Introduction:

Cognitive Workload Estimator is a groundbreaking project at the intersection of psychology and technology, leveraging Python and machine learning to estimate cognitive workload. This innovative application holds immense potential for optimizing human-computer interaction and enhancing user experience.

Problem Statement:

In an era of constant digital engagement, and alarming threat of mental problems, understanding the cognitive workload imposed on users is crucial. This Project aims to quantify mental effort during various tasks, providing valuable insights for designing user interfaces and experiences.

Solution:

Built on a foundation of Python, the project employs advanced data analysis techniques, feature extraction methodologies, and machine learning algorithms to estimate cognitive workload. By processing physiological and behavioral data, the system discerns patterns indicative of varying cognitive loads and classify the cognitive workload as various levels.

Processing:

Visualization:

Theta/Alpha band power ratio:

Classification:

Key Achievements:

Preprocessed the raw EEG signal, removing any artifacts present in it.
Developed a robust feature extraction pipeline capable of capturing nuanced cognitive indicators.
Implemented a machine learning model achieving an accuracy of 88% in predicting cognitive workload levels.

Technical Skills Applied:

Python, Pandas, NumPy, Scikit-learn, Feature Extraction, Data Analysis, Machine Learning.

Cognitive Workload Estimation using EEG signals