| Description: |
This project introduces a practical and intelligent approach to stress detection using EEG signals andmachine learning. By capturing and analyzing brainwave activity, the system identifies five key frequencybands—delta, theta, alpha, beta, and gamma—through the use of a Butterworth bandpass filter. From thesebands, meaningful features are extracted to reflect the brain’s cognitive and emotional states. These featuresare then processed through a hybrid pipeline combining unsupervised clustering with supervised learningmodels, including Support Vector Machine (SVM), Random Forest (RF), and XGBoost, to classify stresslevels into Low, Moderate, and High. To bring this solution closer to real-world application, the trainedmodels are integrated into a user-friendly interface built with Streamlit, enabling real-time monitoring andpredictions. The result is a robust, automated system capable of supporting mental health assessments invarious settings—from clinical environments to personal wellness applications—offering both scalabilityand accessibility. |