You are on page 1of 33

AI Project Logbook

PROJECT NAME : Student Stress Indicator

SCHOOL NAME : Frontline Millennium School, Tirupur

YEAR/CLASS : 12

TEACHER NAME : Mr V.Harikrishnan

TEACHER EMAIL : harikrishnan@frontlinemillenniumschool.com

TEAM MEMBER NAMES AND GRADES:

1. Praddosh S M - Grade 12

2. Arunthathi U V - Grade 12

3. Nitharsana K - Grade 12

4. Sanjith S - Grade 12

5. Sathya Priya S - Grade 12


CONTENTS

S No Particulars Page No

1 Introduction 1

2 Team Roles 2

3 Problem Definition 17

4 The Users 18

5 Brainstorming 21

6 Design 23

7 Data 24

8 Prototype 26

9 Testing 27

10 Team Collaboration 29

11 Individual Learning Reflection 30

12 Video link 32
1. INTRODUCTION

1.1 Capstone Project


A Capstone project is a multifaceted assignment that serves as a culminating
academic and intellectual experience for students, typically during their final year of
high school or middle school, or at the end of an academic programme or learning
pathway.
Capstone projects are generally designed to encourage students to think
critically, solve challenging problems, and develop skills such as oral communication,
public speaking, research skills, media literacy, teamwork, planning, self-sufficiency,
or goal setting—i.e., skills that will help prepare them for college, modern careers,
and adult life. In most cases, the projects are also interdisciplinary, in the sense that
they require students to apply skills or investigate issues across many different
subject areas or domains of knowledge. Capstone projects also tend to encourage
students to connect their projects to community issues or problems, and to integrate
outside-of-school learning experiences, including activities such as interviews,
scientific observations, or internships.

1
2. TEAM ROLES

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

Team Member
Role Description
Name

Project leader ● Schedules and allocates tasks Praddosh S M


among the team
● Ensures tasks are completed on
time
● Acts as the point of contact
between the team and the teacher,
users, and stakeholders
● Resolves team issues

Information ● Collects questions from the team Sathya Priya S


researcher that need answers
● Identifies where answers can be
located (source)
● Searches for answers, writes up a
report and passes information to
the project reporter

Data expert ● Decides on type of data needed to Sanjith S and


train an AI model Sathya Priya S
● Collects data
● 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

2
Designer ● Works with the team and the user Arunthathi U V
to create a process flow for the new
user experience
● Plans the user interface for the
prototype

Prototype builder ● Works with data expert to Nitharsana K and


train/teach computer Arunthathi U V
● Creates the prototype and codes if
necessary

Tester ● Works with users to tests the Nitharsana K


prototype
● Gets feedback from users and user
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

Marketing/ ● Collates the team Project Logbook Praddosh S M


Communications submission and creates the content
leader for the video pitch
● Selects spokespeople within the
team for various matters relating to
the project

Video producer ● Films the activities of the team and Sanjith S


edits these into a presentation for
submission

3
2.2 Project plan

Planned Planned Planned Actual Actual Actual


Phase Task Who is responsible?
start date end date Duration start date end date duration

Preparing for Praddosh S M,


the project Arunthathi U V,
Courseworks, readings 01.09.22 03.09.22 2 days 02.09.2022 05.09.22 3 days
Nitharsana K, Sanjith
S and Sathya Priya S
Set up a team folder on a
01.09.22 01.09.22 5 mins 01.09.22 01.09.22 5 mins Praddosh S M
shared drive
Defining the Sanjith S and Sathya
Researching issues 07.09.22 13.09.22 6 days 07.09.22 14.09.22 5 hours
problem Priya S
Planning team meetings 15.09.22 16.09.22 1 hour 15.09.22 16.09.22 3 hours Praddosh S M
Completing the problem
16.09.22 16.09.22 5 hours 16.09.22 17.09.22 5 hours Praddosh S M
definitions section
Understanding Sanjith S and Sathya
Identifying the users 21.09.22 21.09.22 30 mins 21.09.22 21.09.22 1 hour
the users Priya S
Sanjith S and Sathya
Interviewing the users 26.09.22 29.09.22 3 days 26.09.22 30.09.22 5 hours
Priya S
Completing the user's section 03.10.22 05.10.22 2 days 03.10.22 06.10.22 6 hours Sathya Priya S

4
Brainstorming Team meeting to generate
10.10.22 10.10.22 2 hours 10.10.22 10.10.22 2 hours Praddosh S M
ideas
Completing the
12.10.22 14.10.22 2 days 12.10.22 15.10.22 6 hours Praddosh S M
Brainstorming section
Designing your Team meeting for designing
26.10.22 26.10.22 1 hour 26.10.22 26.10.22 2 hours Arunthathi U V
solution the solutions
Completing the Design 1 hour
26.10.22 26.10.22 1 hour 26.10.22 26.10.22 Arunthathi U V
Section 30 mins
Collecting and Praddosh S M,
Team meeting to discuss data 1 hour
preparing data 31.10.22 31.10.22 1 hour 31.10.22 31.10.22 Sanjith S and Sathya
requirements 15 mins
Priya S
Collecting and Sanjith S and Sathya
Data collection 06.11.22 06.11.22 2 hours 06.11.22 07.11.22 3 hours
preparing data Priya S
prototyping Data preparation and Sanjith S and Sathya
11.11.22 11.11.22 1 hour 11.11.22 11.11.22 2 hours
labelling Priya S
1 hour Sanjith S and Sathya
Completing the design section 15.11.22 15.11.22 1 hour 15.11.22 15.11.22
20 mins Priya S
Praddosh S M,
Team meeting to plan
21.11.22 21.11.22 50 mins 21.11.22 21.11.22 1 hour Sanjith S and Sathya
prototype phasing
Priya S
Prototyping Train your model with input 28.11.22 28.11.22 2 hours 28.11.22 28..11.22 1 hour 30 Nitharsana K and

5
Testing dataset mins Arunthathi U V

Complete Prototype section


Test your model and keep
1 hour Nitharsana K and
training with more data until 06.12.22 06.12.22 1 hour 06.12.22 06.12.22
15 mins Arunthathi U V
you think your model is
accurate

Praddosh S M,
Team meeting to discuss
12.12.22 12.12.22 45 mins 12.12.22 12.12.22 55 mins Nitharsana K and
testing
Arunthathi U V
Testing
Invite users to test prototype 19.12.22 19.12.22 30 mins 19.12.22 19.12.22 55 mins Praddosh S M
creating the
video Nitharsana K and
Conducting test with papers 26.12.22 26.12.22 45 mins 26.12.22 26.12.22 45 mins
Arunthathi U V
Completing the testing
30.12.22 30.12.22 1 hour 30.12.22 30.12.22 45 mins Nitharsana K
sections
Team meeting to discuss
02.01.23 02.01.23 1 hour 02.01.23 02.01.23 50 min Praddosh S M
video creation
1 hour
Write your script 02.01.23 02.01.23 1 hour 02.01.23 02.01.23 Sathya Priya
15 mins
1 hour 1 hour
Film your video 02.01.23 02.01.23 02.01.23 02.01.23 Sanjith S
15 mins 25 mins

6
Edit your video 02.01.23 02.01.23 40 mins 02.01.23 02.01.23 1 hour Sanjith S
Completing the Praddosh S M,
Logbook Reflect on the project with Arunthathi U V,
03.01.23 03.01.23 1 hour 03.01.23 03.01.23 1 hour
your team Nitharsana K, Sanjith
S and Sathya Priya S

7
2.3 Communication Plan:

● Mode of communication:
○ Mixture of face-to-face and online communication
● Discussion timings:
○ We regularly updated each other on our progress, either physically or
through texts.
○ Video conferences were held through Zoom meetings when a stage was to
be initiated or needed a review.
● Role of team leader:
○ Setting up online documents and ensuring the contribution of everyone
○ Stepping in when a member of the team required help or inputs
○ Distributing and redistributing works
● Tools used for communication:
○ Mobile phones, Laptop, School Computer System

8
2.4 Team meeting minutes:

Date of meeting: 01.09.2022

Who attended: Praddosh S M, Arunthathi U V, Nitharsana K, Sanjith S and


Sathya Priya S

Who wasn’t able to attend: NIL

Purpose of meeting: Planning for the project, Drawing roadmap for the project
and Assigning of roles

Items discussed:
1. Timeline of the project
2. Users and team roles
3. Initiated research for problems

Things to do
1. Creating a shared drive
2. Understanding individual's roles and duties
3. Research for problems

9
Date of meeting: 15.09.2022

Who attended: Praddosh S M, Arunthathi U V, Nitharsana K, Sanjith S and


Sathya Priya S

Who wasn’t able to attend: NIL

Purpose of meeting: To define the statement of the problem and to initiate the
process of understanding the users'

Items discussed:
1. Various problems that were identified
2. Why and why not choose a particular problem
3. Defining the statement of problem

Things to do
1. Complete section 3 of the project logbook
2. Identifying our potential users and interviewing them
3. Information collected from users has to be sorted

10
Date of meeting: 10.10.2022

Who attended: Praddosh S M, Arunthathi U V, Nitharsana K, Sanjith S and


Sathya Priya S

Who wasn’t able to attend: NIL

Purpose of meeting: Brainstorming session to generate ideas

Items discussed:
1. Various solution ideas for the project
2. Why and why not an idea is ideal solution

Things to do
1. Develop the chosen idea
2. Check for flaws in chosen idea
3. Have interaction with users to confirm if the idea will be helpful or not

11
Date of meeting:26.10.2022

Who attended: Praddosh S M, Arunthathi U V, Nitharsana K, Sanjith S and


Sathya Priya S

Who wasn’t able to attend: NIL

Purpose of meeting: Design a solution to the developed idea

Items discussed:
1. Various approaches to solve the problem with given idea
2. Possible flaws and outcomings
3. Ways to address these shortcomings that may occur

Things to do
1. The designer has to develop the idea

12
Date of meeting: 31.10.2022

Who attended: Praddosh S M, Arunthathi U V, Nitharsana K, Sanjith S and


Sathya Priya S

Who wasn’t able to attend: NIL

Purpose of meeting: Shortlisting the required data and their sources

Items discussed:
1. Shortlisted the required data list
2. Verifiable and trusted sources were discussed

Things to do
1. The designer, along with the prototype builder, has to make a list of data
required and hand it over to data experts.
2. Data experts have to collect data and upload them to the shared drive

13
Date of meeting: 21.11.2022

Who attended: Praddosh S M, Arunthathi U V, Nitharsana K, Sanjith S and


Sathya Priya S

Who wasn’t able to attend: NIL

Purpose of meeting: Prototyping and Testing

Items discussed:
1. The input of data in teachable machine
2. Working efficiency of our model
3. Feedback from our users and teacher in charge

Things to do
1. To get feedback from stakeholders
2. Remodel our model according to the feedbacks

14
Date of meeting: 12.12.2022

Who attended: Praddosh S M, Arunthathi U V, Nitharsana K, Sanjith S and


Sathya Priya S

Who wasn’t able to attend: NIL

Purpose of meeting: Setting the roadmap of the Testing phase

Items discussed:
1. Required testing data were discussed and their sources were identified
2. Invitation of students to test the model

Things to do
1. Tester and Project leader will have to invite students to test model
2. Once tested, necessary remodelling has to be done to enhance the model and
address the shortcomings

15
Date of meeting: 02.01.2023

Who attended: Praddosh S M, Arunthathi U V, Nitharsana K, Sanjith S and


Sathya Priya S

Who wasn’t able to attend: NIL

Purpose of meeting: Initiating video production

Items discussed:
1. Video script writing and recording
2. The date for the video recording was fixed

Things to do
1. The video producer was assigned the duty of preparing for recording
2. Completing the logbook sections

16
3. PROBLEM DEFINITION

3.1 List important local issues faced by your school or community

1. Providing hybrid education in the contemporary context for better flexibility


and effective delivery of education with state of the art technologies
2. Developing online personalised programmes for students
3. Creating school attendance logs autonomously
4. Monitoring pupils during hands-on / activity-based training sessions
5. Facial emotion analysis to assist teachers inappropriately modifying their
lessons
6. The parents want to ensure that their children are fully grasping the
concepts taught at school.

3.2 Which will you focus on?

Facial emotion/mood analysis to assist teachers and management in appropriately


modifying their schedules to manage the stress of students

3.3 Team’s problem statement

In contemporary educational pedagogy, it has become common for students to


burst out in stress. Teachers and school administration frequently aren't aware of
it, so they keep up their demanding schedules, which only serves to exacerbate the
problem.
A few factors that encouraged us to embark on this endeavour include:
● The intensive preparation for the board examination has caused children in
Grade 12 and 10 to face significant stress.
● Some teachers and schedulers have been observed to be completely clueless
to the struggles that students face.
We, therefore, believed that we could take on this project to understand/ observe
students' mental health during their preparation.

17
4. THE USERS

4.1 Who are the users and how are they affected by the problem?
● Students
● Teachers
● Schedulers (Coordinators, Vice-Principal and Principal)
● School Administration
● Parents

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

● Students: They find it difficult to cope with the pace and sometimes fall out of the
pack, thus disrupting their preparation.
● Teachers and Schedulers: They sometimes fail to understand what students are
going through.

4.3 Empathy map


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

Students

What our users are saying What do our users think


● They are finding it challenging to ● It would be helpful if there are some
sustain the pace. applications to monitor students
effectively.

What do our users do How do our users feel


● Seek solace or relaxation elsewhere, ● Challenging
such as through entertainment or ● Demanding
recreational activities. ● Unmanageable
● Some people, out of necessity, keep ● Competitive
running without stopping for the
required respite.

18
Teachers and Schedulers

What our users are saying What do our users think


● They find it difficult to focus on all ● It would be helpful if there are some
the students. applications to monitor students
effectively.

What do our users do How do our users feel


● Have an ice breaker session with ● Challenging
students ● Unmanageable
● Clueless

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

● Speak with students to learn how they feel about


● Give them free time to engage in activities other than studying
● Taking too much time to address the problems of some in a class cause
disruption to the preparation of others who are spirited to work
● Having a nutritious and healthy diet which could influence the mood of the
students
● Giving time to engage in our hobbies at frequent intervals
● Conducting workshops by experts in the field of psychology on how to manage
stress
● Incorporating practical classes for better understanding and in a way to break
from conventional classes

19
5. BRAINSTORMING

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

AI IDEA #1 Teachers identifying students' emotions through their facial


reactions

AI IDEA #2 Creating a virtual assistant like Alexa to communicate and allow us


to express our emotions

AI IDEA #3 Incorporating a prototype model with the conventional CCTV


camera feeds to detect or analyse the students' moods

AI IDEA #4 Making a scheduling chatbot that can help students schedule


meetings with adults, as well as schedule video conferencing and
send invites to the student and adult's email addresses.

5.2 Priority Grid

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


create create
Making a scheduling chatbot that can Incorporating a prototype model with
help students schedule meetings with the conventional CCTV camera feeds to
adults, as well as schedule video detect or analyse the students' moods
conferencing and send invites to the
student and adult's email addresses.

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


create create
Creating a virtual assistant like Alexa to Creating a personal chatbot and
communicate and allow us to express enabling the kids to communicate with
our emotions a virtual mental health counsellor

20
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?

Incorporating a prototype model with the conventional CCTV camera feeds to


detect or analyse the students' moods. Though this AI idea falls under hard to
create a category, it was chosen because it's the most effective solution.

21
6. DESIGN

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

● Students would use the Google Teaching Machine's webcam to simulate how
they would demonstrate their emotions or moods.
● An application will be developed and teachers can look at them to
understand students in real-time during their classes.
● When there is wide distortion a notification will be sent to the particular
subject teacher, their class teacher and their coordinator.
● Schedulers and teachers will be aware of the situation and respond
appropriately after the student's mood or emotion has been identified.
● If there is a general feeling of melancholy or an outburst, teachers may allow
time for leisure or a break from intense preparation.

22
7. DATA

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

We require many positions that portray various moods or feelings. These poses can
be recorded when students mimic the various emotions or moods they experience.

7.2 Where or how will you source your data?

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

The image
should be used
Snapshots
School only for
Have from school Yes
Management training and
CCTV footage
testing the
system.

The images
should be used
We have to only for
Want/Need Students Yes
capture training and
testing the
system

23
● Due credit
will be given
to the
A wide range original
of postures to owners of
Nice to have express the Online sources No the data
same emotion ● The data will
or mood. only be used
for training
and testing
purposes

24
8. PROTOTYPE

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

The AI tool we prefer to use here is the TEACHABLE MACHINE (powered by


Google)

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

In the teachable machine, we will be building a model and that model can be used
with an Android App and a website.

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

The output that our tool will produce will be dependent on the poses that were
captured in the training images. It will be able to identify any expressed emotions
or moods. Further, we have to test our data by conducting a trial run in a demo
class with a boring lesson, an interesting lesson, and an interactive session. To
produce better outcomes, the model will be enhanced as necessary.

25
9. TESTING

9.1 Who are the users who tested the prototype?

● Students
● Teachers
● Schedulers (Coordinators, Vice-Principal and Principal)
● School Management
● Parents

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

● The training data was captured in a significantly brighter environment than


the classroom, which caused a difference in brightness and luminance that
decreased the degree of confidence.
● Certain emotions and moods, such as melancholy and distortion, generated
confusion and impaired determining accuracy.

9.3 User feedback grid

What works What needs to change

● Extreme emotions and moods, ● Training data with varying


such as sadness and happiness, degrees of brightness and

were easily identified. luminousness must be gathered


and trained.

Questions? Ideas

What can be done to address the ● Atmospheres with various


shortcoming and increase the accuracy? degrees of brightness should be
used to train more data.
● Recording training data in the
classroom may aid in feeding

26
high-accuracy data.

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

When the model was tested, we saw fluctuations in the predictions by the
model. This may be due to insufficient data inputs. So we have to add diverse
inputs to all the data classes to improve the output accuracy.

27
10. TEAM COLLABORATION

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

Each team member had a clear understanding of the project and the duties
assigned to them, which facilitated quick collaboration. We were able to effectively
review our model because the team and the stakeholder were in continual contact.

We held meetings as anticipated, and everything went off without a hitch. Every
participant made a significant contribution and pushed their colleagues to finish
the task. They enthusiastically embraced new duties when they were entrusted to
them when the designated individual was unable to do so for a variety of reasons
and performed them to the best of their abilities.

28
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.

Praddosh S M

It was a terrific learning opportunity for me as the project's leader and


communication representative to organise several meetings and develop a
workable model. We had several obstacles at different points in the project, which
allowed me to make sensible decisions. It assisted me in honing my leadership and
analytical or critical thinking skills. I was taken aback by our team's
communication because there were regular and crystal clear updates of their
progress in their respective duties assigned. I hope to work on other AI projects in
the future, such as smart assistants, virtual travel agents, and so on. In a nutshell,
it was a great opportunity to work with curious and thinking minds.

Arunthathi U V

First, in partnership with the team and the user, I create the process flow for the
new user experience. Additionally, working as a prototyper was interesting and
thrilling. Building the project and seeing it work as intended taught me a lot of new
things. Despite certain difficulties, I enjoyed working on the project.

29
Nitharsana K

The most evident benefit I discovered was the benefit of working in a group. The
success of any project, I discovered, depends on effective teamwork. I learned more
about the potential applications of AI in the contemporary environment.
Furthermore, I discovered how the models responded to various inputs, and user
feedback kept me inspired. This project also introduced me to prototyping and
programming.

Sanjith S

It was a fantastic learning experience, and I was surprised by the functions of AI as


solutions to today's problems. Also, to determine how the models respond to
various inputs, my job was to collect data for training the model so that the AI
could provide the best possible results which gave me deep knowledge about AI. It
was fun and interesting to create the project, and the way it was done helped me
learn a lot of new things. There were a few obstacles, but I had a great time doing
the project.

Sathya Priya S

In order to solve the issue of identifying student tension, I first gathered data
regarding student stress and was able to apply the AI Teachable Machine to
develop a solution. With the help of this great application, I was able to collect the
many types of information I needed for testing concerning students' emotions,
including happiness, confusion, and anger. I tried to tackle the issue using this
strategy; I wrote a report and explained this approach to the reporter.

30
12. Video Link

URL: https://youtu.be/jUjVxTOTsmc

31

You might also like