BOOK:
1. NarsinghDeo, "Graph Theory with Applications to Engineering and Computer Science", Prentice Hall, New Delhi, 2010. for
Unit I, II, III, IV and V.

REFERENCES:
1. Douglas [Link], "Graph Theory", 2nd Edition, Prentice Hall, New Delhi, 2017.
2. Jonathan L. Gross & Jay Yellen, "Graph Theory and its Applications", 2nd Edition, CRC Press, New York, 2006.

[Link] Artificial Intelligence and Data Science - R2020 Page 160

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 explain the types of graphs and illustrate isomorphism on graphs. Understanding (K2)
CO2 use the concepts and properties of different types of trees in data structures. Applying (K3)
CO3 estimate the chromatic partition, chromatic polynomial and matching of a given graph. Applying (K3)
CO4 apply various graph theoretic algorithms to communication and network problems. Applying (K3)
CO5 identify the maximal flow in network by means of algorithms. Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 2
CO2 3 1 3 2
CO3 3 1 3 2
CO4 3 2 1 3 2
CO5 3 2 1 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 10 50 40 100
CAT2 10 30 60 100
CAT3 10 30 60 100
ESE 10 30 60 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 161

 Kongu Engineering College, Perundurai, Erode – 638060, India
SEMESTER VIII

SOFTWARE DEFINED NETWORKS

(Common to AI & DS and AI & ML branches))

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Computer Networks 8 PE 3 0 0 3

Preamble This course provides an insight on programmability protocols, interfaces, controllers and its applications in various
environments like data centers and service provider networks.
Unit - I Introduction to SDN 9
Introduction: Basic packet switching terminology – The modern data center – Traditional switch architecture – Autonomous and
dynamic forwarding table. Evolution of switches and control planes – Cost – Data center innovation – Data center needs. The
Genesis of SDN: The evolution of networking technology – Forerunners of SDN – Getting started with mininet and experimenting
with mininet.
Unit - II SDN and OpenFlow 9
Fundamental characteristics of SDN – SDN operation – SDN devices – SDN controllers – Alternate SDN methods. The
OpenFlow specification: OpenFlow overview – OpenFlow 1.0 and OpenFlow basics - OpenFlow 1.1 Additions - OpenFlow 1.2
Additions - OpenFlow 1.3 Additions – OpenFlow Limitations. NetApp Development: Simple forwarding in OpenDayLight
controller.
Unit - III SDN Interfaces 9
Alternative definitions of SDN: Potential drawbacks of open SDN – SDN via APIs- SDN via hypervisor based overlays – SDN via
opening up the device – Network Functions virtualization – Alternatives overlap and ranking. SDN open source: Open source
licensing issues – OpenFlow source code – Switch implementation – Controller implementations – Orchestration and Network
virtualization – Simulation, Testing and Tools – OpenStack – Applying SDN open source
Unit - IV SDN in the Data center 9
Data center definition – Data center demands – Tunneling technologies for the data center – Path technologies in the data center
– SDN and shortest path complexity – Ethernet fabrics in the data center – SDN use cases in the data center – Open SDN versus
Overlays in the data center – Real-world data center implementation.
Unit - V SDN environments and applications 9
SDN in other environment – Wide area networks – Service provider and carrier networks – Campus networks – Hospitality
networks – Mobile networks – In-Line network functions – Optical networks. SDN Applications: Reactive versus Proactive
applications – A simple reactive Java application – Creating network virtualization tunnels – offloading flows in the data center –
Access control for the campus – Traffic engineering for the service providers –NetApp Development: A simple Firewall.

Lecture:45, Total:45

TEXT BOOK:
1. Paul Goransson and Chuck Black, "Software Defined Networks: A Comprehensive Approach", 1 st Edition, Morgan Kaufmann,
2014.

REFERENCES:
1. SiamakAzodolmolky, "Software Defined Networking with OpenFlow", Packet Publishing, 1 st Edition, 2013.
2. Thomas D. Nadeau and Ken Gray, "SDN: Software Defined Networks", O'Reilly Media, 1st Edition, 2013.
COURSE OUTCOMES: BT Mapped
On completion of the course, the students will be able to (Highest Level)
CO1 apply the programmability in the network using software defined network Applying (K3)
CO2 model a networking task using OpenFlow protocol Applying (K3)
CO3 demonstrate the networking application using software defined network interfaces and open source Applying (K3)
tools
CO4 employ the software defined network architecture in the data centers Applying (K3)
CO5 design and develop various applications of SDN Applying (K3)

[Link] Artificial Intelligence and Data Science - R2020 Page 162

 Kongu Engineering College, Perundurai, Erode – 638060, India

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 1 3 1
CO2 3 2 1 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 10 30 60 100
CAT2 15 25 60 100
CAT3 15 25 60 100
ESE 10 30 60 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 163

 Kongu Engineering College, Perundurai, Erode – 638060, India
SOFTWARE QUALITY AND TESTING
(Common to AI & DS and AI & ML branches)

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Software Engineering 8 PE 3 0 0 3

Preamble This course focuses on the implementation of appropriate functionality that satisfies the requirements/needs of its
targeted client/users for the intended software system, product, or service correctly and efficiently.
Unit - I Software Quality Assurance and Review Techniques 9
Defining Quality – Importance of Quality –Quality Control Vs Quality assurance –Quality assurance at each phase of SDLC -
Need for SQA group in an Organization. Structured walkthroughs –Inspections –Various roles and responsibilities involved in
Inspections –Making review successful.
Unit - II Software Measurement and Metrics 9
Product quality – Models for software product Quality – Process Quality Aspects. Measurement and Metrics: Introduction –
Measurement during software life cycle context –Defect metrics – Metrics for software maintenance– Requirements related
metrics – Measurements and process improvement – Measurement principles.
Unit - III Basics of Testing 9
Introduction – Definition– Testing Approaches – Essentials – features and principles of software Testing. Testing Environment:
Assessing Capabilities – Staff Competency and User Satisfaction – Creating an environment supportive of software testing –
Building the software testing process: Testing Guidelines.
Unit - IV Software Testing process 9
Overview of Software Testing Process – Organizing for testing: Workbench – Input – Procedure. Developing the test
plan:Workbench – Input – [Link] testing: Workbench – Input – Procedure. Validation testing :Workbench – Input –
Procedure.
Unit - V Analyzing and reporting 9
Analyzing and reporting test results: Workbench – Input – Procedure. Testing software system security – Testing client/server
systems – Testing web-based systems – Using Agile Methods to Improve Software Testing.

Lecture:45, Total:45

TEXT BOOK:
1. Nina S. Godbole, "Software Quality Assurance Principles and Practice", 2 ndEdition, Narosa Publishing House, 2017 for Unit I,
II, III, IV and V.
2. Perry William, "Effective Methods for Software Testing", 3 rd Edition, Wiley, India, 2013 (Units 3,4,5)

[Link] Artificial Intelligence and Data Science - R2020 Page 164

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 apply quality assurance steps at each phase of SDLC and conduct reviews and inspections Applying (K3)
CO2 apply the concepts, metrics, and models in software quality assurance Applying (K3)
CO3 apply the step by step activities and set up environment for software testing Applying (K3)
CO4 develop procedures and workbenches for various testing process Applying (K3)
CO5 apply testing for client server, web based and software security systems and identify the agile methods Applying (K3)
for improving the testing process

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 30 50 20 100
CAT2 20 50 30 100
CAT3 20 50 30 100
ESE 25 30 45 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 165

 Kongu Engineering College, Perundurai, Erode – 638060, India
SOFTWARE PROJECT MANAGEMENT
(Common to AI & DS and AI & ML branches)

Programme&
[Link].& Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 8 PE 3 0 0 3

Preamble This course provides an insight into detailed project management activities including project evaluation, planning,
estimation, monitoring and control activities especially for software projects.
Unit - I Introduction to Software Project Management 9
Introduction - Importance – Types of project – Activities – Plans, methods and methodologies – Ways of Categorizing software
projects – Stakeholders – Setting objectives – Business case – Project success and failure - Management and management
control – Traditional vs. Modern project management practices. Project Evaluation: Introduction – A business case – Project
Portfolio Management – Evaluation of Individual Projects – Cost Benefit Evaluation Techniques – Risk Evaluation – Programme
management – Managing the allocation of resources within programme – Strategic programme management – Creating a
programme – Aids – Reservations – Benefits.
Unit - II Project Planning 9
Introduction – Select project - Identify project scope and objectives, project infrastructure – Analyse project characteristics –
Identify project products and activities – Estimate effort for activity – Identify activity risks - Allocate Resources – Review plan –
Execute plan. Software Effort Estimation : Introduction – Estimates – Problems with over and under estimates – Basis –
Techniques – Bottom-up Estimating – Top down approach and parametric models – Expert Judgement – Estimating by analogy –
Albrecht FP – FP Mark II - COSMIC FFP – COCOMO II.
Unit - III Activity Planning 9
Objectives – Project Schedule – Projects and Activities – Sequencing and Scheduling Activities –Network Planning Models –
Formulation –Time dimension - Forward Pass – Backward Pass – Identifying the critical path - Activity Float – Shortening Project
Duration – Identifying critical activities – Activity on Arrow Networks. Risk Management: Risk – Categories of Risk – Framework –
Risk Identification – Risk Assessment – Risk Planning – Risk management – Applying PERT Technique – Monte Carlo Simulation
– Critical chain concepts.
Unit - IV Monitoring and Control 9
Creating Framework – Collecting The Data – Review - Visualizing Progress – Cost Monitoring – Earned Value Analysis –
Prioritizing Monitoring – Getting Project Back To Target – Change Control. Managing Contracts: Introduction – Types of Contract
– Stages In Contract Placement – Typical Terms of A Contract – Contract Management – Acceptance.
Unit - V Managing People 9
Introduction – Understanding Behaviour – Organizational Behaviour: A Background – Selecting The Right Person For The Job –
Instruction in the best methods – Motivation – The Oldham–Hackman Job Characteristics Model – Stress –Health and Safety.
Working in Teams: Introduction – Becoming A Team –Decision Making– Organizational & Team Structures – Coordination
Dependencies – Dispersed and virtual teams – Communication Generes – Communication Plans – Leadership.

Lecture:45, Total:45
TEXT BOOKS:
1. Bob Hughes, Mike Cotterell and Rajib Mall, “Software Project Management”, 6 th Edition, Tata McGraw Hill, New Delhi, 2017.
for Unit I, II, III, IV and V.
2. Pankaj Jalote, “Software Project Management in Practice”, 8 th Edition, Pearson, 2002.
3. Watts S. Humphrey, “PSP: A self-improvement process for software engineers”, 1 stEdition, Addison-Wesley, 2005.

[Link] Artificial Intelligence and Data Science - R2020 Page 166

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 make use of process of software project management and apply evaluation technique to choose best Applying (K3)
project.
CO2 prepare the project plan and calculate the efforts required. Applying (K3)
CO3 plan, schedule and sequence the activities and determine the risks. Applying (K3)
CO4 develop visualization charts to monitor the progress of projects and to control the risks involved. Applying (K3)
CO5 apply the methods of managing people and organising teams while developing a software project. Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 35 45 100
CAT2 20 45 35 100
CAT3 20 35 45 100
ESE 10 45 45 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 167

 Kongu Engineering College, Perundurai, Erode – 638060, India
CYBER FORENSICS
(Common to AI & DS and AI & ML branches)

Programme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 8 PE 3 0 0 3

Preamble This course imparts fundamental principles and techniques for digital forensics investigation and security
management.
Unit - I Computer Forensics and Investigations 9
Understanding computer forensics - Preparing Computer investigations – Taking a systematic approach –Assessing the case –
Planning Investigation – Securing evidence– Procedures for Corporate High-Tech investigations – Conducting an Investigation –
Completing the case.
Unit - II Data Acquisition 9
Understanding storage formats for digital evidence – Determining the best acquisition method - Contingency planning for image
acquisitions – Using Acquisition tools: Windows XP Write-protection with USB Devices – Validating Data Acquisitions: Windows
Validation Methods – Performing RAID Data Acquisitions – Using Remote Network Acquisition tools – Using other Forensics
Acquisition tools.
Unit - III Processing Crime and Incident Scenes 9
Identifying Digital Evidence – Collecting Evidence in Private Sector Incident Scenes –Processing Law Enforcement Crime Scenes
– Preparing for a Search –Securing a Computer Incident or Crime Scene –Seizing Digital Evidence at the Scene –Storing Digital
Evidence –Obtaining a Digital Hash –Reviewing a Case.
Unit - IV Computer Forensics Tools, Analysis and Validation 9
Evaluating Computer Forensics Tool Needs –Computer Forensics Software Tools – Computer Forensics Hardware Tools –
Validating and Testing Forensic Software – Computer Forensics Analysis and Validation: Determining Data Collection and
Analysis –Validating Forensic Data –Addressing Data-Hiding Techniques –Performing Remote Acquisitions.
Unit - V Recovering Graphics Files, Email Investigations 9
Recognizing a Graphics File– Understanding Data Compression – Locating And Recovering Graphic Files- Identifying Unknown
File Formats– Understanding Copyright Issues –Investigating Email Crimes And Violations- Understanding Email Servers– Using
Specialized Email Forensics Tools.

Lecture:45, Total:45

TEXT BOOK:
1. Nelson Bill, Phillips Amelia and Steuart Christopher, “Guide to Computer Forensics and Investigations”, 3 rd Edition, Cengage
Learning, 2017. for Unit I, II, III, IV and V.

[Link] Artificial Intelligence and Data Science - R2020 Page 168

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 apply systematic approach for digital forensic investigation Applying (K3)
CO2 carry out acquisition of data using various tools Applying (K3)
CO3 determine the seizure of digital evidence in a crime scene Applying (K3)
CO4 make use of forensic tools in forensic examination Applying (K3)
CO5 carry out investigationusing E-mail and graphic files Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 3 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 15 35 50 100
CAT2 15 35 50 100
CAT3 15 35 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 169

 Kongu Engineering College, Perundurai, Erode – 638060, India
AGILE METHODOLOGIES FOR SOFTWARE DEVELOPMENT
(Common to AI & DS and AI & ML branches)

Pogramme&
[Link]. & Artificial Intelligence and Data Science Sem. Category L T P Credit
Branch
Prerequisites Nil 8 PE 3 0 0 3

Preamble This course introduces agile methodologies such as Scrum, Extreme Programming (XP), Lean, and Kanban.
Unit - I Agile Principles: 9
Understanding the Agile Values – Silver Bullet Methodology – Agile to the Rescue – A fractured perspective - Agile Manifesto
and Purpose behind each practice – Agile Elephant – Where to start with a new Methodology – 12 principles of Agile Software –
The Customer is always Right – Delivering the project – Communicating and Working Together – Project Execution – Constantly
improving the project and the team – Agile Project.
Unit - II Scrum and Self-Organizing Teams: 9
Basic pattern for a Scrum Project – Rules of Scrum – Command-and-Control Team – Self-Organizing Teams - Scrum Values –
Daily Scrum – Sprints, Planning and Retrospectives.
Unit - III Scrum Planning and Collective Commitment: 9
User stories – Conditions of Satisfaction – Story Points and Velocity – Burndown Charts – Planning and Running a Sprint – GASP
– Scrum Values Revisited – Practices Do Work Without the Values – Company Culture Compatible with Scrum Values.
Unit - IV XP and Incremental Design: 9
Primary Practices of XP – The XP values help the team change their mindset – An effective mindset starts with the XP values –
Understanding the XP principles – Feedback Loops – Code and Design – Make Code and Design Decisions at the Last
Responsible Moments – Incremental Design and the Holistic XP.
Unit - V Lean, Kanban and Agile Coach: 9
Lean Thinking – Commitment, Options Thinking and Set Based Development – Create Heroes and Magical Thinking – Eliminate
Waste – Value Stream Map – Deliver As Fast As Possible – WIP Area Chart – Pull Systems – The Principles of Kanban –
Improving Your Process with Kanban – Measure and Manage Flow – Little’s Law – Emergent Behavior with Kanban – The Agile
Coach – Shuhari - The Principles of Coaching. .
Lecture:45; Total 45
TEXT BOOK:
1. Andrew Stellman and Jennifer Greene, “Learning Agile: Understanding Scrum, XP, Lean and Kanban”, First Edition, O’Reilly
Media Inc, 2015. for Unit I, II, III, IV and V.

REFERENCES
1. Eric Brechner, “Agile Project Management with Kanban”, First Edition, Microsoft Press, 2015.
2. Robert C. Martin, “Agile Software Development: Principles, Patterns, and Practices”, Pearson Prentice Hall, 2011.

[Link] Artificial Intelligence and Data Science - R2020 Page 170

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 outline the purpose of agile’s core principles and apply for project development Applying (K3)
CO2 utilize the scrum’s emphasis on project management and self-organization Applying (K3)
CO3 experiment with practices like user stories, story points, project velocity and visualization tools Applying (K3)
CO4 model applications using XP practices and incremental design Applying (K3)
CO5 make use of Lean thinking to empower a team, eliminate waste, and deliver software fast and learn how Applying (K3)
Kanban’s practices help deliver great software by managing flow

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 1 1 1 3 2
CO2 3 2 1 1 1 1 3 2
CO3 3 2 1 1 1 1 3 2
CO4 3 2 1 1 1 1 2 2
CO5 3 2 1 1 1 1 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT 1-50 marks 30 40 30 100
CAT 2-50 marks 10 50 40 100
CAT 3-50 marks 25 45 30 100
ESE -100 marks 20 40 40 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 171

 Kongu Engineering College, Perundurai, Erode – 638060, India

OPEN ELECTIVE
DEEP LEARNING FOR ENGINEERING APPLICATIONS

Programme&
BE/BTech All branches except AI&ML and AI&DS Sem. Category L T P Credit
Branch
Prerequisites Python Programming 4 OE 3 0 2 4

Preamble This course is designed to impart the skills required to build deep neural network architectures for various
applications.
Unit - I Neural Networks 9
Introduction – Basic Architecture of Neural Networks – Training Neural Network with Backpropagation - Practical Issues in Neural
Network Training - Power of Function Composition – Common Neural Architectures – Neural Architectures : Binary Classification
Models – Multiclass Models
Unit - II Training Deep Neural Networks 9

Introduction – Backpropagation- Setup and Initialization Issues – Vanishing and Exploding Gradient Problems – Gradient Descent
Strategies – Batch Normalization - Bias- Variance Trade-Off – Generalization Issues in Model Tuning and Evaluation
Unit - III Convolution Neural Networks 9
Introduction – Basic Structure of Convolutional Network – Training a Convolutional Network - Case Studies of Convolutional
Architectures - Applications of Convolutional Networks
Unit - IV Python Frameworks for Deep Learning 9
Introduction to TensorFlow- working with keras – steps in deep Learning Models-load data-preprocess data-define the model-
compile the Model-fit the Model-Evaluate the Model-Prediction-Multilayer Perceptron-CNN in Tensor Flow-CNN in Keras

Unit - V Case Studies 9

Image classifier for MNIST data - CIFAR data - Malaria Diseases detection - Heart disease detection - Leaf disease detection –
Covid Identification

List of Exercises / Experiments:

1. Study the methods in Tensorflow / Keras / OpenCV library
2. Create a multi-layer neural network and apply it to MNIST dataset.
3. Create a Multi-layer neural network to perform binary classification
4. Test the performance of multi-layer neural network with various activation and loss functions and tune the performance
with hyper parameters
5. Develop a hand written character recognition application using CNN
6. Implement CNN for malaria disease detection
7. Implement CNN for heart disease detection
8. Develop a CNN model for Covid detection
Lecture:45, Practical:30, Total:75
TEXT BOOK:

1. Charu C. Aggarwal, “Neural networks and deep learning”, Springer, 2018. for Unit I, II, III.
2. Navin Kumar Manaswi, “Deep Learning with Applications using Python”, Apress, 2018. for Unit IV and V.

REFERENCES:
1. Ian Goodfellow, YoshuaBengio, and Aaron Courvill, “Deep Learning”, MIT Press, USA, 2016.
2. Josh Patterson and Adam Gibson, “Deep Learning – A Practitioner’s Approach”, First Edition, O’Reilly Series, August 2017.

3. Indra den Bakker, “Python Deep Learning Cookbook”, First Edition, Packt Publishing, October 2017.

[Link] Artificial Intelligence and Data Science - R2020 Page 172

 Kongu Engineering College, Perundurai, Erode – 638060, India

REFERENCES/MANUAL/SOFTWARE:
1. Operating System : Linux / Windows
2. Software : Python / Keras / Tensorflow / OpenCV
3. Laboratory Manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 use Artificial Neural Network .concepts to solve real world problems Applying (K3)
CO2 solve simple real world problems using deep neural networks. Applying (K3)
CO3 exemplify the concepts of CNN models and apply it for solving problems. Applying (K3)
CO4 use python frameworks for implementing CNN Applying (K3)
CO5 demonstrate the application of deep learning for real world problems Applying (K3)
CO6 perform classifications using Multi-neural Networks Applying (K3)
Precision (S3)
CO7 demonstrate the performance of Multi-neural Networks on different parameters Applying (K3)
Precision (S3)
CO8 implement CNN models related to various applications Applying (K3)
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2
CO2 3 2 2
CO3 3 2 2
CO4 3 2 2
CO5 3 2 2
CO6 3 2 2 2 2
CO7 3 2 2 2 2
CO8 3 2 2 2 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 20 30 50 100
CAT2 20 30 50 100
CAT3 20 30 50 100
ESE 20 30 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 173

 Kongu Engineering College, Perundurai, Erode – 638060, India
COMPUTER VISION

Programme&
BE/BTech All branches except AI&ML and AI&DS Sem. Category L T P Credit
Branch
Prerequisites Python Programming 5 OE 3 0 2 4

Preamble This course aims to provide a broad view on analysis and processing of images and video
Unit - I Introduction to computer vision 9
Computer vision – Geometric Primitives and transformations: Primitives – 2D Transformations – 3D Transformations – 3D
Rotations – 3D to 2D Projections – Lens distortions - Photometric image formation: Lighting – Reflectance and shading – Optics
– The digital camera : Sampling and aliasing – Color - Compression
Unit - II Image Processing 9

Point operators : – pixel transforms – color transforms – compositing and matting – histogram equalization linear filtering:
separable filtering – examples of linear filtering – Band pass and steerable filters – Non linear filtering - Marphology

Unit - III Feature detection and matching 9

Points and patches: feature detectors – feature descriptors – feature matching – feature tracking – Application: performance
driven animation – Edges: Edge detection – edge linking – Application: Edge editing and enhancement – Lines: Successive
approximation – Hough transforms – Vanishing points.
Unit - IV Segmentation 9
Active contours: snakes – dynamic snakes and CONDENSATION – scissors – level sets – Split merge: watershed – region
splitting – region merging – Graph based segmentation – probabilistic aggregation – Mean shift and mode finding – K means and
mixtures of Gaussians – mean shift
Unit - V Motion 9
Structure from motion: Triangulation – Two-frame structure from motion – factorization – bundle adjustment – constrained
structure and motion. Dense motion estimation: Translational alignment – parametric motion – spline-based motion – optical flow
– layered motion. Image stitching: motion models – global alignment – compositing.

List of Exercises / Experiments:

1. Perform edge editing and edge enhancement using edge detection mechanism.
2. Experiment the line detection technique using mathematical approach
3 Implement a snake-based contour tracker
4 Implement the intelligent scissors (live-wire) interactive segmentation algorithm
5 Implement the region segmentation algorithm using K Means and mean shift
6 Develop a motion pictures using bundle adjuster
7 Create optical flow of motion from the continuous image frames
8 Experiment the video denoising technique in your own motion clips

Lecture:45, Practical:30, Total:75

TEXT BOOK:
1. Richard Szeliski, “Computer Vision: Algorithms and Applications”, Springer, 2010, for Unit I, II, III, IV and V.

REFERENCES:
1. D. L. Baggio et al., “Mastering OpenCV with Practical Computer Vision Projects”, Packt Publishing, 2012.

2. Jan Erik Solem, “Programming Computer Vision with Python: Tools and algorithms for analyzing images”, O'Reilly Media,
2012.
3. Rajalingappaa Shanmugamani, “Deep Learning for Computer Vision”, Packt Publishing, 2018.

[Link] Artificial Intelligence and Data Science - R2020 Page 174

 Kongu Engineering College, Perundurai, Erode – 638060, India
REFERENCES/MANUAL/SOFTWARE:
1. Operating System : Linux / Windows
2. Software : Python / Keras / Tensorflow / OpenCV
3. Laboratory Manual

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 use geometric primitives to perform transformations. Applying (K3)
CO2
1. apply linear and non linear filters and perform image processing Applying (K3)
CO3
2. use various techniques in feature detection and matching with images Applying (K3)
CO4 apply the various levels of segmentation and interpret the results at various levels Applying (K3)
CO5 apply the motion techniques in video analytics to understand various transformations. Applying (K3)

CO6 experiment the basic feature detection and matching techniques Applying (K3)
Precision (S3)
CO7 implement image segmentation using the respective models Applying (K3)
Precision (S3)
CO8 create videos using image motion techniques Applying (K3)
Precision (S3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2
CO2 3 2 2
CO3 3 2 2
CO4 3 2 2
CO5 3 2 2
CO6 3 2 2 2 3
CO7 3 2 2 2 3
CO8 3 2 2 2 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 20 30 50 100
CAT2 20 30 50 100
CAT3 20 30 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 175

 Kongu Engineering College, Perundurai, Erode – 638060, India
ARTIFICIAL INTELLIGENCE FOR DATA SCIENCE

Programme&
BE/BTech All branches except AI&ML and AI&DS Sem. Category L T P Credit
Branch
Prerequisites Nil 6 OE 3 0 0 3

Preamble The course focuses on the methodology of how to translate a data driven business problem into an effective
solution by using the powerful AI technologies according to the Data Science paradigm.
Unit - I The AI-Based Data Science Workflow and Data Preparation: 9
The AI-Based Data Science Workflow: Overview of Workflow - Key Steps of AI-Based Data Science Workflow - Project
Organization. Data Preparation: Data Collection - Visual Data Exploration - Data Preprocessing.
Unit - II Data Analysis and Model Development: 9
Data Analysis: Translation of Data into Insight - Multivariate Data Analysis - Variable Selection - Feature Extraction - Data
Visualization. Model Development: Advantages of mathematical models - Key features of a good model - Fighting Overfitting the
Data - Model Generation
Unit - III Revolution of AI and ML, Prediction using Regression 9
Introduction to Machine Learning – Machine Learning vs Classical Programming – The ability to predict – Introduction to
Regression – Regression Models – Linear Regression Model and Machine Learning – Evaluating Model Quality using different
metrics
Unit - IV Non-Linear Models and Feature Engineering 9
Non-Linear Models – Feature Engineering - Insurance cost modeling problem – Reasons for Model Errors – Rectification of
Model Errors – Overfitting and Underfitting – Deriving Data to Train the Model – Train/Test Split
Unit - V Classification Problems and Confusion Matrix 9
Introduction to Classification – Approach followed by Classification Algorithms – A Visual Representation of Logistic Regression
– Evaluating Classification Model Accuracy – Classification with Logistic Regression –Confusion Matrix.

Lecture:45; Total: 45
TEXT BOOK:
1. Arthur K. Kordon “Applying Data Science: How to Create Value with Artificial Intelligence”. Springer Nature, Switzerland, 1st
edition, 2020. for Unit I, II.
2. Sujit Bhattacharyya, Subhrajit Bhattacharyya, “Practical Handbook of Machine Learning”, Career Launcher Infrastructure Pvt
Ltd and G.K. PublicationsPvt Ltd, First Edition, 2021. for Unit III, IV and V.

REFERENCES:
1. Avrim Blum, John Hopcroft and Ravindran Kannan. “Foundations of Data Science”. Cambridge University Press, 1st edition,
England, 2020.
2. Dr. LavikaGoel, “Artificial Intelligence: Concepts and Applications ”. Wiley India PvtLtd., 1st edition, India, 2021.

[Link] Artificial Intelligence and Data Science - R2020 Page 176

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 adapt the data science workflow for finding solution to a given problem Applying (K3)
CO2 perform data analysis and apply modeling techniques for a given problem Applying (K3)
CO3 use regression models to solve problems Applying (K3)
CO4 apply feature engineering techniques and estimate model errors Applying (K3)
CO5 use the metrics and evaluate the performance of machine learning algorithms Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2
CO2 3 2 2
CO3 3 2 2
CO4 3 2 2
CO5 3 2 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 5 60 35 100
CAT2 10 20 70 100
CAT3 10 20 70 100
ESE 10 20 70 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 177

 Kongu Engineering College, Perundurai, Erode – 638060, India
BUSINESS ANALYTICS

Programme&
BE/BTech All branches except AI&ML and AI&DS Sem. Category L T P Credit
Branch
Prerequisites Nil 8 OE 3 0 0 3

Preamble To impart knowledge on various analytical methods for achieving Business Intelligence
Unit – I Foundations of Business Analytics 9
1. Definition - Impacts and Challenges - Analytic Foundations - Descriptive, Predictive, and Prescriptive Analytics - Model
Assumptions – Modern Business Analytics – Data for Business Analytics – Models in Business Analytics - Problem solving with
analytics
Unit - II Competitive advantage, Statistical Qualification and Diagnostics 9
1. Developing competitive advantage: Identifying gaps – assessing business needs. Statistical Qualifications - Statistical
Diagnostics - Statistical Review.
Unit - III 2. Building blocks for Supporting analytics and Sampling 9
3. Data Collection – Methodology for Anecdotal sampling – Design of Samples- Design of Experiments – Data Software – Data
Management. Sampling and Estimation: Statistical Sampling - Sampling Methods- Estimating Population parameters.
Unit - IV 4. Data Visualization and Descriptive Statistics 9
5. Data Visualization: Tools and Software - Creating Charts in Microsoft Excel - Excel Data Visualization Tools - Descriptive
Statistics : Metrics and Data Classification - Frequency Distributions - Cross-Tabulations - Descriptive Statistical Measures -
Populations and Samples- Measures of Location - Using Measures of Location in Business Decisions - Measures of Dispersion -
Excel Descriptive Statistics Tool.

Unit - V Statistical Inference and Regression models 9

1. Statistical Inference: Hypothesis Testing - Hypothesis-Testing Procedure- One-Sample Hypothesis Tests. Trend lines and
Regression Analysis: Modeling Relationships and Trends in Data Simple Linear Regression - Finding the Best-Fitting
Regression Line - Using Regression Models for Prediction
Lecture: 45, Total: 45
TEXT BOOKS:
1. James R. Evans. Business Analytics, 3rd edition, Pearson, 2020. for Unit I, IV and V.
2 Randy Bartlett. A Practitioner's Guide To Business Analytics, 1st edition, McGrawHill, 2013. for Unit II, III.

REFERENCES:
1. U Dinesh Kumar. Business Analytics: The Science of Data - Driven Decision Making, 1st edition, Wiley, 2017.

[Link] Artificial Intelligence and Data Science - R2020 Page 178

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1: select the type of analytics needed for solving a problem Applying (K3)
CO2: assess the need and perform diagnostics for a business problem Applying (K3)
CO3: use the building blocks while performing analytics and apply sampling techniques Applying (K3)
CO4: use tools and methods for data Visualization and summarize data using descriptive Applying (K3)
Statistics
CO5: interpret and making inference on results and use regression models for prediction Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2
CO2 3 2 2
CO3 3 2 2
CO4 3 2 2
CO5 3 2 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT 1 20 45 35 100
CAT 2 20 45 35 100
CAT 3 20 45 35 100
ESE 20 45 35 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 179

 Kongu Engineering College, Perundurai, Erode – 638060, India
HONOURS IN IOT

INTRODUCTION TO IOT

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science
Prerequisites NIL 3 0 0 3

Preamble This course provides insights about the basics of networking, network security, precursor technologies of IoT and
the emergence of IoT. It gives an overview of various connectivity technologies prevalent in the field. It also
focuses on various challenges of IoT and real-time IoT case studies.
Unit - I Basics of Networking and Security 9
Basics of Networking: Introduction - Network Types - Layered Network Models – Addressing - TCP/IP Transport layer. Basics of
Network Security: Introduction – Security - Network Confidentiality – Cryptography - Message Integrity and Authenticity - Key
Management - Internet Security – Firewall.
Unit - II Predecessors and Emergence of IoT 9
Predecessors of IoT: Introduction - Wireless Sensor Networks - Machine-to-Machine Communications - Cyber Physical Systems.
Emergence of IoT: Introduction - Evolution of IoT - Enabling IoT and the Complex Interdependence of Technologies - IoT
Networking Components - Addressing Strategies in IoT. IoT Sensing: Introduction – Sensors - Sensor Characteristics - Sensorial
Deviations - Sensing Types - Sensing Considerations
Unit - III IoT Actuators and Topologies: 9
IoT Actuators: Actuator Types - Actuator Characteristics. IoT Processing Topologies and Types: Data Format - Importance of
Processing in IoT - Processing Topologies - IoT Device Design and Selection Considerations - Processing Offloading. IoT
Connectivity Technologies
Unit - IV Cloud Computing and Fog Computing 9
Cloud Computing: Introduction – Virtualization - Cloud Models - Service-Level Agreement in Cloud Computing - Cloud
Implementation - Sensor-Cloud: Sensors-as-a-Service. Fog Computing and Its Applications: Introduction - View of a Fog
Computing Architecture - Fog Computing in IoT - Selected Applications of Fog Computing.
Unit - V IoT Paradigms and Case Studies 9
Paradigms, Challenges, and the Future: Evolution of New IoT Paradigms - Challenges Associated with IoT - Emerging Pillars of
IoT. IoT case studies: Agricultural IoT - Vehicular IoT - Healthcare IoT
Lecture:45, Total: 45
TEXT BOOK:

1. Sudip Misra, Anandarup Mukherjee, Arijit Roy. “Introduction to IoT”. Cambridge University Press, 1st edition, United
Kingdom, 2021.

REFERENCES:

1. Cuno Pfister. “Getting Started with the Internet of Things: Connecting Sensors and Microcontrollers to the Cloud”. Make
Community, LLC, 1st edition, United States, 2011.
2. Vlasios Tsiatsis, Stamatis Karnouskos, Jan Holler, David Boyle, Catherine Mulligan. “The Internet of Things - Technologies
and Applications for a New Age of Intelligence”. Academic Press, 2nd Edition, United States, 2018.

[Link] Artificial Intelligence and Data Science - R2020 Page 180

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 recall the networking fundamentals and its security concepts Understanding (K2)
CO2 emphasize the importance of IoT fundamentals and IoT sensors Understanding (K2)
CO3 explain the IoT Actuators and IoT Processing Topologies Understanding (K2)
CO4 investigate the Cloud computing and Fog computing technologies Applying (K3)
CO5 examine the IoT Paradigms, Challenges and Case Studies Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 1 3 1
CO2 3 2 1 1 3 1
CO3 3 2 1 1 3 1
CO4 3 2 1 1 3 1
CO5 3 2 1 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 45 55 100
CAT2 35 65 100
CAT3 20 55 25 100
ESE 20 55 25 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 181

 Kongu Engineering College, Perundurai, Erode – 638060, India

IOT ARCHITECTURE AND ITS PROTOCOLS

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science
Prerequisites Introduction to IOT 3 0 0 3

Preamble This course provides a high-level overview of IoT, IoT architecture and IoT applications. Further it discusses about
DNA of IoT, Protocols for IoT and IoT communication technologies
Unit - I Introduction 9
Introduction: Genesis of IoT - IoT and Digitization - IoT Impact - Convergence of IT and OT - IoT Challenges. IoT Network
Architecture and Design: Drivers Behind New Network Architectures - Comparing IoT Architectures - A Simplified IoT
Architecture - The Core IoT Functional Stack - IoT Data Management and Compute Stack.
Unit - II IoT Applications and Four Pillars 9
Ubiquitous IoT Applications: A Panoramic View of IoT Applications - Important Vertical IoT Applications. Four Pillars of IoT: The
Horizontal, Verticals, and Four Pillars - M2M: The Internet of Devices - RFID: The Internet of Objects - WSN: The Internet of
Transducers - SCADA: The Internet of Controllers.
Unit - III DNA and Middleware of IoT 9
The DNA of IoT: DCM: Device, Connect, and Manage - Device: Things That Talk - Connect: Via Pervasive Networks - Manage:
To Create New Business Value. Middleware and IoT: An Overview of Middleware - Communication Middleware for IoT - LBS and
Surveillance Middleware
Unit - IV Protocol standards for IoT and WoT 9
Protocol Standardization for IoT: Web of Things versus Internet of Things - IoT Protocol Standardization Efforts - Unified Data
Standards. Architecture Standardization for WoT: Platform Middleware for WoT - Unified Multitier WoT Architecture - WoT Portals
and Business Intelligence - Challenges of IoT Information Security
Unit - V IoT Communication Technologies 9
IoT Communication Technologies: Introduction - Infrastructure Protocols - Discovery Protocols - Data Protocols - Identification
Protocols - Device Management - Semantic Protocols. IoT Interoperability: Introduction – Standards – Frameworks.

Lecture:45, Total: 45
TEXT BOOKS:
1. David Hanes, Gonzalo Salgueiro,, Robert Barton, Jerome Henry. “IoT Fundamentals: Networking Technologies, Protocols,
and Use Cases for the Internet of Things”. Cisco Press, 1st Edition, USA, 2017. (Unit-1)
2. Honbo Zhou, “The Internet of Things in the Cloud: A Middleware Perspective”, CRC Press, 1st edition, New York, 2013.
(Unit-2,3,4)
3. Sudip Misra, Anandarup Mukherjee, Arijit Roy. “Introduction to IoT”. Cambridge University Press, 1st edition, United
Kingdom, 2021.(Unit-5)

REFERENCES:
1. Cuno Pfister. “Getting Started with the Internet of Things: Connecting Sensors and Microcontrollers to the Cloud”. Make
Community, LLC, 1st edition, United States, 2011.
2. Vlasios Tsiatsis, Stamatis Karnouskos, Jan Holler, David Boyle, Catherine Mulligan. “The Internet of Things - Technologies
and Applications for a New Age of Intelligence”. Academic Press, 2nd Edition, United States, 2018.

[Link] Artificial Intelligence and Data Science - R2020 Page 182

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 explains the IoT Network Architecture and Design Understanding (K2)
CO2 interpret the Pillars of IoT and IoT applications Understanding (K2)
CO3 describe the technological aspects of the DCM layers of the IoT value chain and IoT Understanding (K2)
middleware
CO4 examine the possibility of creating a unified IoT middleware architecture based on existing Understanding (K2)
protocol standard
CO5 determine the requirements associated with IoT communication Applying (K3)
protocols in real-world solutions

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 1 3 1
CO2 3 2 1 1 3 1
CO3 3 2 1 1 3 1
CO4 3 2 1 1 3 1
CO5 3 2 1 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT1 45 55 100
CAT2 35 65 100
CAT3 20 55 25 100
ESE 20 55 25 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 183

 Kongu Engineering College, Perundurai, Erode – 638060, India
COGNITIVE IOT

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science
Prerequisites 3 0 0 3

Preamble To impart the knowledge ofcognitive Internet of Things in various domains

Unit – I Introduction 9
Introduction to Cognitive Device - Cognitive Devices as Human Assistants - Cognitive Things in an Organization - Reuse
and Monetization -Intelligent Observations – Organization of Knowledge and Problem-Solving
Unit - II Architecture and Interfaces 9
Installation, Training, Maintenance, Security and Infrastructure - Machine-to-Machine Interfaces - Man-to-Machine Interfaces -
Assisting in Human Communications.
Unit - III Cognitive IoT Paradigm 9
Describing the Cognitive IoT Paradigm - Demystifying the Cognitive Computing Paradigm – Basics of Cloud computing - The
Cognitive IoT: The Platforms, Technologies, and their Use cases - Delineating the Key Capabilities of Cognitive Cloud
Environments.
Unit - IV 9
Machine Learning (ML) Algorithms for enabling the Cognitive Internet of Things (CIoT) - Unsupervised and Semi-Supervised
Machine Learning Algorithms for Cognitive IoT Systems - Deep Learning Algorithms for Cognitive IoTSolutions - Computer
Vision (CV) Technologies and Tools for Vision-based Cognitive IoT Systems.
Unit - V 9
Natural Language Processing (NLP) Methods for Cognitive IoT Systems - Design of a Secure Infrastructure for Cognitive IoT
platforms and Applications - Revolutionizing Manufacturing using Cognitive IoT Technologies - Edge AI – Consumer, Social and
Industry Use Cases
Lecture:45, Total: 45
TEXT BOOKS:

1 Arvind Sathi. Cognitive (Internet of) Things. Palgrave Macmillan, 1 st edition, 2016 (Units I, II)
2. Pethuru Raj, Anupama C. Raman, Harihara Subramanian. Cognitive Internet of Things
Enabling Technologies, Platforms, and Use [Link] Publications, 1st edition, 2022 (Units III , IV, V)

REFERENCES:

1 ArshdeepBahga and Vijay Madisetti, Cloud Computing: A Hands-on Approach, 1st edition, CreateSpace Independent
Publishing Platform, 2013.
2. Alessandro Bassi, Martin Bauer, Martin Fiedler, Thorsten Kramp, Rob van Kranenburg, Sebastian Lange and Stefan
Meissner, Enabling things to talk –Designing IoT solutions with the IoT Architecture Reference Model, 1st edition ,Springer
Open, 2016.

[Link] Artificial Intelligence and Data Science - R2020 Page 184

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1: gain insights of cognitive devices and their applications Understanding (K2)
CO2: understand different types of interfaces and organizations in cognitive things Understanding (K2)

CO3: develop knowledge on significance of Cognitive IoT Understanding (K2)

CO4: implement different computational intelligent techniques for Cognitive IoT Applying (K3)

CO5: design cognitive IoT architectures using advanced methods Understanding (K2)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 3 3 3 3 2
CO2 3 3 2 2 3 2
CO3 3 2 3 3 3 3
CO4 3 2 3 3 3 3
CO5 3 2 2 3 3 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT 1 40 45 15 100
CAT 2 40 45 15 100
CAT 3 40 45 15 100
ESE 40 45 15 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 185

 Kongu Engineering College, Perundurai, Erode – 638060, India

INDUSTRIAL AND MEDICAL IOT

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 3 0 0 3

Preamble This course deals with introduction to Industrial and medical IoT
and how IoMT is used to for remote healthcare
Unit - I Industrial IoT 9
Introduction to IoT- key technologies- I-IoT- IoT Analytics and AI- Industrial process – CIM pyramid architecture -devices and
networks- I-IoT data Flow
Unit - II Industrial Data Flow 9
I-IoT dataflow-Industrial protocols-Supervisory control and Data Acquisition-Discovering OPC-Understanding I-IoT Edge-
Implementing I-IoT dataflow-OPC UA Simulation server-
Unit - III Implementing I-IoT 9
Developing Industrial I-IoT and Architecture-Implementing custom Industrial IoT Platform -Implementing a cloud Industrial IoT
solution with AWS
Unit - IV Internet of Medical things 9
Introduction-IoMT- IoMT Medical Devices- Remote Patient monitoring- privacy of IoT -based health records - remote Health
Care: wearable smart devices - Communication technologies
Unit - V IoMT Applications 9
Smart Assistance for Elderly Individuals -Parkinson’s Disease handling using IoMT- Machine Learning with IoMT
Lecture:45, Total: 45
TEXT BOOK:

1. Giacomo Veneri,Antonio Capsso, “Hands-On Industrial Internet of Things: Create a powerful Industrial IoT infrastructure
using Industry 4.0,Packt Publishing Ltd, 1st edition,2018
2. [Link] Hemanth,[Link],George A. Tsihrintzis “Internet of Medical things- remote healthcare systems and applications”,
Springer, 1st edition, 2021.

REFERENCES:

1. Ismail Butun,“Industrial IoT Challenges, Design Principles, Applications, and Security”, Springer Publications,1 st edition,
2020.

[Link] Artificial Intelligence and Data Science - R2020 Page 186

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 understand the basic concepts of Industrial IoT Understanding (K2)
CO2 explain the principles of Industrial Data Flow Understanding (K2)
CO3 explore different aspects of implementing I-IoT Understanding (K2)
CO4 implement the concepts of Internet of Medical things Applying(K3)
CO5 demonstrate various IoMT Applications Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 2 3 2
CO2 3 2 2 2 3 2
CO3 3 2 2 2 3 2
CO4 3 2 2 3 3 2
CO5 3 2 2 3 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test /
Remembering Understanding Applying Analyzing Evaluating Creating
Bloom’s Total %
(K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
Category*
CAT1 50 50 100
CAT2 20 50 30 100
CAT3 20 50 30 100
ESE 20 50 30 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 187

 Kongu Engineering College, Perundurai, Erode – 638060, India
IOT AND MACHINE LEARNING

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 3 0 0 3

Preamble
To impart knowledge on various mechanisms of integrating IoT devices and Machine Learning algorithms

Unit – I Introduction 9
Infusion of AI and data science in IoT - Data Access and Distributed Processing for IoT :txt, csv,xlsx,json,HDF5,SQL, NoSQL,
HDFS. Edge Computing on IoT Devices - Distributed Machine Learning - Machine Learning Accelerator - Machine Learning
Model Optimization.
Unit - II Machine Learning for IoT 9
Prediction using linear regression - Logistic regression for classification - Ensemble learning - Improving machine learning model

Unit - III Deep Learning for IoT 9

Introduction to Deep learning - Multilayered perceptrons for regression and classification - Convolutional neural networks -
Recurrent neural networks – Autoencoders
Genetic Algorithms for IoT Optimization
Unit - IV 9

Deterministic and analytic methods - Natural optimization methods- Introduction to genetic algorithms - Coding genetic
algorithms using Distributed Evolutionary Algorithms in Python - Reinforcement Learning for IoT
Unit - V Advanced models for IoT 9
Generative Models for IoT - Distributed AI for IoT - AI for the Industrial IoT - Processing different types of data - Computing in the
cloud

Lecture:45, Total: 45
TEXT BOOKS:
1. Hantao Huang, Hao Yu. Compact and Fast Machine Learning Accelerator for IoT Devices. Springer, 1 st edition, 2019.

2. Amita Kapoor. Hands-On Artificial Intelligence for IoT. Packt Publishing, 1st edition, 2019.

REFERENCES:

1 Shrirang Ambaji Kulkarni, Varadaraj [Link], Steven [Link]. Introduction to IoT with machine learning and image
processing using Raspberry pi. CRC Press, 1st edition, 2020.

[Link] Artificial Intelligence and Data Science - R2020 Page 188

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1: describe the basic concepts of IoT and Machine learning Understanding (K2)
CO2: implement machine learning algorithms for IoT applications Applying (K3)
CO3: describe various Deep Learning algorithms for IoT Understanding (K2)
CO4: apply Genetic Algorithms for IoT Optimization Applying (K3)

CO5: understand advanced models for IoT Understanding (K2)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 3 3 3 3 2
CO2 3 3 2 2 3 2
CO3 3 2 3 3 3 3
CO4 3 2 3 3 3 3
CO5 3 2 2 3 3 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) %
CAT 1 40 50 10 100
CAT 2 40 45 15 100
CAT 3 40 50 10 100
ESE 40 45 15 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 189

 Kongu Engineering College, Perundurai, Erode – 638060, India
PRIVACY AND SECURITY IN IOT

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 3 0 0 3

Preamble This syllabus explores issues of privacy and security with regard to the IoT environments, as well as technical
solutions to help address them.
Unit - I Attacks and Protection Mechanisms in IoT Devices 9
Introduction-physical attacks in IoT Devices-Profiling Attacks-Real World Attacks-count measures- Remote Attestation- Types of
Remote Attestation-remote Attestation-Human Aspects of IoT Security and privacy
Unit - II Defence Mechanisms Against Attacks 9
Introduction - Data Exfiltration- Types-Attack Mechanisms, and Defence Technique- Types of Data Exfiltration-Data Exfiltration
Attack Techniques-Data Exfiltration Threats-Counter Data Exfiltration-Mechanisms to Defend Against Physical Data Exfiltration-
Threat Scenario-Scenario Execution and Analysis-Discussion
Unit - III Protocol for UAV Remote Identification 9
Introduction- Drone Security - Drone Security in UTM-Security Attacks on Drones -Security Attacks from Drones-Drone Safety-
Drone Detection and Classification-Interdiction Technologies-UAV Remote Identification-Authentication Protocol for Remote
Identification-Secure Communication Protocol-Security Analysis- Formal Verification
Unit - IV Cyber-Security IoT Infrastructure 9
Cyber-Attacks on IoT Infrastructure – Eavesdropping - Solutions-Network Activity Analysis Solutions-Active Reconnaissance-
Solutions-Volumetric Attack -Solutions - Masquerading Attack -Solutions- Access Attack – Solutions-Active Crypto Attack -
Solutions - Data Exfiltration- Solutions-Blocking Attack- Solutions-Sleep Deprivation Attack - Solutions Trigger Action Attack-
Solutions- Network Behavioral Model of IoTs -Enforcing MUD Profile to Network
Unit - V Security and privacy - Case studies 9
Securing Contemporary eHealth Architectures- Techniques and Methods: Introduction -
eHealth- Fog or Edge Computing for eHealth- Cloud Computing for eHealth -Applications of IoT in eHealth- eHealth Threat
Landscape-eHealth Threat Model- eHealth IoT Vulnerabilities and Threats-Real-world Attacks-Counter measures. Security and
Privacy of Smart Homes- Issues and Solutions :Smart Homes’ Security and Privacy-Smart Home Technologies-Privacy
Techniques and Mechanisms
Lecture:45, Total: 45
TEXT BOOK:

1. Ali Ismail Awad, Jemal Abawajy, “Security and Privacy in the Internet of Things -Architectures, Techniques, and
Applications”, Wiley-IEEE Press, 1st edition ,2018.
2. Fei Hu ,Security and Privacy in Internet of Things (IoTs): Models, Algorithms, and Implementations, CRC Press; 1st
edition,2016.

REFERENCES:

1. Zaigham Mahmood, Security, Privacy and Trust in the IoT Environment”, Springer ,1st edition2019.

[Link] Artificial Intelligence and Data Science - R2020 Page 190

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 describe Attacks and Protection Mechanisms in IoT Devices Understanding (K2)
CO2 explain Defence Mechanisms Against Attacks Understanding (K2)
CO3 summarize Protocol for UAV Remote Identification Understanding (K2)
CO4 design Cyber-Security IoT Infrastructure Understanding (K2)
CO5 implement Security and privacy mechanisms Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 2 3 2
CO2 3 2 2 3 2
CO3 3 2 2 3 2
CO4 3 2 2 3 2
CO5 3 2 2 3 2
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 50 50 100
CAT2 50 50 100
CAT3 20 50 30 100
ESE 20 50 30 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 191

 Kongu Engineering College, Perundurai, Erode – 638060, India
HONOURS IN BLOCKCHAIN

INTRODUCTION TO BLOCKCHAIN

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 3 0 0 3

Preamble This course provides technical fundamentals of Blockchain, and hands on development aspects of Blockchain
applications
Unit - I Introduction 9
Overviw of blockchain – Centralized vs Decentralized Systems – Layers of Blockchain – Importance – Blockchain Uses and Use
Cases – Laying the Blockchain Foundation .
Unit - II Working of Blockchain 9
Game Theory – Prisoner‟s Dilemma – Byzantine Generals‟ Problem – The Blockchain – Merkle Trees – Properties of Blockchain
Solutions – Blockchain Transactions – Distributed consensus mechanisms – Blockchain applications – Scaling blockchain.
Unit - III Bitcoin and Altcoins 9
History of Bitcoin – bitcoin is volatile – key and address- transactions – blocks – bitcoin network : types of nodes – Network
discovery wallets – Altcoins: Introducing Altcoins – alternative currency – acquiring cryptocurrency.
Unit - IV Ethereum and Introduction to Hyperledger 9
Bitcoin to Ethereum – Ethereum Blockchain – Ethereum Smart Contracts – Ethereum Virtual Machine and Code Execution –
Ethereum Ecosystem – Swarm – Whisper – DApp – Development components – Hyperledger: Introduction – Projects. Fabric –
Sawtooth lake – Iroha – Blockchain explorer – Fabric chaintool – Fabric SDK Py-Corda
Unit - V Blockchain Application Development 9
Decentralized Applications – Blockchain Application Development – Interacting with Bitcoin Blockchain – Sending Transactions –
Creating a Smart Contract – Executing Smart Contract Functions – Public vs. Private Blockchains – Decentralized Application
Architecture – Building an Ethereum DApp.

Lecture:45, Total:45
TEXT BOOK:

1. Bikramaditya Singhal, Gautam Dhameja, Priyansu Sekhar Panda, “Beginning Blockchain: A Beginner‟s Guide to Building
Blockchain Solutions”, APress, 1st Edition, 2018. (Units 1,2,4,5)
2. Brenn Hill, Samanyu Chopra, Paul Valencourt, “Blockchain Quick Reference: A guide to exploring decentralized blockchain
application development”, Packt publishing, 1st Edition, 2018.(Unit – 3)

REFERENCES:

1. Elad Elrom,”The Blockchain Developer: A Practical Guide for Designing, Implementing, Publishing, Testing, and Securing
Distributed Blockchain-based Projects”, Apress, 2019

[Link] Artificial Intelligence and Data Science - R2020 Page 192

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
explore the history, background, and theoretical aspects of blockchain and apply in real case
CO1 Applying (K3)
scenarios
CO2 demonstrate core components and working of blockchain Applying (K3)
CO3 outline Bitcoin‟s technical concepts and apply it for real case scenarios Applying (K3)
CO4 adapt Ethereum blockchain for different use cases Applying (K3)
CO5 demonstrate the end-to-end development of a decentralized application Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 2 3
CO2 3 2 1 2 3
CO3 3 2 1 2 3
CO4 3 2 1 2 3
CO5 3 2 1 2 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 30 50 100
CAT2 20 30 50 100
CAT3 20 30 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 193

 Kongu Engineering College, Perundurai, Erode – 638060, India

CRYPTOGRAPY

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 3 0 0 3

Preamble This course describes cryptographic algorithms deployed for offering confidentiality, integrity, authentication and non
repudiation.
Unit - I Introduction 9
Computer Security Concepts – The OSI Security Architecture – Security Attacks – services and mechanisms – Model for Network
Security – Classical encryption techniques: symmetric cipher model – substitution techniques – transportation techniques -
steganography
Unit - II Block ciphers and Data Encryption standard 9
Block cipher Structure – data encryption standard – the strength of DES - DES Example – block cipher design principles – Finite
fields: Groups – rings – fields - Advanced encryption standard – Block cipher operation.
Unit - III Asymmetric cipher 9
Public key cryptography and RSA – Other Public key cryptosystems – Diffie-Hellman Key Exchange – Elgamal Cryptographic
System – Elliptic Curve Arithmetic – Elliptic Curve Cryptography
Unit - IV Cryptographic Data Integrity Algorithms 9
Cryptographic hash functions – Message authentication codes: Message Authentication Requirements – Message Authentication
Functions – Requirements for Message Authentication Codes – Security of MACs – MACs Based on Hash Functions: HMAC –
Digital signatures: Elgamal Digital Signature Scheme – Schnorr Digital Signature Scheme – NIST Digital Signature Algorithm –
Elliptic Curve Digital Signature Algorithm.
Unit - V Network and Internet Security 9
Network access control and cloud security –Transport level security – Wireless network security – Electronic mail security – IP
security – Intruder – Firewalls

Lecture:45, Total:45

TEXT BOOK:
1. William Stallings, "Cryptography and Network Security", 7th Edition, Pearson Education, 2017. (Unit 1-5)

REFERENCES:
1. Christof Paar and Jan Pelzl, “Understanding Cryptography: A Textbook for Students and Practitioners”, Springer, 2009

[Link] Artificial Intelligence and Data Science - R2020 Page 194

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 interpret the basic security architecture and classical symmetric key techniques in cryptography Applying (K3)
CO2 apply various block ciphers and data encryption standars to solve the problems Applying (K3)
CO3 make use of various public key cryptography techniques for solving real time problems Applying (K3)
CO4 explore hashing and digital signature techniques Applying (K3)
CO5 determine the appropriate security protocols and standards for the given application Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 2 3
CO2 3 2 1 2 3
CO3 3 2 1 2 3
CO4 3 2 1 2 3
CO5 3 2 1 2 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 30 50 100
CAT2 20 30 50 100
CAT3 20 30 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 195

 Kongu Engineering College, Perundurai, Erode – 638060, India

BITCOIN TECHNOLOGY

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 3 0 0 3

Preamble The course focuses on the basics of Bitcoin technology and various technologies involved.
Unit - I Introduction: 9
Introduction to Bitcoin and How Bitcoin works: Transactions, Blocks, Mining and the Blockchain – Bitcoin Transactions –
Constructing a Transaction – Bitcoin Mining – Mining transactions in Blocks – Bitcoin Core: The Reference Implementation –
Bitcoin Development Environment – Compiling Bitcoin Core from the Source Code – Running a Bitcoin Core Node – Bitcoin Core
API.
Unit - II Keys, Addresses, Wallets and Transactions: 9
Keys, Addresses: Introduction – Bitcoin Addresses – Implementing Keys and Addresses in Python – Advanced Keys and
Addresses - Wallets: Wallet Technology Overview – Wallet Technology Details - Transactions: Transactions in Detail –
Transaction Outputs and Inputs – Transaction Scripts and Script Language – Digital Signatures (ECDSA) – Bitcoin Addresses,
Balances and other Abstractions.
Unit - III Advanced Transactions and Bitcoin Network: 9

Advanced Transactions and Scripting: Multisignature – Pay-to-Script-Hash(P2SH) – Data Recording Output (RETURN) –
Timelocks –Scripts with Flow Control - The Bitcoin Network: Peer-to-Peer Network Architecture – Nodes Types and Roles – The
Extended Bitcoin and Relay Networks – Network Discovery – Full Nodes – Exchanging “Inventory” – SPV Nodes – Bloom Filters
– How SPV Nodes Use Bloom Filters – SPV Nodes and Privacy.

Unit - IV Blockchain and Consensus: 9

The Blockchain: Structure of a Block – Block Header and Identifiers – The Genesis Block – Linking Blocks in the Blockchain –
Merkle Trees - Merkle Trees and SPV – Bitcoin’s Test Blockchains - Mining and Consensus: Decentralized Consensus –
Independent Verification of Transactions – Mining Nodes – Aggregating Transactions into Blocks – Constructing the Block Header
and validating the Block - Assembling and Selecting Chains of Blocks – Mining and the Hashing Race – Consensus Attacks –
Changing the Rules.

Unit - V Applications: 9
Bitcoin Security: Security principles – User Security Best Practices – Blockchain Applications: Building Blocks(Primitives) –
Applications from Building Blocks – Colored Coins – Counterparty – Payment Channels and State Channels – Routed Payment
Channels (Lightning Network).
Lecture:45, Total: 45
TEXT BOOK:
1. Andreas M. Antonopoulos, “Mastering Bitcoin Programming the Open Blockchain”, Second Edition, O’Reilly Media, Inc.,
2017. (Units I to V)

[Link] Artificial Intelligence and Data Science - R2020 Page 196

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)

CO1 understand the Bitcoin basics and use it for creating transactions. Applying (K3)
CO2 apply the concepts of Keys, Addresses and Wallet for security applications. Applying (K3)
CO3 develop scripts to provide security in a Bitcoin network. Applying (K3)
CO4 explore and apply Blockchain technology and Consensus . Applying (K3)
CO5 apply Blockchain to provide security for real time applications. Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 15 35 50 100
CAT2 15 35 50 100
CAT3 15 35 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 197

 Kongu Engineering College, Perundurai, Erode – 638060, India

BLOCKCHAIN AND CRYPTOCURRENCY TECHNOLOGIES

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Nil 3 0 0 3

Preamble To understand blockchain concepts, working functionality and its main application cryptocurrency. which is new
global money for the Internet age.
Unit - I Introduction 9
Distributed Database - Two General Problem - Byzantine General problem and Fault Tolerance - Hadoop Distributed File System
- Distributed Hash Table - ASIC resistance - Turing Complete - Hash function - Digital Signature - ECDSA, Memory Hard
Algorithm - Zero Knowledge Proof
Unit - II Blockchain 9
Blockchain Network - Mining Mechanism - Distributed Consensus - Merkle Patricia Tree - Gas Limit - Transactions and Fee -
Anonymity – Reward - Chain Policy - Life of Blockchain application - Soft & Hard Fork - Private and Public blockchain
Unit - III Distributed Consensus 9
Nakamoto consensus - Proof of Work - Proof of Stake - Proof of Burn - Difficulty Level - Sybil Attack - Energy utilization and
alternate–Real time Case Study - Play with Go-ethereum
Unit - IV Cryptocurrency 9
History - Distributed Ledger - Bitcoin protocols - Mining strategy and rewards - Ethereum – Construction – DAO - Smart Contract
– GHOST – Vulnerability – Attacks – Sidechain–Namecoin – Real time Case Study - Smart Contract Construction
Unit - V Cryptocurrency Regulation 9
Stakeholders - Roots of Bitcoin - Legal Aspects - Cryptocurrency Exchange - Black Market and Global Economy - Hashcash
implementation - Toy application using Blockchain - Mining puzzles

Lecture:45, Total: 45
TEXT BOOK:

1. Arvind Narayanan, Joseph Bonneau, Edward Felten, Andrew Miller and Steven Goldfeder, Bitcoin and Cryptocurrency
Technologies: A Comprehensive Introduction, Princeton University Press (July 19, 2016)

[Link] Artificial Intelligence and Data Science - R2020 Page 198

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 To know about distributed database Applying (K3)
CO2 To explore blockchain concept Applying (K3)
CO3 To understand the concepts of consensus Applying (K3)
CO4 To learn the basics of cryptocurrency Applying (K3)
CO5 To utilize cryptocurrency technologies in real time scenarios Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 3 1
CO2 3 2 1 3 1
CO3 3 2 1 3 1
CO4 3 2 1 3 1
CO5 3 2 1 3 1
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing (K4) Evaluating Creating
Total %
Category* (K1) % (K2) % (K3) % % (K5) % (K6) %
CAT1 15 35 50 100
CAT2 15 35 50 100
CAT3 15 35 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 199

 Kongu Engineering College, Perundurai, Erode – 638060, India

BLOCKCHAIN APPLICATION DEVELOPMENT THROUGH SMART CONTRACTS

Programme & BTech. & Artificial Intelligence and Data

Sem. Category L T P Credit
Branch Science

Prerequisites Introduction to Blockchain 3 0 0 3

Preamble This course enables the students to develop the applications through smart contracts

Unit - I Introduction to Ethereum Blockchain 9

History of Blockchain-Characteristic of a Blockchain: Decentralized Networks-Consensus Protocols-Transaction Processing-

Transaction Finality. Ethereum Fundamentals: Ether and Gas-Accounts-Contracts-Blocks and Transactions. Decentralized
Applications: Tokens- Supply Chain -Permanent Records -Evaluating Blockchain for Application
Unit - II Smart contract development 9
Ethereum Clients-Installing MetaMask-Installing [Link]-Installing the Truffle Suite- First Smart Contract Development.
Deploying and Interacting with Contracts: Contract Compilation and Deployment-Setting Up the UI-Deploying to Ganache-
Deploying to Goerli with Parity-Deploying to Rinkeby with Infura.
Unit – III Application Development 9
The Fundraiser Application-Application Overview - Initializing Fundraisers - Editing the Beneficiary-Making Donations-
Withdrawing Funds- Fallback Functions. FundraiserFactory : Migrating FundraiserFactory -Creating Fundraisers - Viewing
Available Fundraisers-Setting Up the UI
Unit – IV Interacting Smart Contracts through Web 9
Web3: Frontend-Web3-Blockchain- Web3 Methods. Connecting the UI to Our Contracts: React -Truffle. Larger DApp : Starting
with React Truffle Box-React and Material UI-Fundraiser UI
Unit – V Securing Smart Contracts 9
Smart Contract Security- Types of Smart Contract Vulnerabilities: Unprotected Function - Transaction Ordering Dependence -
Integer Overflow and Underflow – Reentrancy- Block Gas Limit - Timestamp Dependence. Contract for an External Audit
preparation: External Auditing - Auditing Companies -Solidified

Lecture:45, Total:45
TEXT BOOK
1. Solorio, K., Kanna, R., & Hoover, D. H. Hands-on Smart Contract Development with Solidity and Ethereum: From
Fundamentals to Deployment. O'Reilly Media, 2019. Unit -1,2,3,4,5

REFERENCE BOOK
1. Zand, M., Wu, X. B., & Morris, M. A. Hands-On Smart Contract Development with Hyperledger Fabric V2. O'Reilly Media,
2021.

[Link] Artificial Intelligence and Data Science - R2020 Page 200

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
explore smart contract fundamentals, ethereum protocol, solidity programming language, ethereum
CO1 Applying (K3)
virtual machine.
CO2 develop smart contract using solidity and Interacting with Contracts Applying (K3)
CO3 deploy and test the smart contracts using Truffle framework tools Applying (K3)
CO4 make use of web3 to connect the smart contract to an application Applying (K3)
CO5 demonstrate smart contract security with free online resourse for smart contract security auditing Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 2 3
CO2 3 2 1 2 3
CO3 3 2 1 2 3
CO4 3 2 1 2 3
CO5 3 2 1 2 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 30 50 100
CAT2 20 30 50 100
CAT3 20 30 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 201

 Kongu Engineering College, Perundurai, Erode – 638060, India

PRACTICAL ASPECTS OF BLOCKCHAIN

Programme & BTech. & Artificial Intelligence and Data Credi

Sem. Category L T P
Branch Science t

Prerequisites Introduction to Blockchain 3 0 0 3

Preamble This course intended the students to study the basics of Blockchain technology. During this course
learner will explore various aspects of Blockchain technology like application in various domains.

Unit - I Blockchain Basics and Nodes 9

Introduction to Cryptoeconomics and blockchain- Overloading Cryptocurrencies- Blockchain P2P Network. Blockchain Node:
Running a Blockchain Node- Bitcoin Core API

Unit - II Creating Blockchain, Bitcoin Wallets and Transactions 9

Basic P2P Network creation- Genesis Block and Sharing Blocks creation -Registering Miners and Creating New Blocks-Storing
Blocks in LevelDB-Creating a Blockchain Wallet-Creating an API-Creating a Command-Line Interface.
Bitcoin Wallets and Transactions: Bitcoin Core RPC Resources -Bitcoin Wallet-Transactions- Bitcoin Colored Coins
Unit – III Ethereum Wallets, NEO Blockchain and Smart Contracts 9
Ganache Simulated Full-Node Client- IntelliJ IDEA Plugin for Solidity- Truffle Suite- Compile with Remix- Private Ethereum
Blockchain with Geth- Connect the Mist Ethereum Wallet to Private Network- MetaMask. NEO Blockchain and Smart Contracts
: NEO’s High-Level Blockchain Architecture- Setting Up Local Environment- Create a Local NEO Private Testnet- Publish a
Smart Contract on a Private Testnet
Unit – IV Hyperledger 9
Hyperledger Overview- Hyperledger Fabric- Installing Hyperledger Fabric and Composer- Hyperledger Composer- “Hello, World”
with Playground- Deploying on a Local Hyperledger Fabric Network- Running “hello-network” Network- Error Troubleshooting
Unit – V Build Dapps with Angular 9
Dapp-Angular- Smart Contract transfer -Link with the Ethereum Network- MetaMask connection-Test Dapp Functionality

Lecture:45, Total: 45

TEXT BOOK
1. Elrom, E. (2019). The Blockchain Developer: A Practical Guide for Designing. Implementing, Publishing, Testing, and
Securing Distributed Blockchain-based Projects. Unit -1,2,3,4,5

REFERENCE BOOK
1. Krishnan, S., Balas, V. E., Golden, J., Robinson, Y. H., Balaji, S., & Kumar, R. (Eds.). (2020). Handbook of research on
blockchain technology. Academic Press.

[Link] Artificial Intelligence and Data Science - R2020 Page 202

 Kongu Engineering College, Perundurai, Erode – 638060, India

COURSE OUTCOMES: BT Mapped

On completion of the course, the students will be able to (Highest Level)
CO1 make use of the structure and mechanism of blockchain to address the basic security. Applying (K3)
CO2 deploy Blockchain and create a Bitcoin Wallets and Transactions. Applying (K3)
CO3 create Ethereum Wallets, NEO Blockchain and publish a Smart Contract on a Private Testnet Applying (K3)
CO4 solve the business network issues using Hyperledger Composer. Applying (K3)
CO5 build Dapps with Angular and link with the Ethereum Network Applying (K3)

Mapping of COs with POs and PSOs

COs/POs PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2
CO1 3 2 1 2 2 2 3
CO2 3 2 1 2 2 2 3
CO3 3 2 1 2 2 2 3
CO4 3 2 1 2 2 2 3
CO5 3 2 1 2 2 2 3
1 – Slight, 2 – Moderate, 3 – Substantial, BT- Bloom’s Taxonomy

ASSESSMENT PATTERN - THEORY

Test / Bloom’s Remembering Understanding Applying Analyzing Evaluating Creating Total
Category* (K1) % (K2) % (K3) % (K4) % (K5) % (K6) % %
CAT1 20 30 50 100
CAT2 20 30 50 100
CAT3 20 30 50 100
ESE 10 40 50 100
* ±3% may be varied (CAT 1,2,3 – 50 marks & ESE – 100 marks)

[Link] Artificial Intelligence and Data Science - R2020 Page 203