A Brain-Computer Interface for classifying EEG correlates of chronic mental stress

In this paper, a Brain-Computer Interface (BCI) for classifying EEG correlates of chronic mental stress is proposed. Data from 8 EEG channels are collected from 26 healthy right-handed students during university examination period and after the examination whereby the former is considered to be relatively more stressful to students than the latter. The mental stress level are measured using the Perceived Stress Scale 14 (PSS-14) and categorized into stressed and stress-free groups. The proposed BCI is then used to classify the subjects´ mental stress level on EEG features extracted using the Higuchi´s fractal dimension of EEG, Gaussian mixtures of EEG spectrogram, and Magnitude Square Coherence Estimation (MSCE) between the EEG channels. Classification on the EEG features are then performed using the K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM). The performance of the proposed BCI is then evaluated from the inter-subject classification accuracy using leave-one-out validation. The results showed that the proposed BCI using features extracted by MSCE yielded a promising inter-subject validation accuracy of over 90% in classifying the EEG correlates of chronic mental stress.