SKD ACADEMY

SESSION: 2023-2024
Project on:
Classification System Model

Subject: Artificial Intelligence (843)

SUBMITTED TO : SUBMITTED BY :

Ms. DEV SHRUTI SUTRADHAR NAME: ADESH PATEL

[ PGT AI ] ROLL NO :
\

CERTIFICATE
Name : ................................................................
Roll No.......................................... Class: XII.........

School: SKD Academy Vikrant Khand

This is to certify that the bonafide work of

Artificial Intelligence-843(Practical/Project) has been
done by the student as per CBSE requirement during the
academic session: 2023-24.

Examiner's Signature Teacher-In-charge

Date
HEAD OF INSTITUTION
 ACKNOWLEDGEMENT
I wish to express my deep sense of gratitude and indebtedness to our
learned teacher Ms. Dev Shruti Sutradhar , SKD Academy Vikrant
Khand for his invaluable help, advice and guidance in the preparation of
this project.

I am also greatly indebted to our principal Dr. Kavita Srivastava Ma’am

and school authorities for providing me with the facilities and
requisite laboratory conditions for making this Logbook file.

I also extend my thanks to a number of teachers, my classmates and friends

who helped me to complete the Project successfully.

Teacher’s Signature
 TABLE OF CONTENT

[Link] Topic Page no.

1 Certificate 1
2 Acknowledgment 2
3 Table Of Content 3
4 Intro and Project Plan 4-9
5 Communication Plan 9-10
6 Problem Definition 11-12
7 The User 13-16
8 Brainstorming 16-18
9 Design 19-20
10 Data 19-20
11 Prototype 20
12 Testing 21-22
13 Team Collaboration 22-23
14 Individual Learning Reflection, 23-24
15 Video Link 24
16 Output screen and Code 25-27
17 Bibliography 28
 AI PROJECT LOGBOOK
2023-24

SIGN LANGUAGE RECOGNITION

Project Name: Classification System Model

School Name: SKD Academy
Class: Class XII
Teacher Name : Ms. Dev Shruti Sutradhar
Teacher Email : devvk@[Link]

TEAM MEMBER NAMES AND GRADES

1. Adesh Patel - XII B

2. Chaitanya Trivedi - XII D
1. Introduction

This Classification Model aims to categorize input data into predefined classes or labels based
on certain features. Its primary objective is to discern patterns and relationships within the
d a t a , a l l o w i n g f o r a c c u r a t e p r e d i c t i o n s o r c l a s s i f i c a t i o n s o f n e w, u n s e e n i n s t a n c e s . B y
leveraging various algorithms and techniques, the model learns from labeled training data to
generalize and make informed decisions about the class membership of unseen examples.

The usefulness of a Classification Model lies in its ability to automate decision-making

processes and provide insights into data patterns. They empower systems to autonomously
a s s i g n c a t e g o r i e s t o d a t a p o i n t s , e n a b l i n g e ff i c i e n t a n d s c a l a b l e s o l u t i o n s f o r t a s k s t h a t r e q u i r e
sorting, filtering, or labelling based on distinct characteristics. In essence, classification
models serve as intelligent tools that enhance decision support and streamline complex
decision-making scenarios across diverse fields.

2. Team Roles
2.1 W ho is in your team and what are their roles?

Role Role description Te a m M e m b e r

Name

Project leader S c h e d u l e s t h e t a s k a m o n g t h e t e a m m e m b e r, E n s u r e t h e Adesh Patel

task is c o m p l e t e o n t i m e , R e s o l v e d o u b t s (if a n y ) , a n d o n e
source of contact

Data Expert Decides upon the data required, type of data for training Adesh Patel,
the model, collects the data, ensure the type of data, and Chaitanya Trivedi
its a u t h e n t i c i t y

Information researcher Collects questions from the end users which needs to be Chaitanya Trivedi
answered, look for the answers for those questions a n d
then prepare a report which will be passed to the project
leader

Designer Wi l l create t h e d e s i g n a n d t h e o w o f h o w t o g o a b o u t Adesh Patel

making the solution for the problem statement

Prototype builder/ Wo r k s t o b u i l d t h e m o d e l , train it f o l l o w e d b y testing t h e Adesh Patel,

coder/Tester e ff i c i e n c y a n d a c c u r a c y o f t h e m o d e l Chaitanya Trivedi

2.2. Project Plan

This following table is a guide for your project plan. Yo u m a y use this or create your o w n version using

a spreadsheet w h i c h y o u can paste into this section. Yo u can paste into this section. Yo u can e x p a n d

the ‘Notes’ section to a d d r em in de rs , things that y o u n e e d to follow u p on, p r o b l e m s that n e e d to b e

fixed urgently, etc.

Phase Task Planned start planned end Plann Actual Start Actual Actual W h o is Notes/Remarks
date date ed Date End Date Duratio responsible
dur ati n
on (hours,
(hour minute
s, s)
minu
tes)

Preparing for Cou rs ew or k , 16-9-2023 10-11-2023 20-3 16-9-2023 10-11-2 20-30 All team
the project reading 0 023 hours members
h ou r
s

Set up a team 16-9-2023 16-9-2023 1.5 16-9-2023 10-11-2 20 All team

folder o n h o ur 023 hours members
shared drive s per
sessi
on
13.5
h o ur
s

Defining the Background 16-9-2023 16-9-2023 2 16-9-2023 16-9-2 2 Te am

p r o ble m reading h o ur 023 hours members
s

Research 16-9-2023 30-9-2023 24 16-9-2023 30-9-2 24 Te am

issues in our Evening Evening h o ur Evening 023 hours members
community s

Team 30-9-2023 30-9-2023 2 30-9-2023 30-9-2 2 Te am Collaborative

meeting to h o ur 023 hours members work
dis cuss i s s u e s s
and select a n
issue for the
project

Complete 30-9-2023 30-9-2023 2 30-9-2023 30-9-2 2 Te am

section 3 of h o ur 023 hours members
the project s
logbook

Rate yourself 5/5

Understandin Identify users 3-10-2023 3-10-2023 2 30-9-2023 30-9-2 2

g the users Evening Evening h o ur Evening 023 hours
s Evening

Meeting with 3-10-2023 3-10-2023 2 3-10-2023 3-10-2 2

users to morning morning h o ur morning 023 hours
observe t h e m s mornin
g

Interview 3-10-2023 3-10-2023 2 3-10-2023 3-10-2 2 Chaitanya

with user (1) afternoon afternoon h o ur afternoon 023 hours Trivedi
s afte rno
on

Interview 3-10-2023 3-10-2023 2 3-10-2023 3-10-2 2 Chaitanya o nline

with user (2), Evening Evening h o ur Evening 023 hours Trivedi i n t e r a c t ions
etc… s Evening with end users
 Complete 3-10-2023 3-10-2023 2 3-10-2023 3-10-2 2 Adesh Patel
section 4 of h o ur 023 hours
the Project s
logbook

Rate yourself 5/5

Brainstormin Team 5-10-2023 5-10-2023 12 5-10-2023 5-10-2 12 Te a m At school

g meeting to morning eve ning h o ur morning 023 hours members +
g e n erate s evening counsellor
ideas for a + teachers
project
logbook

Complete 5-10-2023 5-10-2023 1.5 5-10-2023 5-10-2 1.5 all collaborative

section 5 of eve ning day end h o ur eve ning 023 hours members work
the logbook s day end

Rate yourself 5/5

Designing Team 1 0 - 1 0 - 2 0 23 10-10-2023 3 10-10-202 10-10-2 3 All team Offline

y o u r solution meeting to morning h o ur 3 morning 023 hours members meeting
design the s
solution

Complete 1 0 - 1 0 - 2 0 23 10-10-2023 2 10-10-202 1 0 - 1 0-2 2 All team online

section 6 of eve ning eve ning h o ur 3 evening 023 hours members meeting
the logbook s evening

Rate 5/5
yourselves

Collecting Team 1 2 - 10 - 2 02 3 1 3- 1 0-2023 24 1 2- 1 0 - 2 0 23 1 3-10-2 24 All team Wi t h h e l p o f

and meeting to h o ur 023 hours members counsellor
p r e p a r i ng discuss data s and teachers
data r e quirem e nt s

Phase Task Planned start planned end Planne Actual Start Actual Actual W h o is Notes/Remarks
date date d Date End Date Duratio responsible
d u r atio n(hours
n ,minute
(hours, s)
minute
s)

Collecting Data 1 5 - 1 0 -2023 16-10-202 24 1 5 - 1 0 - 2 02 16-10- 24 Adesh Patel

and collection 3 hours 3 2023 hours
preparing
d ata
p r ototyping

Data 16-10-2023 16-10-202 24 16-10-202 16-10- 24 Chaitanya

preparation 3 hours 3 2023 hours Trivedi
and labelling
 Complete 1 7 - 1 0 -2023 1 7 - 1 0 - 2 02 2 17-10-202 1 7 - 10-2 2 ho u r s All team collaborative
Section 6 of eve ning 3 day end hours 3 evening 023 day members work
the Project end
Logbook

Te a m 16-10-2023 16-10-202 2 16-10-202 16-10- 2 ho u r s All team done during

meeting to 3 hours 3 2023 members d esigning
plan p h ase
p r o t o typing
p h ase

P r ot o t ypi ng Tr a i n y o u r 20-10-20232 20-10-202 4 20-10-2023 20-10-2 4 hours All team collaborative

Te s ting model with 3 afternoon hours members work
input data set 3
ternoon

Te s t y o u r 20-10-202 4 20-10- 4 hours All team collaborative

20-10-2023 20-10-2023
model and 3 hours 2023 members work
keep training afternoon eve ning afternoon evening
with more
data until y o u
think your
m o d e l is
accurate

Wr i t e a 24-10-2023 24-10-202 30 24-10-202 24-10- 30 Js code with help

program to 3 mins 3 2023 mins of Teachable
initiate Machine
actions based
o n the result
of your model

Complete 24-10-2023 24-10-202 1 hour 24-10-202 24-10- 1 hour All team collaborative
section 8 of 3 3 2023 members work
the Project
Logbook

Rate 5/5
yourselves

Te a m 25-10-2023 25-10-202 1 hour 25-10-202 25-10- 1 hour All team O ff l i n e m e e t i n g

meeting to 3 3 2023 members
discuss
testing p l a n

Te s ting Invite users 26-10-2023 26-10-202 2 26-10-202 26-10- 2 ho u r s All team

Creating the to test y o u r 3 hours 3 2023 members
video p r o totype

Conduct 28-10-2023 28-10-202 4 28-10-202 28-10- 4 hours All team

testing with 3 hours 3 2023 members
us ers

Complete 28-10-2023 28-10-202 1 hour 28-10-202 28-10- 1 hour All team collaborative
section 9 of 3 3 2023 members work
the project
logbook

Rate 5/5
yourselves

Te a m 1-11-2023 1-11-2023 15 1-11-2023 1-11-20 15 Te am collaborative

meeting to mins 23 mins members work
discuss video
 cr eation

Wr i t e y o u r 1-11-2023 1-11-2023 1 hour 1-11-2023 1-11-20 1 hour Te am

script 23 members

Film your 1-11-2023 1-11-2023 30 1-11-2023 1-11-20 30 Te am

video mins 23 mins members

Edit y o u r 1-11-2023 1-11-2023 30 1-11-2023 1-11-20 30 Te am (if required)

video mins 23 mins members

Completing Reflectin g o n 5 - 11-2023 5 - 11-2023 30 5 - 11-2023 5 - 11 -20 30 Te am

the Logbook the project mins 23 mins members
with your
team

Complete 5 - 11-2023 5 - 11-2023 30 5 - 11-2023 5 - 11 -20 30 Te am

sections 1 0 mins 23 mins members
and 11 of the
Project
Logbook

Review your 5 - 11-2023 5 - 11-2023 30 5 - 11-2023 5 - 11 -20 30 Te am

project mins 23 mins members
logbook and
video

S u b m i ssion Submit your 5 - 11-2023 5 - 11-2023 30 5 - 11-2023 5 - 11 -20 30 Te am individual

entries to I B M mins 23 mins members submission on
google
classroom

2.3 Communication Plan

Will y o u meet face-to-face , online or a mixture of each to communicate? - a mixture of each

H o w often will you come together to share your progress?- Three times a week

W h o will set u p online documents a n d ensure that everyone is contributing? - Adesh Patel

W h a t tools will you use for communication? -WhatsApp, Zoom, Pages by Apple and Google
D o c s for collaborative d ocu m ent a tio n s a n d w o r k .
2.4 Te a m Meeting Minutes (create one for each meeting held)

D a t e of m ee t ing: 30-09-2023
W h o attended: Adesh Patel, Chaitanya Trivedi
W h o wasn’t able to attend: -
Purpose of meeting: Discussing issues faced b y team members.
Items discussed:
1. Topic
2. As si g nm e nt of work(roles)
3. As si g nm e nt of time period for completion o f the project

Things to do (what, by w h o m , by when)

[Link] the data, reprocess it a n d prepare it
[Link] Patel, Chaitanya Trivedi
3. 01-10-23

D a t e of me et ing: 17-09-2023
W h o attended: All team members
Who wasn’t able to attend: N/A
Purpose of meeting: To discuss the problems faced b y users.
Items discussed:
[Link] faced b y users
2 . W h a t information are they looking for

Things to do (what, by w h o m , by when)

1. Online interaction w i t h a n d users
[Link] Chaitanya
[Link] d ay

D a t e of me et ing: 1 9 - 0 9 - 2 0 2 3
W h o attended: All team members
Who wasn’t able to attend: N/A
P u r p o s e of m eet ing: Brainstorming a n d designing solution
Items discussed:
[Link] the requirement o f e n d user a n d decide u p o n the solution
2. Me et online to design a solution
 [Link] section 6 of the logbook

Things to do (what, by whom, b y when)

[Link] o n the solution
[Link] Everyone
[Link] d ay

D a t e of m ee t ing: 21-09-2023
W h o attended: All team members
Who wasn’t able to attend: N/A
Purpose of meeting: Video filming
Items discussed:
1. W h i c h screen recording item to be used?
2. W h a t all(entities,dialog)to b e included in the video ?
[Link] voice over required

Things to do (what, by whom, b y when)

[Link] changes
[Link] team m e m b e r s
[Link] d ay

3. Problem Definition

3.1 List important challenges faced by Sign language.

C l a s s i f i c a t i o n m o d e l s i n A I e n c o u n t e r s e v e r a l c h a l l e n g e s . N o i s y o r i n s u ff i c i e n t t r a i n i n g d a t a c a n
impede accurate learning, leading to suboptimal predictions. The curse of dimensionality poses a
h u r d l e w h e n d e a l i n g w i t h d a t a s e t s f e a t u r i n g a l a rg e n u m b e r o f a t t r i b u t e s . I m b a l a n c e d c l a s s
distributions may cause bias, as the model tends to favour the majority class. Overfitting and
u n d e r f i t t i n g a r e p e r s i s t e n t c o n c e r n s , i m p a c t i n g t h e m o d e l ' s g e n e r a l i z a t i o n a b i l i t y. F i n e - t u n i n g
p a r a m e t e r s i s c r u c i a l b u t c a n b e c o m p l e x , r e q u i r i n g a b a l a n c e t o a c h i e v e o p t i m a l p e r f o r m a n c e . L a s t l y,
evolving data over time may necessitate continuous adaptation, making model maintenance a perpetual
challenge. Addressing these issues is essential for the robust and reliable deployment of classification
models in diverse applications.
M a i n issues/challenges:

1. Curse of Dimensionality
2. Insufficient Data
 3. Evolving Data and Model Adaption
4. Imbalanced Class Distribution
5. Overfitting and Underfitting

3.2 Which issues matter to you and why?

C l a s s i f y i n g A I m o d e l a l g o r i t h m s o f t e n r a i s e s e t h i c a l c o n c e r n s , i n c l u d i n g b i a s , t r a n s p a r e n c y, a n d

a c c o u n t a b i l i t y. T h e i m p a c t o f b i a s e d a l g o r i t h m s o n m a rg i n a l i z e d g r o u p s , t h e n e e d f o r

transparent decision-making processes, and establishing accountability mechanisms are crucial

issues in the development and deployment of classification AI models.

A t i t s c o r e , c l a s s i f i c a t i o n m o d e l i s s u e s a r e p i v o t a l a s t h e y i m p a c t t h e f a i r n e s s , a c c o u n t a b i l i t y,

and trustworthiness of AI in our daily lives. These challenges demand a careful exploration of

biases, transparent decision-making processes, and accountability frameworks. By addressing

these issues, we can ensure ethical AI implementation that align with our societal values.

3.3 Which issue will you focus on?

We will make sure the classification model helps classify everything across broader aspects.

The target audience, the people who find it hard to actually distinguish or classify between

va r i ou s item s s hall be benefitte d from it. O u r mai n fo cu s s h o u l d b e o n b et t erm en t o f o u r t a rg e t

audience as they’re the one facing the issue in classifying.

3.4 Write your team’s problem statement in the format below .

H o w can w e help People with disabilities which lead them to not be able to distinguish [a specific

user or group of users] to find a w a y to classify items [do what] so that it is easier for them to

distinguish and live an easier life.[ d o s o m e t h i n g n o t d o n e before that c a n b e measured].

Rate yourself

3
Problem definition

1 point - A local pr obl em is described.

2 point - A local pr oblem w h i c h has not been fully solved before is described.

3 point - A local p r o b l e m w h i c h has not bee n fully solved is explained in detail w i t h supporting resear

4. The User

4.1 W h o are the users and h o w are they affected by the problem?

1. People with sensory issues

2. ADHD and OCD diagnosed people
3. Normal audience

Some people find it hard to distinguish and classify

4.2 What have you actually observed about the users and h o w the problems a ect
them?

C o m m o n observations a n d challenges faced b y individuals i n this situation are:

1. Navigational Difficulty
2. Communication Hurdles
3. Safety Concerns
4. Social Interactions
5. Educational Barriers
6. Employment Limitations
4.3 Record your interview questions as well as responses from users.

1. **Question:** How do you address potential bias in the Classification AI Model?

I regularly analyze the model's output and adjust the training data to minimize biases
identified by user feedback.

2. **Question:** Has transparency in the decision-making process been effective, or are there
suggested improvements?

Transparency is generally effective, but users have suggested incorporating additional

visualizations for a more intuitive understanding of the decision process.

3. **Question:** Any emerging ethical concerns identified by users as the AI model adapts to new
data?

User feedback has highlighted evolving ethical concerns, prompting us to conduct more
frequent and proactive ethical reviews as the model evolves.

4. **Question:** How valuable is user feedback in refining the model, and are there specific
improvements suggested?

User feedback is invaluable. Specific refinements based on user use cases are currently guiding
our ongoing efforts to enhance the model.

5. **Question:** Is there confidence in the model's decisions, and are users satisfied with current
accountability measures?

Users generally trust the model, but there's room for improvement in explaining decisions and
enhancing confidence scores to ensure user satisfaction.

6. **Question:** Were there challenges with ambiguous input, and how can we enhance the
model's handling of uncertainty?

Users have noted instances of uncertainty. We're actively working to improve communication of
model confidence in ambiguous situations for a smoother user experience.

7. **Question:** Any unexpected success stories shared by users regarding the positive impact of
the AI model?

Users have shared success stories, particularly in fraud detection, prompting us to explore more
diverse applications and potential areas for improvement.
4.4 Empathy Map
M a p w h a t the users say, think, d o a n d feel about the p r o b l e m in this table.

What our users are saying: What our users thinking:

“I rely on classification systems as I find it hard to “I hope this technology can keep up with ever
differentiate due to my ADHD and OCD” evolving type of items.”

“I struggle with Model usage in various settings.” “I wonder if this technology is user-friendly and easy to
learn.”

“How can I trust that my personal data and privacy are

protected?”

What our users are doing: How our users feel:

- S e e k s out tools o r res ources that help them -Inadequacy

differentiate and classify.
- Confused
-Asks for help at times needed.

4.5 What are the usual steps that users currently take related to the problem and
where are the difficulties?

1. Navigate Through Overwhelming Details

2. Communicate Ambiguous Perceptions
3. Navigate Safety Hazards
4. Navigate Social Interactions
5. Navigate Educational Materials
6. Navigate Employment Challenges
4.6 Write your team’s problem statement in the format below.

H o w can w e help People with disabilities which lead them to not be able to distinguish [group

of users] to find a w a y to classify items [do what] so that it is easier for them to distinguish

and live an easier life.[ d o s o m e t h i n g not d o n e before that c a n b e measured].

Rate yourself

3
Problem definition

1 point- T h e user g r o u p is described but it is unclear h o w they are a ected b y the problem.

2 point- U n d e r s t a n d i n g o f the user g r o u p is evidenced b y completion o f m o s t of the steps in the section.

3 point- U n d e r s t a n d i n g o f the user g r o u p is evidenced b y completion o f m o s t of the steps in the section a n d

thorough investigation.

5. Brainstorming

5.1 Ideas
H o w might y o u use the p o w e r of A I / m a c h i n e learning to solve the users’ p r o b l e m b y increasing their

k n o w l e d g e o r improving their skills?

AI ideas #1 Feature Engineering Enhancement

AI ideas #2 A u g m e n t e d Tr a i n i n g D a t a

AI ideas #3 H y p e r P a r a m e t e r Tu n i n g

AI ideas #4 Ensemble Learning Techniques

AI ideas #5 Continuous Feedback Integration

5.2 Priority Grid
Evaluate y o u r five A I ideas ba se d o n values to users a n d ease of creation a n d implementation.

High value to users,easy to create High value to users, hard to create

Ensemble Learning Techniques Continuous Feedback Integration

Low value to user, easy to create Low value to users, hard to create

Hyper Parameter Tuning Augmented Training Data

Easy EASE OF DEVELOPMENT Hard

5.3 Based on the priority grid, which AI solution is best fit for your users and for your
t e a m to create a n d implement
Briefly s u m m a r i z e the idea for y o u r solutions in a f e w sentences a n d b e sure to identify the tool that

you will use.

We have decided upon a Classification System Model. The advantages of converting the
current s y s t e m to Recognition m o d e l will b e
1 . E ff i c i e n t C a t e g o r i z a t i o n
2. Predictive Insights
3. Automation of Decision-Making
4. Scalability
5. Pattern Recognition
6 . E n h a n c e d E ff i c i e n c y i n I n f o r m a t i o n
 Rate yourself

3
Problem definition

1 point- A brainstorming session w a s conducted. A solution w a s selected.

2 point- A brainstorming session w a s conducted u s i n g creative a n d critical thinking. A solution w a s selected

w i t h s u p p o r t i n g a r g u m e n t s i n this s e c t i o n .

3 point- A bra instormi ng session w a s c o n d u c t e d using creative a n d critical thinking. a compelling solution

w a s selected w i t h s u p p o r t i n g a rg u m e n t s in this session.

6. D e s i g n

6.1 What are the steps that users will now do using your AI solution to address the
problem?

[Link] c a n recognize specific items or a se t of i te ms an d cl as s i fy t h em acco rd i n g l y.

2. A t ex t b ox is im pl em ente d so tha t users wi th p h y s i cal i m p ai rm en t can s t i l l fi n d i t eas i e r t o u s e

3.T h e m o d e l c a n classify dozens of items in a second with a score bar at bottom which tells the
percentage of items actually matching the trained classification date

4.T h e m o d e l c a n identify a n d correct errors or inaccuracies, providing f e e d b a c k o r suggestions for

improvement.
 Rate yourself

3
Problem definition

1 point - The use of A I is a good fit for the solution.

2 point - T h e use of A I is a g o o d fit for the solution a n d there is s o m e doc umenta tion a b o u t h o w it m e e t s the

ne eds of users.

3 point - T h e use of A I is a g o o d fit for the solution. T h e n e w user experience is clearly d o c u m e n t e d s h o w i n g

h o w users will b e better s e r v e d than t h e y are today.

7. Data

7.1 What data will you need to train your AI solution?

Videos and Images , Quantity , Variation & Challenges

7.2 Where and how will you source your data?

Data needed Where will the Who owns Do you have the Ethical
data come the data? permission to considerations
from? use the data?

Have GitHub Junqiang Yes

Chen

Want/Need Youtube Teachable Yes

Machine

Nice to have Google Creative Group of

Lab People Yes
 Rate yourself

3
Data

1 point - relevant data to train the A I m o d e l h a v e been identified as well as h o w the data will b e sourced or

collected.

2 point - relevant data to train the A I m o d e l h a v e b e e n identified a s well as h o w the data will b e sourced or

collected. T h e r e is evidence that the dataset is balanced.

3 point - relevant data to train the A I m o d e l h a v e bee n identified a s well as h o w the data will be sourced or

collected. T h e r e is evidence that the dataset is balanced. a n d that safety a n d privacy h a v e b e e n considered.

8. Prototype

8.1 Which AI tool(s) will you use to build your prototype?

Te a c h a b l e m a c h i n e
8.2 Which AI tool(s) will you use to build your solution?

OpenAI User Package

8.3 What decisions or outputs will your tool generate and what further action needs
to be taken after a decision is made?

[Link] c a n recognize specific items or a se t of i te ms an d cl as s i fy t h em acco rd i n g l y.

2. A t ex t b ox is im pl em ente d so tha t users wi th p h y s i cal i m p ai rm en t can s t i l l fi n d i t eas i e r t o u s e

3.T h e m o d e l c a n classify dozens of items in a second with a score bar at bottom which tells the
percentage of items actually matching the trained classification date

4.T h e m o d e l c a n identify a n d correct errors or inaccuracies, providing f e e d b a c k o r suggestions for

improvement.
 Rate yourself

3
Data

1 point - A concept for a prototype s h o w s h o w A I model will w o r k

2 point - A prototype for the solution has b e e n created a n d trained.

3 point - A prototype f o r the solution h a s b e e n created a n d successfully trained to m e e t users’ requirements.

9. Te s t i n g

9.1 W h o are the users who tested the prototype?

1) Te a m M e m b e r s
2 ) Ta r g e t a u d i e n c e
3) N o r m a l users

9.2 List your observations of your users as they tested you solution.

1. Accuracy
2. Scalability
3. Reliability
4. U s e r friendliness

9.3 Complete the user feedback grid

What works? What needs to change?

- Recognise various items and classifies instantly. - Address any potential technical issues or glitches.
- Improve the user interface for easier use.

Questions Ideas

- Will the model work offline? - Implement a feature to actually say the name
- Is trained data enough? of item out loud
- Implement an online data feeder [Link]
9.4 Refining the prototype: Based on user testing, what needs to be acted on n o w so
that the prototype can be used?

This will include refining the user interface for better usability,fixing a n y b u g s or technical
issues,and i n c o r p o r a t i n g additional features o r functionality that u s ers f o u n d valuable.

9.5 What improvement can be made later?

1. Bug fixes
2. Performance
3. Updating Signs
4. Usability
5. Feature Enhancement

Rate yourself

3
Data

1 point - A concept for a prototype s h o w s h o w it will be tested.

2 point - A pr ototype has b e e n tested w i t h users a n d i m p r o v e m e n t s h a v e b e e n identified to m e e t user

requirement.
3 point - A prototype h a s b e e n tested w i t h fair representation o f user a n d also tasks in this section h a v e b e e n

c o m p l e t ed.

10 . Team collaboration

10.1 How did you actively work with others in your team and with the stakeholders?

● Offline sessions with counsellor for gathering data.

● Mixed sessions with group members for brainstorming.
● Work divided between various group members.
● Prototype testing done by each team members and stakeholders.
 Rate yourself

3
Data

1 point - T h e r e is s o m e evidence o f t e a m interaction a m o n g peers a n d stakeholders.

2 point - Te a m collaboration a m o n g peers a n d stakeholders is clearly d o c u m e n t e d in this section.

3 point - E ffective t e a m collaboration a n d c o m m u n i c a t i o n a m o n g pee rs a n d stakeholders is clearly d o c u m e n t e d

in this section.

11. Individual Learning Reflection

11.1 Team Reflections

A g o o d w a y to identify w h a t y o u have learned is to ask yourself w h a t surprised y o u during the project.

List the things that surprised y o u a n d a n y other thoughts y o u m i g h t h a v e o n issues in y o u r local

c o m m u n i t y.

Team member name: Adesh Patel

Throughout this project, I’ve witnessed the power of our classification model in addressing diverse
challenges. Personally, this journey has not only honed my technical skills in classification but has
also deepened my understanding of effective problem-solving. As we conclude, I’m confident that
the impact we’ve made will continue to resonate across the varied domains we aimed to influence.

Team member name: Chaitanya Trivedi

Completing the Classification AI Model project was incredibly rewarding. Exploring

classification algorithms deepened my understanding of AI applications, and the
collaborative teamwork significantly contributed to my growth. Excited to apply these skills
in the future.
 Rate yourself

Individual Learning Reflection

1 point - S o m e t e a m m e m b e r s present a n a c c o u n t of their learning d u r i n g the project.

2 point - E a c h t e a m pres en ts a n a c c o u n t o f their learning d u r i n g the project

3 point - E a c h t e a m m e m b e r presents a reflective a n d insightful a c c o u n t of their learning d u r i n g the project.

12. Video link

URL of your team video:
 Code

Main Code File : [Link]

Output Screen
 Bibliography
Website :

· [Link]
· [Link]
· [Link]
· [Link]