AI Project Logbook

PROJECT NAME: ETHINICITY DETECTION

SCHOOL NAME: MAHARISHI VIDYA MANDIR

YEAR/CLASS: 2024-25/ XII A2

TEACHER NAME: S.RAMYA

TEACHER EMAIL: [email protected]

TEAM MEMBER NAMES AND GRADES:

1. SAKTHI SHABARIESHVAR XIIA2

2. AAYUSH XIIA2

3. ADITYA XIIA2

4. KANISHK XIIA2

5. PRATIK KOTHARI XIIA2

6. RAGHAVAN XIIA2

7. SAI HARESH XIIA2

2
1. Introduction
People from all over the world make up a colorful mix of different ethnic groups, each with
its own special culture and looks. Figuring out which continent someone's ethnic
background comes from can tell us a lot about their family history and cultural roots. This
project looks into how AI might be able to and sort people based on which continent their
ethnicity is from. We want to build a dependable AI system that can pinpoint people's
continental background by using machine learning methods and ways to recognize images.

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

Role Role description Team Member

Name
 Schedules and allocates tasks among
the team.

PROJECT LEADER  Ensures tasks are completed on time. SAKTHI

SHABARIESHVAR
 Acts as the point of contact between the
team and the teacher, users and
stakeholders.

 Resolves team issues

 Decides on type of data needed to train an
AI model
DATA EXPERT
 Collects data ADITYA

 Ensures data is in a format that the team

can work with

 Ensures data is ethically sourced and

unfair bias is eliminated

 Works with prototype builder to train

the AI model

3
  Collects questions from the team that
need answers.
INFORMATION AAYUSH
RESEARCHER  Identifies where answers can be
located (source) .

 Searches for answers, writes up a

report and passes information to the
project reporter
 Works with the team and the user to
create a process flow for the new user SAI HARESH
DESIGNER experience

 Plans the user interface for the prototype

 Works with data expert to
train/teach computer RAGHAVAN
PROTOTYPE
BUILDER/CODER  Creates the prototype and codes if
necessary

 Works with users to tests the prototype

TESTER  Gets feedback from users and user PRATIK

sign-off when they prototype has met
user requirements

 Creates an action plan on what needs

to be fixed and prioritises requests for
future improvements

 Collates the team Project Logbook

submission and creates the content
MARKETING/ for the video pitch SAKTHI
COMMUNICATION SHABARIESHVAR
LEADER  Selects spokespeople within the
team for various matters relating to
the project

 Films the activities of the team and KANISHK

VIDEO PRODUCER edits these into a presentation for
submission

4
 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 fixedurgently,
etc.

Phase Task Planned Planned Planned Actual Actual Actual Who is Notes/Remarks
start end duration start end date duration responsible
date date (hours, date (hours,
minutes) minutes)
Preparing for Coursework, 07/07/2024 4 hours 04/07/2024 07/07/2024 4 hours TEAM LEADER
the project readings 04/07/2024

Set up a
team folder
on a shared
drive
Defining the Background 07/07/2024 14/07/2024 4 hours 07/07/2024 14/07/2024 4 hours TEAM LEADER
problem Reading
DATA EXPERT
Research
issues in our
community INFORMATION
RESEARCHER
Team
meeting to
discuss
issues and
select an
issue for the
project

Complete
section 3 of
the Project
Logbook
Understanding Identify users 14/07/2024 21/07/2024 4 hours 14/07/2024 21/07/2024 4 hours INFORMATION
the users RESEARCHER
Meeting with
users to
observe
them
Interview
with user (1)
Interview
with user (2),
etc…
Complete
section 4 of
the Project
Logbook
Brainstorming Team 21/07/2024 25/07/2024 3 hours 21/07/2024 25/07/2024 3 hours INFORMATION
meeting to RESEARCHER
generate
ideas for a
Solution

Complete
section 5 of
the Project
Logbook
Designing Team 25/07/2024 27/07/2024 2 hours 25/07/2024 27/07/2024 2 hours DESIGNER
your solution meeting to
design the
solution
Complete
section 6 of
the logbook
Collecting and Team 27/07/2024 31/07/2024 3 hours 27/07/2024 31/07/2024 3 hours DATA EXPERT
preparing data meeting to
discuss data
requirements

5
Collecting and Data 01/08/2024 07/08/2024 3 hours 01/08/2024 07/08/2024 3 hours DATA EXPERT
preparing data collection
Prototyping PROTOTYPE
BUILDER/CODER
Data
preparation
and labelling

Complete
Section 6 of
the Project
Logbook

Team
meeting to
plan
prototyping
phase
Prototyping Train your 08/08/2024 14/08/2024 4 hours 08/08/2024 14/08/2024 4 hours PROTOTYPE
Testing model with BUILDER/CODER
input dataset

Test your
model and
keep training
with more
data until you
think your
model is
accurate

Write a
program to
initiate
actions
based on the
result of your
model

Complete
section 8 of
the Project
Logbook

Team
meeting to
discuss
testing plan
Testing Invite users 15/08/2024 21/08/2024 2 hours 15/08/2024 21/08/2024 2 hours TESTER
Creating the to test your
video prototype VIDEO PRODUCER

Conduct
testing with
users

Complete
section 9 of
the Project
Logbook

Team
meeting to
discuss
video
creation

Write your
script

Film your
video

Edit your
video
Completing Reflect on 21/08/2024 23/08/2024 1 hour 15/08/2024 23/08/2024 1 hour MARKETTING/
the logbook the project COMMUNICATION
with your LEADER
team

6
 Complete
sections 10
and 11 of the
Project
Logbook

Review your
Project
logbook and
video
Submission Submit your MARKETTING/
entries on COMMUNICATIO
the IBM N LEADER

2.3 Communications plan

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

Ans) Mixture of face-to-face and online.

2) How often will you come together to share your progress?

Ans) At least once a day, sometimes once every 2 days.

3) Who will set up online documents and ensure that everyone is contributing?

Ans) A shared Google drive, remainder sent regularly for everyone to do respective work

4) What tools will you use for communication?

Ans) Google meet

2.4 Team meeting minutes

DATA OF MEETING: 04/07/2024

WHO ATTENDED: Sakthi Shabarieshvar, Aayush, Aditya, Kanishk, Pratik Kothari, Raghavan,
Sai Haresh
WHO WASN’T ABLE TO ATTEND: NIL
PURPOSE OF MEETING: Introduce the project, define objectives, and outline the project
timeline.
ITEM DISCUSSED:
1) Project scope and goals
2) Data acquisition and preparation
3) AI algorithm selection (e.g., deep learning, machine learning)
4) Ethical considerations and bias mitigation
5) Team roles and responsibilities
THINGS TO DO:
1) Form a project team
2) Identify key stakeholders
3) Develop a project timeline

7
DATA OF MEETING: 10/07/2024
WHO ATTENDED: Sakthi Shabarieshvar, Aayush, Aditya, Kanishk, Pratik Kothari, Raghavan, Sai
Haresh
WHO WASN’T ABLE TO ATTEND: NIL
PURPOSE OF MEETING: Analyze the collected dataset, identify potential biases, and prepare it for
modeling.
ITEM DISCUSSED:
1) Data cleaning and normalization
2) Feature engineering and selection
3) Handling imbalanced datasets
4) Data visualization to understand patterns and distributions
5) How to model the AI
THINGS TO DO:
1) Collect and organize relevant datasets
2) Perform data cleaning and preprocessing tasks

DATA OF MEETING: 17/07/2024

WHO ATTENDED: Sakthi Shabarieshvar, Aayush, Aditya, Kanishk, Pratik Kothari, Raghavan, Sai
Haresh
WHO WASN’T ABLE TO ATTEND: NIL
PURPOSE OF MEETING: Discuss ethical implications of the project and plan for deployment.
ITEM DISCUSSED:
1) Privacy and data security
2) Bias mitigation strategies
3) Transparency and explainability
4) Potential societal impacts
5) Deployment plan and monitoring
THINGS TO DO:
1) Develop an ethical framework for the project
2) Create a deployment plan
3) Implement monitoring and evaluation procedures

8
DATA OF MEETING: 28/07/2024
WHO ATTENDED: Sakthi Shabarieshvar, Aayush, Aditya, Kanishk, Pratik Kothari, Raghavan, Sai
Haresh
WHO WASN’T ABLE TO ATTEND: NIL
PURPOSE OF MEETING: Gather feedback from stakeholders and potential users.
ITEM DISCUSSED:
1) Stakeholder needs and expectations
2) User interface design and usability
3) Addressing potential biases and concerns
4) Incorporating stakeholder feedback into the project
THINGS TO DO:
1) Conduct stakeholder interviews and surveys
2) Analyze feedback and identify areas for improvement

DATA OF MEETING: 10/08/2024

WHO ATTENDED: Sakthi Shabarieshvar, Aayush, Aditya, Kanishk, Pratik Kothari, Raghavan, Sai
Haresh
WHO WASN’T ABLE TO ATTEND: NIL
PURPOSE OF MEETING: Evaluate the project's success and achievements.
ITEMS DISCUSSED:
1) Project outcomes and impact
2) Lessons learned and best practices
3) Future research directions and collaborations
4) Recommendations for future projects
THINGS TO DO:
1) Prepare a final project report
2) Present findings to stakeholders
3) Plan for future research and development

9
3. Problem Definition
3.1 List important local issues faced by your school or community

 Bias in Algorithms: AI algorithms can be biased if they are trained on data that is not
representative of the entire population. This can lead to inaccurate or discriminatory
results.
 Data Privacy Concerns: Collecting and storing personal data, such as facial images or
genetic information, can raise privacy concerns.
 Ethical Implications: The use of ethnicity detection technology can raise ethical questions
about surveillance, discrimination, and the potential for misuse.
 Cultural Sensitivity: The technology might not be culturally sensitive, especially in
communities with diverse ethnic backgrounds and traditions

3.2 Which issues matter to you and why?

 Bias: Ethnicity detectors can be biased if they are trained on data that is not
representative of the entire population. This can lead to inaccurate or discriminatory
results, perpetuating harmful stereotypes.
 Privacy: Collecting and storing personal data, such as facial images or genetic
information, for ethnicity detection can raise privacy concerns.
 Ethics: The use of ethnicity detection technology can raise ethical questions about
surveillance, discrimination, and the potential for misuse

3.3 Which issue will you focus on?

I would focus on ensuring that the technology is developed and used in a way that is ethical,
unbiased, and respects privacy.
This would involve:
Training the algorithm on diverse and representative data to minimize bias. Implementing
strong data privacy and security measures to protect individuals' information.
Considering the potential ethical implications of the technology and addressing any concerns

10
3.4 Write your team’s problem statement in the format below.

How can we help [ a specific user or group of users] find a way to

[do what] so that they can [ do something not done before that can be measured].

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

Our users include:

1) Law Enforcement- confirming the identity of individuals in various contexts
2) Researchers- Understanding population distributions and trends by analyzing demographics
3) Businesses- Personalizing services, tailoring products to individual preference

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

Businesses- International Businesses have Global customers, tailoring their products to suit a
demographic location can help business grow in a exponential amount
Law enforcement- can reduce crimes such as faking id’s
Researchers- exploring deeper end of demographic location by understanding locals features
and trends

11
4.3 Record your interview questions here as well as responses from users.

Question 1: What do you the AI model for?

Response 1: In business, personalize products for a demographic heightens profits.
Question 2: Problems faced previously before the AI model?
Response 2: Faking of id’s was a common crime which we were able to over come with the AI
Model.

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

 "I need a reliable way to identify  Accuracy and reliability of the model
individuals based on their facial  Potential biases and discrimination
features."  Ethical implications of using such
 "I'm worried about the potential for technology
bias in the model."  Privacy concerns
 "How can we ensure that this
technology is used ethically?"
 "What are the limitations of this
technology?"

What our users are doing How our users feel

 Searches for information about  Concerned about potential biases and
ethnicity detection AI discrimination
 Evaluates different models and their  Curious about the accuracy and
performance limitations of the technology
 Considers the ethical implications of  Uncertain about the ethical
using such technology implications of using such technology
 Implements the chosen model in their  Relieved at the potential for solving
application certain problems (e.g., identifying
 Monitors the model's performance suspects in criminal investigations)
and addresses any issues

12
4.5 What are the usual steps that users currently take related to the problem and where
are the difficulties?

Law Enforcement:
 Manual identification: Relying on visual observation and descriptions from witnesses.
 Traditional databases: Using fingerprint databases or other biometric information to
identify individuals.
Immigration Authorities:
 Document verification: Checking passports, visas, and other identification documents.
 Interviews: Conducting interviews to assess the credibility of individuals' claims.
Researchers:
 Census data: Analyzing census data to gather demographic information.
 Surveys and interviews: Conducting surveys and interviews to collect data on ethnicity
and other characteristics.
Businesses:
 Customer surveys: Gathering information about customer demographics through
surveys.
 Market research: Conducting market research to understand customer preferences and
behaviors.

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

[a specific user or group of users]

are experiencing issues with [problem] today

because of [cause]

13
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 Healthcare
● Personalized Medicine: Tailor treatments and medication based on genetic
predispositions associated with specific ethnicities.
● Disease Prevention: Identify at-risk populations for certain diseases and
provide targeted health interventions.

AI Idea #2 Law Enforcement

● Human Trafficking: Assisting in identifying victims of human trafficking
based on demographic information.
● Missing Persons: Providing leads in missing persons cases based on
physical characteristics.
● Criminal Profiling: Supporting investigations by providing potential suspect
profiles based on evidence
AI Idea #3 Research
● Social Science Studies: Gain insights into cultural practices, beliefs, and
behaviors.
● Genetic Research: Study the genetic variations associated with different
ethnicities.

AI Idea #4 Product recommendations

● Skin Tone Matching: Identifying a person's skin tone can help recommend
cosmetics that perfectly match their complexion.
● Hair Texture: Understanding a person's hair texture can lead to
recommendations for hair products that suit their specific needs.
● Cultural Preferences: Considering cultural preferences can help
recommend products that align with an individual's cultural identity.
● Environmental Factors: Recommendations can be tailored to the climate
and environmental conditions of the person's location.

AI Idea #5 Language Learning

● Recommend Language Resources: Suggest language learning materials
that are culturally relevant and engaging.
● Provide Contextual Understanding: Offer insights into cultural nuances
and historical context to facilitate language learning.
● Match Language Partners: Connect language learners with native
speakers from similar cultural backgrounds.

14
 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

Product
Product recommendations recommendations
VALUE TO USERS

Healthcare Research

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

Language Learning Law Enforcement

Low
Easy Hard
EASE OF DEVELOPMENT

15
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.

Product recommendations :
 Skin Tone Matching: Identifying a person's skin tone can help recommend
cosmetics that perfectly match their complexion.
 Hair Texture: Understanding a person's hair texture can lead to
recommendations for hair products that suit their specific needs.
 Cultural Preferences: Considering cultural preferences can help
recommend products that align with an individual's cultural identity.
 Environmental Factors: Recommendations can be tailored to the climate
and environmental conditions of the person's location.
Tools:
 Scikit-learn: A machine learning library for classification, regression, and
clustering.
 NLTK (Natural Language Toolkit): A Python library for natural
language processing tasks.
 TensorFlow or PyTorch: Deep learning frameworks for building and
training neural networks.
 OpenCV: A computer vision library for image processing and analysis.
 Python: A popular programming language for AI and machine learning,
with extensive libraries and frameworks.

16
6. Design
6.1 What are the steps that users will now do using your AI solution to address the
problem?

1.User Login to the model

2.User requires a photo to be uploaded or can use the camera to make the model detection a
person face

3.AI gives the demographic location of the person

4.AI gives a specification of the average human

5.User can use the data for further analysis.

7. Data

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

Pictures of a lot of humans along with their demographic location is required to train the AI
to its best performance

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?
Kaggle A data scientist in The owner listed the Photos of people used
Pictures of
Kaggle dataset as free are used with
People
permission
Want/Need

Nice to have

17