Centre for Internet of Things
Computer Vision (3230621)
Course Objectives: To provide students with foundational knowledge and practical skills in computer vision, enabling themto
design, develop, and deploy vision-based solutions for IoT and embedded systems applications.
Unit 1: Introduction to Computer Vision & Image Fundamentals: Definition and scope of computer
vision, applications in IoT, digital image representation, pixels, color spaces (RGB, Grayscale, HSV, YCbCr), image
acquisition devices, image formats, basic image operations, introduction to OpenCV, image sampling and
quantization, image histograms, camera calibration.
Unit 2: Image Processing & Enhancement: Image filtering, smoothing, sharpening, Gaussian blur, noise
reduction techniques, edge detection, thresholding techniques, morphological operations, histogram equalization,
contrast enhancement, color-based segmentation, image gradients, image resizing and geometric transformations.
Unit 3: Feature Extraction & Object Detection: Feature detection (corners, blobs), feature descriptors
(SIFT, SURF, ORB), keypoint matching, contour detection, template matching, object detection fundamentals, face
detection using Haar cascades, motion detection, optical flow, tracking techniques (Kalman filter, CamShift),
background subtraction.
Unit 4: Deep Learning for Computer Vision:Introduction to neural networks, convolutional neural
networks (CNNs), convolutional and pooling layers, activation functions, transfer learning, pre-trained models (VGG,
ResNet, MobileNet), real-time object classification, object detection, semantic segmentation, instance segmentation,
lightweight CNNs for edge devices.
Unit 5: Computer Vision Applications in IoT: Smart surveillance, anomaly detection, gesture and sign
recognition, autonomous robots and drones, embedded vision systems (Raspberry Pi, NVIDIA Jetson, ESP), smart
home applications, industrial IoT applications, healthcare and medical imaging.
Course Outcomes: After completing this course, the students will be able to:
CO1 Explain fundamentals of computer vision, image representation, and processing techniques for IoT.
CO2 Apply image enhancement, filtering, and feature extraction methods to analyze visual data.
CO3 Analyzeand implement object detection, tracking, and recognition algorithms.
CO4 Evaluate deep learning models for real-time image classification, detection, and segmentation.
CO5 Design and develop computer vision-based IoT solutions for real-world applications.
Recommended Books:
1. A. K. Jain, Fundamentals of Digital Image processing, Pearson Education, 2009.
2. D. A. Forsyth and J. Ponce, Computer Vision, A Modern Approach, Pearson Education, 2003.
3. D. H. Ballard and C. M. Brown, Computer Vision, Prentice Hall, 1982.
4. R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis, John Wiley, 2006.
5. R. Jain, R. Kasturi and B. G. Schunck, Machine Vision, McGraw-Hill, 1995.
6. R. C. Gonzalez and R. E. Woods, Digital Image Processing, Addison-Wesley, 2008.
7. R. Schalkoff, Pattern Recognition – Statistical, Structural and Neural Approaches, John Wiley, 2007.
Centre for Internet of Things
Soft Computing Techniques (3230622)
Course Objective:
● To provide the student with the basic understanding of neural networks and fuzzy logic fundamentals, Program
the related algorithms and design the required and related systems.
● To understand the basics of an evolutionary computing paradigm known as genetic algorithms and its
application to engineering optimization problems
Unit I-Introduction to Soft Computing: Soft Computing v/s Hard Computing, Basic models of Artificial Neural
Networks, Terminologies of ANNs McCulloch-Pitts Neurons, Linear Separability, Hebb Network, Supervised
Learning Networks: Introduction, Perceptron Networks, Back Propagation Networks, Radial Basis Function
Networks, Hopefield networks.
Unit II- Fuzzy Set Theory: Fuzzy Sets, Fuzzy Membership Functions, Operations on Fuzzy Sets, Fuzzy Relations,
Fuzzy rules, Fuzzy Reasoning, Defuzzification: Lambda-Cuts for Fuzzy sets (AlphaCuts), Lambda-Cuts for Fuzzy
Relations. Fuzzy Inference System: Introduction, Mamdani Fuzzy Model, Takagi-Sugeno Fuzzy Model.
Unit III- Evolutionary Algorithm: Traditional optimization and Search Techniques, Basic Terminologies in GA,
Operators in Genetic Algorithm, Stopping Condition for Genetic Algorithm Flow, Classification of Genetic
Algorithm, Comparison with Evolutionary algorithm, Application of Genetic algorithm.
Unit IV- Introduction to Nature-Inspired Optimization Algorithms: Particle Swarm Optimization (PSO)
Algorithm, Differential Evolution (DE) Algorithm, Artificial BeeColony (ABC) Algorithm, Ant Colony
Optimization (ACO) Algorithm, Cuckoo Search (CS), Firefly Algorithm (FA), Immune Algorithm (IA), Grey Wolf
Optimization (GWO), Spider Monkey Optimization.
Unit V- Hybrid Soft Computing Techniques: Introduction, Neuro-fuzzy Hybrid system, Adaptive Neuro fuzzy
inference system (ANFIS), Genetic Neuro Hybrid system, Application of Soft Computing Techniques.
Course Outcomes:After completing this course, the student will be able to:
1. Describe the fundamental concepts of neural networks and fuzzy systems
2. Explain supervised and unsupervised learning models
3. Compare nature-inspired algorithms based on their application aspects
4. Analyze the efficiency of different hybrid systems, considering factors such as performance and adaptability
5. Design a soft computing model tailored to solve real-world problems.
Recommended Books:
1. Principles of Soft Computing, S. N. Sivanandam and S. N. Deepa, Wiley Neural Networks, Fuzzy Logic and Genetic
Algorithms: Synthesis and Applications- S. Rajasekaran& G.A. VijayalakshmiPai, PHI
2. Introduction to Soft Computing Neuro-Fuzzy and Genetic Algorithms, Samir Roy and Udit Chakraborty, Pearson
3. Neural Networks and Learning Machines-Simon Haykin PHI
4. Fuzzy Logic and Engineering Application, Tomthy Ross, TMH
5. Evolutionary Optimization Algorithms, D. Simon (2013), Wiley
6. Fundamentals of Natural Computing: Basic Concepts, Algorithms, and Applications, L. N. de Castro (2006), CRC
Press.
Centre for Internet of Things
Artificial Intelligence & Machine Learning (3230623)
Course Objectives:
● To provide the fundamental knowledge of Artificial Intelligence, Neural Network and Machine Learning.
● To present the basic representation and reasoning paradigms used in AI &ML.
● To understand the working of techniques used in AI &ML.
Unit – I: Introducing Artificial Intelligence:Definition, Goals of AI, Task of AI, Computation, Psychology and
Cognitive Science. Perception, Understanding, and Action. Artificial intelligence vs machine learning vs deep
learning and other related fields. Applications of Artificial intelligence and Machine Learning in the real world.
Unit – II: Problem, Problem Space and Search: Production System, Blind Search: BFS & DFS, Heuristic Search,
Hill Climbing, Best First Search. Introduction to Neural Networks: History, Biological Neuron, Artificial Neural
Network, Neural Network Architectures, Classification, & Clustering.
Unit – III: Introduction to Machine Learning: Traditional Programming vs Machine learning. Key Elements of
Machine Learning: Representation, process (Data Collection, Data Preparation, Model selection, Model Training,
Model Evaluation and Prediction), Evaluation and Optimization. Types of Learning: Supervised, Unsupervised and
reinforcement learning. Regression vs classification problems.
Unit – IV: Supervised Machine Learning: Linear regression: implementation, applications & performance
parameters. Decision tree classifier, terminology, classification vs regression trees, tree creation with Gini index and
information gain, IDE3 algorithms, applications and performance parameters. Random forest classifier. Case study
on regression and classification for solving real world problems.
Unit –V: Unsupervised Machine Learning: Introduction, types: Partitioning, density based, DBSCAN, distribution
model-based, hierarchical, Agglomerative and Divisive, Common Distance measures, K-means clustering algorithm.
Case study on clustering for solving real world problems.
Course Outcomes:After completing this course, the student will be able to:
1. Define basic concepts of Artificial Intelligence & Machine Learning.
2. Illustrate various techniques for search and processing.
3. Identify various types of machine learning problems and techniques.
4. Analyze various techniques in Artificial Intelligence, ANN & Machine Learning.
5. Apply AI and ML techniques to solve real world problems.
Recommended Books:
1. Artificial Intelligence: A Modern Approach by Stuart J. Russell and Peter Norvig, PrenticeHall.
2. Artificial Intelligence: Elaine Rich, Kevin Knight, Mc-GrawHill.
3. Introduction to AI & Expert System: Dan W. Patterson,PHI.
4. Pattern Recognition and Machine Learning, Christopher [Link]
5. Introduction to Machine Learning using Python: Sarah Guido
6. Machine Learning in Action: Peter Harrington
Centre for Internet of Things
Computer Vision Lab (3230601)
Course Outcomes focused on Employability/ Entrepreneurship and Skill Development
[Link]. Course Outcome (CO) Mapping
Illustrate the fundamental concepts of computer vision
CO1 Skill Development
and image processing.
Implement various image processing and feature
CO2 Skill Development
extraction techniques using OpenCV and Python.
Develop object detection, recognition, and tracking
CO3 Skill Development
algorithms for practical applications.
Analyze and evaluate computer vision models and
CO4 Skill Development
techniques based on performance metrics.
Apply computer vision methods to solve real-world
CO5 problems in domains such as healthcare, security, and Skill Development
industry.
LIST OF PROGRAMS
1. Implement a face detection and emotion recognition system to identify human expressions in real time.
2. Build a hand gesture recognition application to control applications using a webcam.
3. Design a facial recognition-based authentication system for secure access control.
4. Build an object counting system for inventory management system.
5. Monitor occupancy in rooms for smart classroom.
6. Develop a traffic sign recognition system to detect and classify road signs from video streams using deep learning
models.
SKILL BASED MINI PROJECTS
1. Design a vehicle counting and traffic analysis system to monitor traffic flow from video feeds.
2. Develop an automated attendance system using face recognition to record student or employee presence.
3. Design a pose estimation system to track human body joints for fitness or rehabilitation monitoring.
4. Build a lane detection algorithm for autonomous driving to identify road lanes in video streams.
5. Develop a license plate detection and recognition system for automated toll or parking management.
6. Develop a document scanner and text extraction system using OCR for handwritten or printed text.
7. Design a plant disease detection system to identify and classify leaf diseases from images.
8. Monitor animal behavior in farms for health and productivity analysis.
9. Design Facial Age and Gender Estimation
10. Fire or Smoke Detection for Early Warning.
Centre for Internet of Things
Artificial Intelligence & Machine Learning Lab (3230603)
Course Outcomes focused on Employability/ Entrepreneurship and Skill Development
[Link]. Course Outcome (CO) Mapping
CO1 Illustrate The Concepts of PROLOG Programming Language. Skill Development
Implement Various Techniques for Knowledge Representation Skill Development
CO2
and Processing.
CO3 Explore Different AI And ML Tools In Python. Skill Development
Analysis Various Artificial Intelligence & Machine Learning Skill Development
CO4
Techniques over Various Performance Parameters.
CO5 Apply AI And ML Techniques to Solve Real World Problems. Skill Development
LIST OF PROGRAMS
7. Study of PROLOG programming language and its functions.
8. Write simple fact for the statements using PROLOG
9. WAP to implement factorial, Fibonacci of a given number using PROLOG.
10. Write a program to solve the 4-Queen problem using PROLOG and Python both.
11. Explore numpy, Pandas, SciPy, Matplotlib and Scikit Learn libraries in Python
12. Study and implement various Dimensionality reduction, Feature selection and Normalization techniques in
Python
13. Implement Linear Regression model in Python.
14. Implement Logistic Regression model in Python.
15. Implement decision tree Classification Model using C4.5 and CSRT algorithms in Python.
16. Implement K-means clustering technique.
17. Implement Fuzzy C-means clustering technique.
18. Study various performance parameters used for evaluating the performance of various regression, classification
and clustering models.