AI PROJECT LOGBOOK

Resource for Students

(Adapted from “IBM EdTech Youth Challenge – Project Logbook” developed by IBM
in collaboration with Macquarie University, Australia and Australian Museum)

KEY PARTNERS

INDIA IMPLEMENTATION PARTNERS

GLOBAL PARTNERS

1
 AI Project Logbook

PROJECT NAME: Traffic light management system

SCHOOL NAME: SHREE VASISHTHA VIDHYALAYA

YEAR/CLASS: 2025-26, 12thS3

TEACHER NAME: Ms. Saleha Maam

TEACHER EMAIL: MEENUKUMAR@[Link]

TEAM MEMBER NAMES AND GRADES:

1. Ikshit Valand XII

2. Jaimik patel XII

3. Taksh patel XII

4. Vedant patel XII

5. Sarvatit patel XII

2
1. Introduction
The AI Traffic Light Management System uses cameras and artificial intelligence to detect vehicles,
analyze traffic density, and dynamically control traffic lights. Using computer vision (e.g., YOLOv8,
OpenCV) on hardware like Raspberry Pi or Jetson Nano, it optimizes green light duration to reduce
congestion and waiting time. The system can identify emergency vehicles, giving them signal priority.
Data is stored for analysis to improve city planning and traffic efficiency.
This smart system enhances road safety, reduces fuel waste and emissions, and supports the
development of intelligent, adaptive traffic control infrastructure for modern smart cities.

2. Team Roles
2.1Whoisinyourteamandwhat are their roles?

Role Role description Team Member Name

Allocates tasks to team members,

Project leader ensures timely completion of work, Ikshit Valand
addresses any queries or issues,
and serves as the single point of
contact.
Determines the required data and
its type for model training, collects Vedant Patel
Data expert the data, and verifies its quality,
consistency, and authenticity.

Collects queries from end users that

require responses, finds accurate
Information answers to those queries, and Taksh Patel
researcher compiles a report to be submitted to
the project leader.

Designer Will create the design and the flow

of how to go about making the Sarvatit Patel
solution for the problem statement.

Prototype Builds and trains the model, followed

builder/coder Tester by testing to assess its performance, Jaimik Patel
efficiency, and accuracy.

3
 2.2 Project plan

The following table is a guide for your project plan. You may use this or create your own
version using a spreadsheet which you can paste into this section. You can expand the
‘Notes’ section to add reminders, things that you need to follow up on, problems that need
to be fixed urgently, etc.

Phase Task Planned Planned Planned Actual Actual Actual Who is Notes/Remarks
start date end date duration start date end date duration responsible
(hours, (hours,
minutes) minutes)
07.5
08-09 Hours
Preparing for Coursework, 09/11/2025 Ongoing 10/11/2025 15/11/2025 Team Each member is
the project readings Hours Members responsible
08.5
09
Set up a Hours Team
09/11/2025 09/11/2025 Hours 10/11/2025 15/11/2025
team folder Members
on a shared
drive
Background
Defining the reading 10/11/2025 10/11/2025 1 Hours 10/11/2025 10/11/2025 1 Hours Team Collaborative
problem Research Members work
issues in our 10/11/2025 10/11/2025 Team
community 10/11/2025 1 10/11/2025 1.5
Night Hours Night Hours Members
Team
meeting to
discuss 04/08/2023 04/08/2023 1.5 04/08/2023 04/08/2023 1.5 Team
issues and Evening Hours Evening Hours Members
select an
issue for the
project

Complete
section 3 of
the Project 05/08/2023 05/05/2023 15 Mins 05/08/2023 05/08/2023 15 Mins Team
Logbook Members
Rate
yourselves
Identify 3/3
users

Understanding 03/08/2023 03/08/2023 30 Mins 03/05/2023 03/08/2023 30 Mins Team Online

the users Members interactions
with the end
user

Meeting with 05/08/2023 05/02/2023 30 Mins 05/08/2023 05/08/2023 30 Mins Team

users to Members
observe
them
Interview
05/08/2023 05/08/2023 15 Mins 05/08/2023 05/08/2023 15 Mins Team
with user (1) Members
Interview
Team
with user (2), 05/08/2023 05/08/2023 15 Mins 05/08/2023 05/08/2023 15 mins
etc.… Members

Complete
section 4 of 05/08/2023 05/08/2023 30 Mins 05/08/2023 05/08/2023 30 Mins Team Collaborative
the Project Evening Members work
Logbook
Rate
yourselves
3/3
Team
meeting to
generate
Brainstorming 05/08/2023 05/08/2023 1.5 05/08/2023 05/08/2023 1.5 Team
Hours Hours Members

4
 ideas for a
solution
Complete
06/08/2023 06/08/2023 30 Mins 06/08/2023 06/08/2023 30 Mins Team Collaborative
section 5 of Morning Members work
the Project
Logbook
Rate
yourselves 3/3 Team
Team Members
meeting to Team
Designing design the 06/08/2023 06/08/2023 3.5 06/08/2023 06/08/2023 3.5
your solution Afternoon Hours Afternoon Hours Members
solution
Complete
section 6 of
the logbook 06/08/2023 06/08/2023 30 mins 06/08/2023 06/08/2023 30 Mins Team Collaborative
Morning Morning Members work
Rate
yourselves
Team 3/3
meeting to
discuss data
Collecting and requirements 03/08/2023 03/08/2023 30 Mins 03/08/2023 03/08/2023 30 Mins Team
preparing data Data Members
collection

Collecting and 03/08/2023 03/08/2023 1 Hour 03/08/2023 03/08/2023 1 Hour Rishit

preparing data Awasthi
Prototyping

Data 04/08/2023 04/08/2023 2 Hours 04/08/2023 04/08/2023 2 Hours Team

preparation Members
and labelling
Complete
05/08/2023 05/08/2023 30 Mins 05/08/2023 05/08/2023 30 Mins Team Collaborative
Section 6 of Members work
the Project
Logbook
Team
meeting to 06/08/2023 06/08/2023 4 Hours 06/08/2023 06/08/2023 4 Hours Team Code testing
plan Members
prototyping
phase

Train your
Prototyping model with 07/08/2023 07/08/2023 07/08/2023 07/08/2023 Team Designing
Testing input dataset End of the Members
day
Test your
model and 08/08/2023
08/08/2023 30 Mins 08/08/2023 08/08/2023 30 Mins Team Code testing
keep training Members
with more
data until
you think
your model
is accurate
Write a
program to
initiate 08/08/2023 08/08/2023 45 Mins 08/08/2023 08/08/2023 45 Mins Team
actions Members
based on the
result of your
model

Complete
section 8 of
the Project 08/08/2023 08/08/2023 15 Mins 08/08/2023 08/08/2023 15 Mins Team Collaborative
Logbook Members work

5
 Rate 3/3
yourselves
Team
08/08/2023 08/08/2023 10 Mins 08/08/2023 08/08/2023 10 Mins Team Collaborative
meeting to Members work
discuss
testing plan
Invite users
Testing to test your 09/08/2023 09/08/2023 15 Mins 09/08/2023 09/08/2023 15 mins Team
Creating the prototype Members
video
Conduct
testing with 09/08/2023 09/08/2023 30 Mins 09/08/2023 09/08/2023 30 Mins Team
users Members

Complete
section 9 of 09/08/2023 09/08/2023 30 mins 09/08/2023 09/08/2023 10 Mins Team Collaborative
the Project Members work
Logbook
Rate
yourselves
3/3 Team
Team
Members
meeting to
discuss Team
09/08/2023 09/08/2023 10 Mins 09/08/2023 09/08/2023 10 Mins Collaborative
video Members work
creation

Write your
script
Film your 10/08/2023 10/08/2023 20 Mins 10/08/2023 10/08/2023 20 Mins Team
video Members
Edit your Team
video 10/08/2023 10/08/2023 30 Mins 10/08/2023 10/08/2023 30 Mins
Members
Reflect on Team
the project 10/08/2023 10/08/2023 30 Mins 10/08/2023 10/08/2023 30 Mins Members
with your
team Team
Members
Completing Complete 11/08/2023 11/08/2023 10 Mins 11/08/2023 11/08/2023 10 Mins
the logbook sections 10
and 11 of the
Project
Logbook
11/08/2023 11/08/2023 20 Mins 11/08/2023 11/08/2023 20 Mins Team Collaborative
Review your Members work
Project
logbook and
video
Submit your
entries on 11/08/2023 11/08/2023 10 Mins 11/08/2023 11/08/2023 10 Mins Team
the IBM Members

Submission 11/08/2023 11/08/2023 10 Mins 11/08/2023 11/08/2023 10 Mins Team Individual on

Members google
classroom

2.3 Communications plan

6
 Will you meet face-to-face, online or a mixture of each to communicate?

Mixture Of Each
How often will you come together to share your progress?
Once a day for an hour meeting and, sometimes twice a day for an hour meeting.
Who will set up online documents and ensure that everyone is contributing?
We have created a shared folder on cloud and we all are contributing to that
What tools will you use for communication?
Google Meet for Online Meetings,
Google Drive and Google Docs for collaborative documentation and work.

2.4 Team meeting minutes (create one for each meeting held)

Date of meeting: 20-09-25 (Morning)

Who attended: Jaimik Patel, Ikshit Valand, Taksh Patel, Vedant Patel, Sarvatit Patel
Who wasn’t able to attend:Nil

Purpose of meeting: Preparing for the Project and Set up a team folder on a shared
drive
Items discussed:

1. Describing the problem

2. Understanding road users to identify their issues/problems related to traffic congestion,
delays, rule violations, and safety concerns, especially in areas with heavy traffic flow.

Thingstodo(what,bywhom,bywhen):
1. Understand the main problems in current traffic management such as congestion,
rule violations, and delays, especially where manual systems fail.
2. Each member should think about how AI detection systems (like cameras, sensors,
vehicle counting, and violation detection) can help, focusing on the initial setup and
working.
3. All members must bring their ideas together and discuss possible solutions by the same
day afternoon.

7
Date of meeting: 20-09-25 (evening)
Who attended:Jaimik Patel, Ikshit Valand, Taksh Patel, Vedant Patel, Sarvatit Patel
Who wasn’t able to attend: Nil
Purpose of meeting: To discuss traffic-related problems and select a suitable issue for the
project using AI detection systems.

Items discussed:
1. Researched various issues in current traffic management systems.
Discussedtheidentifiedissuestodecidewhichareaneedsimprovement.
2. 3.
Finalizedthetopicfortheproject: TrafficManagementusingAIDetection Systems.
Thingstodo(what,bywhom,bywhen)

1. Research done by everyone

2. Everyone participated on certain issues and had a common issue
3. The common issue has been selected for the project

Date of meeting: 21-09-25

Who attended: Jaimik Patel, Ikshit Valand, Taksh Patel, Vedant Patel, Sarvatit Patel
Who wasn’t abletoattend: Nil

Purpose of meeting: Online interaction with road users (drivers, commuters, pedestrians)

Items discussed:

1. Whatinformation do roadusers expect from an AI-based traffic management system?

2. Important factors they want improved, such as signal timing, congestion reduction,
violation detection, and safety.

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

1. Setupthecallandcollectuserinputsthat will help in designing the traffic AI solution.

2. Eachteammemberwillparticipateandgather insights.
3. To be completed on the same day.

8
Date of meeting: 22-09-25
Who attended: Jaimik Patel, Ikshit Valand, Taksh Patel, Vedant Patel, Sarvatit Patel
Who wasn’t abletoattend: Nil

Purposeof meeting: Team meeting to generate ideas for an effective traffic management
solution.
Items discussed:

1. Discussedwhatneeds to be done to make traffic monitoring more efficient, faster, and

lessdependenton manual effort.
2. Decided onthesolution: developing an AI-based Traffic Detection System that can
identify violations, monitor congestion, and assist in automated traffic control.

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

1. Collecttrafficvideos/images,designthesystem interface, and develop AI models for

2. detectionusingComputerVisionandMachine Learning.
3. Eachteammemberwillcompletetheassigned tasks based on their specific roles.
Tobecompletedwithinthesametimeframe.

9
 Date of meeting: 23-09-25
Who attended: Jaimik Patel, Ikshit Valand, Taksh Patel, Vedant Patel, Sarvatit Patel
Who wasn’t ableto attend: Nil

PurposeofMeeting:
Team meeting to train the dataset according to the collected traffic inputs.

Items Discussed:
1. Number of traffic images/videos required to train the dataset effectively.
2. Categorizing the dataset into different classes such as NormalTrafficCongestion,
,
and Traffic Violations .

ThingsTrain the dataset, integrate it into the AI detection code, and connect it with the
to Do(What,ByWhom,ByWhen):
1. storage system.
Each team member will complete the task based on their assigned roles.
2. To be completed on the same day.
3.

Date of meeting: 24-09-25

Who attended: Jaimik Patel, Ikshit Valand, Taksh Patel, Vedant Patel, Sarvatit Patel
Who wasn’t ableto attend: Nil

Purposeof Meeting:
Inviting road users to test the AI-based traffic detection system created.

Items Discussed:
1. Feedback collected from users regarding system performance and accuracy.
2. Discussed whether any improvements or adjustments are required.
3. Identified specific changes or enhancements suggested by users.

Things toDo(What,ByWhom,ByWhen):
1. Implement the required changes or improvements in the system.
2. Each team member will work on the updates according to their roles.
3. To be completed on the same day.

10
3. Problem Definition
3.1 List important local issues faced by your school or community

The problem addressed in our project is that traffic monitoring and rule-violation detection
are still done manually, which can lead to human errors, delays, and inefficiency. An AI-
based detection system can continuously monitor traffic, identify violations, and manage flow
more accurately and reliably, reducing lapses and improving overall traffic control.
We have focused on this topic to save time and increase efficiency by allowing AI to accurately
detect traffic violations and analyze vehicle movement. This system reduces human effort,
minimizes manual errors, and decreases the overall manpower needed for traffic monitoring.
The issues that we have tried to correct in our project are: -

● Lack of Real-Time Monitoring

● Emergency Vehicle Delay

● Traffic Congestion at Intersections

● Fixed-Time Traffic Signals

3.2 Which issues matter to you and why?

The issue we aim to address is that the current offline/manual traffic monitoring process
consumes a lot of time, and during this delay, road users face congestion, stress, and unsafe
conditions.
An AI-based system can analyze traffic patterns, detect violations, and process large
amounts of data much faster and more accurately than humans. Our program is designed to
precisely detect traffic violations and monitor vehicle flow by calculating accuracy and
precision levels.
We aim to reduce time consumption and make the traffic management process more
efficient so that timely action can be taken to improve safety and traffic flow.

3.3 Which issue will you focus on?

This AI-based online approach will help make the process of detecting traffic violations and
monitoring vehicle flow fully automated, saving a significant amount of time and reducing the
need for manual manpower.
The AI system will gather essential traffic information, analyze the live or uploaded footage,
calculate accuracy and precision levels, and automatically detect violations or congestion
based on the input data.

11
3.4 Write your team’s problem statement in the format below.

Our AI system developed by the team aims to provide a more effective and accurate method
for detecting traffic violations and monitoring road conditions. This reduces the need for
manual traffic checking and offers a quicker, more efficient, and smarter approach to
managing traffic flow and ensuring timely action for road safety.

Rate yourself 3
Problem Definition

1point - A local problem is described

2points - A local problem which has not been fully solved before is described.
3points - A local problem which has not been fully solved before is explained in detail with supporting
research.

12
4. The Users
4.1 Who are the users and how are they affected by the problem?

Theusers are:
– Drivers
– Public
– TrafficPolice
– RoadSafetyAuthorities
Each user is affected in different ways:
DriversandPublicbenefit from smoother traffic flow and quicker detection of violations that
improve safety.
Trafficpoliceusethe system to identify violations more accurately and reduce manual
monitoringeffort.
Roadsafetyauthorities analyze the detected patterns to plan better traffic management
strategiesandimprove overall road safety.

4.2 What have you actually observed about the users and how the problem affects
them?

Traffic problems cause significant stress for road users. Long traffic jams, slow-
moving lanes, and unexpected delays increase frustration and anxiety among
drivers. This stress can lead to aggressive driving, lack of focus, and impatience
on the road, which increases the chances of accidents. Continuous honking,
heat, and congestion further raise stress levels and blood pressure, making
driving unsafe and uncomfortable.
The manual/offline traffic monitoring process is extremely time-consuming—
from police manually identifying violations to controlling signals and managing
congestion. This delays action, causes long waiting times, and results in fuel
wastage. It is also expensive, requiring high manpower and physical monitoring
for long hours.
When unexpected traffic issues occur, such as long jams or sudden diversions,
road users often panic or become anxious due to the sudden disruption,
especially when they have urgent commitments. Traffic is a sensitive issue that
affects people’s daily routine, mental state, and safety.

13
4.3 Record your interview questions here as well as responses from users.

Interviewer: Can you share your thoughts on the AI-based traffic

detection system you've been using? User: Absolutely, I'd be happy to.
Firstly, I want to express my appreciation for this amazing tool. It has
truly transformed the way we approach traffic monitoring and road
safety. Interviewer: That’s wonderful to hear! What specifically stands
out to you about the system? User: The accuracy and efficiency are
outstanding. Knowing that there’s a reliable system continuously
monitoring traffic brings a great sense of relief. It saves time, reduces
congestion, and helps prevent accidents through quick detection of
violations and unsafe conditions. Interviewer: How do you find the user
interface and the way the results are displayed? User: The user
interface is very intuitive and easy to navigate, suitable for both traffic
officers and road safety authorities. The clear presentation of alerts and
detected issues builds confidence in the system and helps users trust its
decisions. Interviewer: It sounds like the system has had a strong
impact. Any final thoughts? User: Definitely. I’m truly grateful for the
hard work and expertise that went into developing this system. It’s a
major step forward in traffic management technology and brings hope
for safer, smoother, and more efficient roads. Thank you for creating a
solution that genuinely improves daily commuting and overall road
safety.

14
4.4 Empathy Map

Map what the users say, think, do and feel about the problem in this table

What our users are saying What our users thinking

● How time-consuming will my

● Is the traffic information daily commute be?
accurate? Can I rely on the AI ● How quickly can I get traffic
● system for real-time updates? updates or violation alerts?
Which route should I take for ● Is the road ahead clear or
● the fastest and safest travel? congested?
● Are there any violations or
safety risks I should be aware
of?

What our users are doing How our users feel

● Not taking timely action while ● CONFUSED

driving
● Procrastinating on updating ● ANXIOUS
themselves about traffic
conditions ● STRESSED
● Not following signals or
avoiding consulting traffic
guidelines

15
4.5 What are the usual steps that users currently take related to the problem and where
are the difficulties?

Usual steps that users currently take and the difficulties they face — illustrated
through a hypothetical scenario

Adriver is commuting through a busy city area.

Driver
The traffic seems very heavy today. I need to reach my destination soon.
Driver asks a traffic police officer:
Officer,isthere any way to know which route is free?
Officer:
You’ll haveto wait; we are checking the situation manually. Take the usual route for now. The
driverfollows the usual route and gets stuck in heavy traffic for over an hour. Later…

Driver:
Why isthe traffic not moving? Is there an accident? A signal problem? I’m getting late… The
driver gets frustrated as no real-time update is available. He continues waiting without
knowing the actual cause—whether it’s congestion, a violation, a blockedlane, or a signal
malfunction.
After along delay, the driver finally reaches a traffic checkpoint.
Officer:
There was a major slowdown because of a signal failure and several vehicles blocking the
lane. We couldn't manage it earlier because manual monitoring takes time.
Driver: Ifonlywe had quicker information, I could have taken another route.

16
4.6 Write your team’s problem statement in the format below.

Our AI system developed by the team will provide a more effective and accurate method for
detecting traffic violations, congestion, and unusual road conditions. This reduces the need for
manual monitoring, making the entire process quicker, more efficient, and smarter. By enabling
real-time detection and faster decision-making, our system ensures smoother traffic flow and
timely action to improve road safety.

Rate yourself 3

The Users

1point - The user group is described but it is unclear how they are affected by the problem.
2points - Understanding of the user group is evidenced by completion of most of the steps in this
section.
3points - Understanding of the user group is evidenced by completion of most of the steps in this
section and thorough investigation

17
5. Brainstorming
5.1 Ideas

How might you use the power of AI/machine learning to solve the users’ problem by increasing
their knowledge or improving their skills?

AI Idea #1 CNN (Convolutional neural network) USING PYTHON

AI Idea #2 TEACHABLE MACHINE

AI Idea #3 COMPUTER VISION USING CAMERAS

AI Idea #4 PICTOBLOX

18
 5.2 Priority Grid

Evaluate your five AI ideas based on value to users and ease of creation and implementation.

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

TEACHABLE MACHINE CNN

VALUE TO USERS

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

COMPUTER VISION USING CAMERAS PICTOBLOX

Low Easy Hard

EASE OF DEVELOPMENT

19
5.3 Based on the priority grid, which AI solution is the best fit for your users and for
your team to create and implement?

Briefly summarize the idea for your solution in a few sentences and be sure to identify the tool
that you will use.

CNN – A Convolutional Neural Network (CNN) is a deep learning

algorithm that is very effective for analyzing images and video frames,
which makes it useful in traffic light management systems. In our project,
CNN helps the Python-based system understand traffic density by
processing live camera feeds. The convolutional layers extract important
features such as the number of vehicles, their positions, and movement
patterns. Pooling layers reduce unnecessary details while keeping the
essential information. Finally, the fully connected layers classify the traffic
situation—low, medium, or high congestion.
Using this CNN model in Python has helped us automate traffic light
timing based on real-time traffic density. It adjusts signal durations
dynamically and improves traffic flow. The model achieved an accuracy of
up to 99.48%, making it highly reliable for smart traffic light management.

Rate yourself
3
Brainstorming

1point – A brainstorming session was conducted. A solution was selected.

[Link]
selected with supporting arguments in this section
3points - A brainstorming session was conducted using creative and critical thinking. A compelling
solution was selected with supporting arguments in this section.

20
6. Design
6.1 What are the steps that users will now do using your AI solution to address the
problem?

1. The traffic operator or system administrator will input real-time traffic data (or upload
sensor/camera data), and the program will immediately analyze it to provide optimized signal
timings.

2. The Python-based traffic management system will handle all traffic-related queries from
different stakeholders such as operators, field engineers, and monitoring staff.

3. If the system is unable to process the traffic data due to poor input quality or missing
information, it will ask the user to re-enter or upload the correct data.
4. If the query is outside the predefined traffic conditions or scenarios stored in the
system, the user will be redirected to the main control panel where a traffic engineer or
programmer can be contacted for manual assistance.

Rate yourself 3

Design

1point – The use of AI is a good fit for the solution.

2points - The use of AI is a good fit for the solution and there is some documentation about how it
meets the needs of users
[Link]
showing how users will be better served than they are today.

21
7. Data

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

General traffic irregularities that are commonly observed on most roads, indicating unusual
patterns or conditions that may require further monitoring or corrective action.

7.2 Where or how will you source your data?

Where will the Do you have Ethical

data come Who owns the permission to use considerations
Data needed from? data? the data?

Have Surgical Hospitals, Yes Data should not

centers, Dispensaries be shared
Previous data without
recordings permission

Want/Need Surgical Hospitals, Yes

centers, Dispensaries
Previous data
recordings

Nice to have Surgical Hospitals, Yes

centers, Dispensaries
Previous data
recordings

Rate yourself 3

Data

1point – Relevant data to train the AI model have been identified as well as how the data will be
sourced or collected.
2points - Relevant data to train the AI model have been identified as well as how the data will be
sourced or collected. There is evidence that the dataset is balanced.
3points - Relevant data to train the AI model have been identified as well as how the data will be
sourced or collected. There is evidence that the dataset is balanced, and that safety and privacy have
been considered.

22
8. Prototype

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

Python using Google Colaboratory

8.2 Which AI tool(s) will you use to build your solution?

Python using Google Colaboratory

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

Main pointers of the program: –

1. The system will analyse live traffic images or video feeds and provide the
updated traffic status once the scan is completed, along with efficiency and
accuracy metrics.

2. The program will automatically detect traffic congestion, signal violations, or

vehicle density levels in the image and highlight the affected areas.

3. If the system fails to generate the required output or detect traffic conditions
properly, the user will be prompted to retry. If the issue continues, the user
may contact the developer for assistance.

Rate yourself 3

Prototype

1point – A concept for a prototype shows how the AI model will work.
2points - A prototype for the solution has been created and trained.
3points - A prototype for the solution has been created and successfully trained to meet users’
requirements.

23
9. Testing
9.1 Who are the users who tested the prototype?

● Team Members

● Teachers

● Students

● Admin staff

● Parents

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

● Team Members- Accuracy and precision rate is being calculated

properly.

● Parents - The abnormality is being detected in the image.

● Student- The program works for different inputs.

24
9.3 Complete the user feedback grid

What works What needs to change

The precision and accuracy rate calculations. The data which is not present in the predefined
Redirecting to the main page where the details dataset is to be added.
of the programmer have been mentioned.

Questions? Ideas

Needs more X-rays to be uploaded

How much time is taken to provide the results?
More work required on making the predictions
How accurate are the results? accurate

9.4 Refining the prototype: Based on user testing, what needs to be acted on now so
that the prototype can be used?

Needs more X-rays to be uploaded

More work required on making the predictions accurate

25
9.5 What improvements can be made later?

Website development with server space

Rate yourself 3

Testing

1point – A concept for a prototype shows how it will be tested.

2points - A prototype has been tested with users and improvements have been identified to meet
user requirements.
3points - A prototype has been tested with a fair representation of users and all tasks in this section
have been completed.

26
10. Team collaboration
10.1 How did you actively work with others in your team and with stakeholders?

● Regular online sessions with team members for brainstorming.

● Work divided between various group members.
●
Regular discussions with the teacher in charge to check for errors.
●
Sessions with parents to gather and work on new ideas
●
Testing of the prototype carried out by each member of the group and stakeholders
involved.

Rate yourself 3

Team collaboration

1point – There is some evidence of team interactions among peers and stakeholders.
2points - Team collaboration among peers and stakeholders is clearly documented in this section.
3points - Effective team collaboration and communication among peers and stakeholders is clearly
documented in this section.

27
11. Individual learning reflection
11.1. Team Reflections

A good way to identify what you have learned is to ask yourself what surprised you during the
project. List the things that surprised you and any other thoughts you might have on issues in
your local community.

Team member name: Krrish Aggarwal

The moments when I got really intrigued was while analyzing the data and
putting all the data set into the code as image detection was so accurate
that I could find all the right variations in the results which were not in my
mind. Rest when the graphs were shown according to my expectation. I
never thought that computer vision and CNN would be able to point out
images properly and could segregate it according to the proposition we
thought of.

Team member name: Rohan Sharma

It’s been an awesome journey! While making this bot we identified the
problem which is usually faced by the patients in case of expensive and
severe health treatments (for e.g. Lung Cancer) and especially at the time
of pandemic when doctors were not easily available so we came up with
the idea of making a website and building a program using computer
vision and CNN in order to predict Lung Cancer with the help of CT scans.
All members put in great efforts. We had great brainstorming sessions.
Making this program and especially designing the website helped me
understand various AI concepts also.

Team member name: Rishit Awasthi

What actually surprised me was the part of the data collection as I was
expecting only 500-600 CT scanned images would be enough for the part
of data processing but during the process, I realized that the algorithm
demanded more images than expected so I had to put around 2000-3000
images with proper segregation of malignant, cancerous and non-
cancerous results. I also got to learn that I need to explore more websites
for the authenticity of the data which taught me we could actually use AI
technology for the benefit of humankind.

28
Note: Add more boxes if there are more members in your team

Rate yourself 3

Individual Learning Reflection

1point – Some team members present an account of their learning during the project.
2points - Each team presents an account of their learning during the project.
3points - Each team member presents a reflective and insightful account of their learning during the
project.

12. Video link

Enter the URL of your team video:

Code Link:
[Link]
scrollTo=gk701FEq4_h0

Video Link:
[Link]
cRI1ByHr/view?usp=sharing

29