ML-Based Connitive Load Detection

Inspiration

In today’s fast-paced digital world, students and professionals often face mental fatigue and cognitive overload without realizing it. While working on laptops for long hours, we tend to ignore signs of stress, reduced focus, and burnout.

This inspired us to build a system that can analyze human behavior in real-time and detect cognitive load using simple interactions like typing patterns and mouse movements.

What it does

Our project is a Real-Time Cognitive Load Detection System that monitors user behavior and predicts whether the user is under stress or in a normal state.

The system:

Tracks typing speed
Measures time taken for tasks
Analyzes mouse movement patterns
Uses a Machine Learning model to predict cognitive load

How we built it

We built the project in multiple stages:

Data Collection
- Collected typing speed and time-based data
- Prepared dataset for training
Machine Learning Model
- Used a classification algorithm (Random Forest)
- Trained model to predict cognitive load
Behavior Tracking
- Used pynput to track keyboard and mouse activity
- Calculated typing speed and movement dynamically
User Interface
- Built an interactive dashboard using Streamlit
- Added real-time feedback and results

Challenges we faced

Integrating real-time tracking with ML prediction
Handling continuous data updates in Streamlit
Feature mismatch between training data and live system
Managing performance and avoiding lag

What we learned

Real-time systems require synchronization between UI and backend
Feature consistency is critical in Machine Learning
Streamlit is powerful for rapid prototyping
Debugging is a key part of building real-world projects

Future Scope

Add eye blink detection using computer vision
Improve model accuracy with more features
Generate detailed performance reports
Deploy as a web application for students and professionals

Conclusion

This project demonstrates how simple behavioral data can be used to detect cognitive load and improve productivity. It has the potential to help users manage stress and maintain better focus in their daily tasks.