Discrete Wavelet Transform based EEG Feature Extraction and Classification for Mental Stress using Machine Learning Classifiers

This paper aims to develop a discrete wavelet transform-based EEG feature extraction method for the classification of mental stress using machine learning classifiers. It has been evidence that EEG Oscillations can discriminate mental states, for instance, stressed and non-stressed. However, it is still not clear in which range of EEG oscillations the neural activities are associated with the mental states. Hence, in this analysis, wavelet-based EEG power analysis was performed on an EEG dataset of 22 participants, where the dataset has both stress and control conditions. The EEG alpha, theta, and beta frequency bands showed promising results for the classification of mental stress vs. control conditions by achieving an average accuracy of 95% using the decision tree. The results of the proposed method were superior to the Fast Fourier Transform in feature extraction. The proposed method has the potential to be used in Computer-Aided Diagnosis (CAD) systems for mental stress assessment in the future.