EEG dataset of drug addicts

This study is designed to assess stress reduction outcomes using Electroencephalographic (EEG) signals as biomarkers in drug addicts undergoing Cognitive Behavioral Therapy (CBT). Approach-EEG signals were collected from a sample of 360 drug addicts before and after CBT. Seven feature extraction techniques, both in frequency and temporal domains, were applied to the EEG data to extract stress-related biomarkers. A variety of conventional classifiers, including quadratic and linear Support Vector Machine (SVM), decision tree (DT) and logistic regression models were evaluated using performance metrics including accuracy, precision, sensitivity, specificity, and F1 score. To address class imbalance and enhance classification accuracy, an advanced predictive model based on random under-sampling boosting decision trees (RUSBoosted Trees) was also implemented