Explainable Quantum EEG Analysis For Stress Detection

Stress detection from EEG signals has become an essential task in understanding mental health. This research focuses on integrating quantum computing with classical machine learning algorithms to enhance the detection of stress and non-stress states from EEG data. The dataset used for this project is sourced from Kaggle, specifically the EEG Features for Stress Classification dataset. The project employs multiple algorithms, including SVM, Random Forest, XGBoost, as well as Hybrid Quantum with XGBoost and Hybrid Quantum with SVM models, to achieve accurate classification. The aim is to enhance feature extraction using quantum computing, which is then followed by classification using traditional machine learning techniques.

The system comprises several modules, including Home, Register, Login, Prediction/Classification, and Logout, and is implemented using HTML, CSS, and JavaScript for the front-end, and Flask as the Python-based back-end framework. The project is designed to classify EEG data into stress and non-stress categories, aiming to contribute to the development of efficient, non-invasive stress detection systems.

Keywords: Stress Detection, EEG Signals, Quantum Computing, Machine Learning, SVM, Random Forest, XGBoost, Hybrid Quantum, Flask, Mental Health Monitoring.