Mental Workload Assessment using Low-Channel Prefrontal EEG Signals

Objective: Monitoring stress using physiological signals has recently achieved a lot of attention since it has a significant adverse influence on an individual daily’s health and efficiency. As it has been proven that stress and mental workload are proportionally correlated, several studies have proposed algorithms for stress monitoring by increasing the mental workload. Despite the promising results reported in the literature, a majority of the proposed algorithms require the employment of several physiological signals which hinder their real-life application. Nonetheless, the advent of low-cost wearable devices has provided a new possibility for outdoor stress monitoring. The objective of this paper is to present an algorithm for stress detection using low-channel prefrontal electroencephalography (EEG) data. Methods: Firstly, artifacts in EEG signals are removed. Secondly, EEG signals are split into sub-bands using the discrete wavelet transform and two nonlinear parameter-free features are extracted. Thirdly, the extracted features are fed to three classifiers, i.e., support vector machine, Adaboost, and the K-Nearest Neighbours to discriminate stress from relaxed states. Main results: According to the obtained results, the highest accuracy (80.24%) was achieved using the AdaBoost classifier. Significance:Given that the proposed method does not require any parameter adjustment before processing, it has the potential to be used in real-world scenarios.