SIX WEEKS INDUSTRIAL TRAINING PROJECT SYNOPSIS

ON

“EDUVISION”
Submitted in the partial fulfilment of the
requirement for the Award of Degree of

Bachelor of Technology

In

Computer Science & Engineering

Session: 2023-2027

SUBMITTED TO: SUBMITTED BY:

Dr. Sandip Goyal Jasleen Singh

Head of Department 11232669

Department of Computer Science & Engineering

MAHARISHI MARKANDESHWAR DEEMED TO BE

UNIVERSITY, MULLANA.

1
EduVision: Revolutionizing Student Performance Tracking
1. Introduction:

In the modern educational landscape, the ability to analyze and predict student performance
plays a crucial role in enhancing learning outcomes and academic success. With the increasing
availability of data and advancements in technology, educators and students alike can benefit
from tools that provide insights into factors influencing academic achievement. EduVision is a
student score predictor application designed to leverage these opportunities by combining data
management, predictive analytics, and a user-friendly interface into a cohesive platform.
The primary goal of EduVision is to assist students and educators in understanding the
relationship between study habits, attendance, and academic performance. By collecting relevant
data such as attendance percentages, study hours, and previous scores, the system employs
machine learning techniques to predict future performance, thereby enabling proactive
intervention and better academic planning.

This project addresses several key challenges in education, including the difficulty of manually
tracking student progress, the lack of personalized feedback based on objective data, and the
absence of accessible predictive tools tailored to individual learning behaviors. EduVision fills
this gap by providing a comprehensive solution where users can easily input their academic data,
visualize past and predicted scores, and manage records through a secure and intuitive interface.

EduVision’s design integrates a robust MySQL database backend with Python-based

technologies such as Tkinter for the graphical user interface and scikit-learn for predictive
modeling. The application supports multiple user roles, including regular users and
administrators, allowing for secure access control and efficient data management. Features like
data entry, score prediction, visualization of results, record management, and administrative
oversight make EduVision a versatile and practical tool in educational settings.

By utilizing linear regression models, the project demonstrates how simple yet effective machine
learning algorithms can be applied to real-world educational data, producing meaningful
predictions with relatively small datasets. Furthermore, the application’s modular architecture
ensures ease of maintenance and future scalability, enabling enhancements such as integration of
more advanced algorithms, cloud-based data storage, and expanded user functionality.

In conclusion, EduVision is not just a score prediction tool—it is a step toward data-driven
education where insights empower students and educators to make informed decisions, improve
learning strategies, and ultimately foster academic excellence. This project exemplifies the
intersection of education and technology, highlighting the potential of predictive analytics to
transform how academic success is approached and supported.

2
 2. Objectives of the Project:

The primary objective of the EduVision project is to develop an intelligent and user-friendly
application that simplifies student performance tracking and provides predictive insights to
support academic decision-making. The specific goals of this project are:

1. To Build a Centralized Platform:

Create a unified application for students and administrators to manage academic records
efficiently.
2. To Implement Secure User Authentication:
Ensure role-based access (Admin and Student) with secure login/signup functionality
using encrypted password storage (bcrypt).

3. To Enable Easy Data Entry and Management:

Allow users to enter, view, update, and delete student data, including attendance, study
hours, and other relevant academic inputs.

4. To Predict Student Performance:

Use machine learning (Linear Regression) to predict student scores based on various
academic and behavioral parameters.

5. To Visualize Data Through Graphs and Charts:

Provide visual insights into student performance trends using graphs (matplotlib or
ttkbootstrap charts).
6. To Support Data Export for Offline Use:
Allow exporting student records and prediction results to Excel/CSV files for external
reporting or backup.
7. To Provide Admin Control Features:
Enable admin users to monitor overall usage, manage user accounts, and view system
statistics.

3
 3. Scope of the Project:

The EduVision application is designed to assist educational institutions, teachers, and students
by providing a digital solution to manage academic performance and predict student scores based
on various factors. The scope of this project includes:

1. User Roles and Access Control:

o Separate login/signup system for Admin and Students.

o Admin can manage users, view statistics, and handle system-wide operations.

o Students can input their academic data and view predictions.

2. Data Management:

o Secure storage and retrieval of student data using a MySQL database.

o Functions to add, update, view, and delete student records through an intuitive
interface.
3. Score Prediction:

o Use of machine learning (Linear Regression via scikit-learn) to forecast academic

performance based on factors like study hours, attendance, etc.

4. Interactive Dashboard:

o A clean, responsive dashboard using Tkinter and ttkbootstrap for better UX.

o Centralized access to features like data entry, prediction, graph visualization, and
data export.
5. Visualization and Reporting:

o Real-time graphical representation of student scores and performance trends.

o Export of data to Excel/CSV for offline access or reporting.

6. Security:

o Passwords are securely hashed using bcrypt.

o User-specific access ensures data privacy and security.

4
 4. Methodology:

The development of the EduVision: Student Score Predictor application followed a modular,
user-centric, and iterative software development methodology, combining aspects of Software
Development Life Cycle (SDLC) and machine learning practices.

1. Requirement Analysis

• Identified the need to help students and educators analyze academic performance.

• Gathered functional requirements:

o User authentication (Login/Signup)

o Data entry for student scores

o Score prediction based on input factors

o Admin-level user and usage management

2. System Design

• Designed the system using a modular architecture:

o Frontend with Tkinter and TTKBootstrap for modern GUI

o Backend with MySQL for persistent data storage

o Integration with sklearn for score prediction using Linear Regression

• Decided on key entities like Users and Student Scores with normalized relational
database schema.

3. Technology Stack
• Frontend: Python with Tkinter and TTKBootstrap for GUI

• Backend: MySQL (via mysql-connector and sqlalchemy)

• Data Processing & ML: Pandas, Scikit-learn (Linear Regression)

• Visualization: Matplotlib for plotting actual vs predicted scores

4. Implementation

• Authentication System:

o Users register and login with roles (user, admin)

5
 • Dashboard Navigation:

o Frames switch dynamically based on user role

• Student Data Entry:

o Input fields for subject, score, attendance, and study hours

o Data stored in MySQL

• Prediction Module:

o Fetch user-specific data

o Train Linear Regression model on past entries

o Accept input and predict score based on attendance and study hours

• Visualization:

o Bar chart comparing predicted vs actual scores

• Admin Panel:
o View/delete users

o View usage statistics (total users, records, active users)

5. Deployment and Usage

• Desktop application runnable via Python interpreter

• MySQL must be installed and configured locally

6
 5.1 User Interface Design
The user interface (UI) of EduVision is developed using Tkinter, enhanced with the
ttkbootstrap library to provide a modern, clean, and consistent appearance. The UI is
designed to be intuitive, making it easy for users to navigate and interact with the
application features.

Key components of the interface include:

• Login and Signup Screens: Simple, secure forms with password input, user type
selection (admin or user), and error handling. These ensure secure access and user
authentication.

• Dashboard: A central hub displayed after login, providing clearly labeled buttons for key
functionalities such as data entry, prediction, viewing records, visualization, and admin
tools (for admins).

• Data Entry Form: A structured form for entering student information including subject
marks, attendance percentage, and study hours. Input fields are validated to avoid
incorrect data entry.

• Prediction View: After submitting student data, the system uses a machine learning
model to predict the score. The result is shown within the same window, along with a
short summary.
• Student Records Page: Displays all entered records in a neatly formatted table using
ttk.Treeview. Includes options to edit, delete, or export data to Excel/CSV.
• Graph Visualization: Score distributions and trends are shown through embedded charts
using matplotlib, providing visual insight into student performance.

• Admin Panel: Accessible only by admin users, this section allows viewing registered
users, deleting accounts, and seeing system statistics like total predictions and user count.

The UI maintains responsive layout design, uses large readable fonts, placeholder text
with focus behavior, and color themes to improve usability. Each window is managed to
prevent overlap, ensuring only one active page at a time.

7
 6. Hardware and Software Requirements:

The development and deployment of the EDUVISION application require certain hardware and
software configurations to ensure smooth operation, efficient processing, and optimal user
experience. These requirements have been carefully selected to balance performance with
accessibility for typical users.

Hardware Requirements:
• The EduVision system requires a computer with at least an Intel Core i3 processor or an
equivalent.

• A minimum of 4 GB RAM is necessary for the application to run smoothly, while 8 GB

or more is recommended for better performance.

• The system should have at least 500 MB of free hard disk space for storing the
application and its data.

• A monitor with a resolution of 1024×768 pixels or higher is required to properly display

the graphical user interface.

• Standard input devices such as a keyboard and mouse are needed to interact with the
application.

• A network interface is required for database connectivity or remote access, if applicable.

Software Requirements:
• The system should run on a modern operating system like Windows 10 or 11, macOS, or
Linux.

• Python version 3.10 or higher is required for running the application.

• Python libraries used include Tkinter and ttkbootstrap for the GUI, pandas and scikit-
learn for data handling and machine learning, matplotlib for visualization, and bcrypt for
password security.

• MySQL Server (version 8.0 or above is recommended) is used for the database
management system.

• Development tools like an IDE (Visual Studio Code, PyCharm) and Python’s package
manager (pip) are needed for installation and management of dependencies.

• Database management tools such as MySQL Workbench or phpMyAdmin help manage

and interact with the database.

8
 7. Tools and Technologies Used:

The EduVision application is developed using a combination of technologies that support

efficient user interaction, data management, prediction, and visualization:

• Python: The core programming language used for application logic, data handling, and
machine learning integration.

• Tkinter: Python’s standard GUI library, used for creating the application interface. It
provides the windowing structure and basic widgets.

• ttkbootstrap: A modern theming library built on top of ttk, used to enhance the
appearance of the UI with a professional, responsive look and built-in color themes.
• MySQL: A relational database used to store user credentials and student records securely.
It allows for efficient querying, insertion, and deletion of data.

• bcrypt: A password-hashing library used to securely store and verify user passwords,
ensuring secure authentication.

• pandas: A powerful data analysis library used for handling student data, cleaning,
transformation, and exporting to Excel or CSV formats.

• scikit-learn: A machine learning library used to train and apply models for predicting
student scores based on input parameters such as study hours, attendance, and subject
marks.

• matplotlib: A visualization library used to display graphs and charts within the
application, such as score distributions and performance trends.

• ttk.Treeview: A widget from the ttk module used for displaying tabular data like student
records in a scrollable and editable format.

These tools together create a robust, scalable, and user-friendly desktop application that supports
both functional requirements and future extensibility.

9
 8. Results and Performance:

The EduVision application successfully meets its core objectives by providing a reliable and
user-friendly platform for predicting student scores and managing academic records. Key results
and performance highlights include:

• Accurate Predictions: The machine learning model integrated using scikit-learn delivers
accurate predictions for student scores based on input features like study hours,
attendance, and marks in key subjects.
• User Management: Secure login and signup functionalities with bcrypt password
hashing ensure only authorized access to the system.

• Efficient Data Handling: With the help of MySQL and pandas, the application
efficiently stores, retrieves, and manages large sets of student records without significant
lag or performance issues.

• Responsive UI: The GUI, built using Tkinter and styled with ttkbootstrap, offers a clean
and intuitive interface, making navigation smooth and user-friendly.

• Visual Feedback: Graphs and charts generated using matplotlib allow users to
understand data trends, score distributions, and performance patterns visually.

• Stable Performance: The application runs smoothly on standard desktop environments

with minimal resource usage, showing no major crashes or delays during extended usage.

These results indicate that EduVision performs well in both usability and technical functionality,
making it a valuable tool for educational prediction and student record management.

10
 9. Advantages:

• Accurate Score Prediction:

EduVision uses machine learning models to predict student scores based on key academic inputs,
helping educators and students anticipate performance.

• User-Friendly Interface:
The application features a clean and intuitive GUI built with Tkinter and ttkbootstrap, making it
easy for users to navigate without technical knowledge.

• Secure User Management:

Passwords are securely hashed using bcrypt, ensuring safe login and signup functionalities for
all users.

• Data Visualization:
Integration with matplotlib allows users to view performance trends and score distributions
through clear and informative charts.

• Efficient Record Management:

Students’ data can be added, viewed, edited, or deleted easily, with MySQL providing fast and
reliable database operations.

• Portability and Lightweight:

EduVision is a desktop-based application that can run on most Windows/Linux systems without
requiring high system resources.

• Educational Insight:
Teachers and administrators can use the app to identify students needing academic attention,
supporting early interventions.

10. Limitations:

• Limited Dataset Size:

Prediction accuracy may decrease with small or unbalanced datasets.

• Static Model:
The machine learning model does not automatically update with new data.

• Single-User Environment:
The application is designed for local use only and does not support multiple users or online
access.

• Basic Error Handling:

Limited input validation may lead to unexpected crashes or incorrect data entries.

11
 11. Future Enhancements:

• Model Enhancement: Advanced machine learning algorithms (like neural networks or

ensemble methods) can be integrated for more accurate predictions.

• Mobile App Integration: A mobile version can be developed to provide educators and
students access on the go.

• Cloud Deployment: Hosting the app and database on the cloud will enhance accessibility,
scalability, and data backup.

• Role-Based Access Control: Future versions can support different user roles like teachers,
students, and parents with tailored access.

• Automated Report Generation: Auto-generated PDFs of student performance and prediction

results can be added.

• More Data Parameters: Including more academic and behavioral parameters can further
improve prediction accuracy.

• AI Feedback System: Implementing a recommendation engine to guide students on how to

improve based on their predicted performance.

12
 12. Conclusion:

The EduVision project successfully demonstrates the integration of user-friendly software design
with predictive analytics to enhance student performance evaluation. By combining a robust
backend database, a clean and intuitive Tkinter-based graphical interface, and a straightforward
linear regression model, the application provides students and educators with an accessible
platform for entering academic data, predicting future scores, and managing student records
efficiently.

This project highlights the practical utility of machine learning in educational contexts by using
historical student data to forecast performance based on key factors such as attendance and study
hours. The results offer valuable insights for both students and educators to identify areas
requiring improvement and to tailor study plans accordingly.
Through its modular design, EduVision supports different user roles, including regular users and
administrators, facilitating better management and oversight of user accounts and data. The
application also incorporates essential features such as data export, record deletion, and visual
comparison of predicted versus actual scores, enhancing usability and engagement.

While the project has certain limitations, such as reliance on linear models and local-only
deployment, it sets a strong foundation for future enhancements. These could include more
sophisticated prediction models, real-time data updates, and multi-user, cloud-based
functionality.

Overall, EduVision represents an effective blend of software engineering, database management,

and data science techniques to support academic success. It serves as a practical example of how
technology can empower students and educators through data-driven decision-making, making
learning more targeted and impactful.

13
 13. References:

• Python Programming Language

https://www.python.org
– Official website for Python documentation, tutorials, and updates.

• Tkinter GUI Toolkit

https://docs.python.org/3/library/tkinter.html
– Official documentation for Tkinter, the standard GUI library for Python.

• MySQL Database
https://www.mysql.com
– Official site for MySQL with guides, downloads, and documentation.

• Scikit-learn (Machine Learning Library)

https://scikit-learn.org
– Official documentation and resources for Scikit-learn.

• Pandas Library
https://pandas.pydata.org
– Official site for pandas, used for data manipulation and analysis.

• Matplotlib Visualization Library

https://matplotlib.org
– Official site for matplotlib, used for plotting and visualization in Python.

• bcrypt for Python (Password Hashing)

https://pypi.org/project/bcrypt/
– Python Package Index (PyPI) entry for bcrypt, a secure password hashing library.

14