Non-invasive EEG-metric based stress detection

Abstract

Psychological stress is a vital parameter related to individual's health and cognitive performance which may affect emotions and professional efficiency. Regula stress profile generated can be used as neurofeedback for the clinical as personal assessment. This paper describes a method to detect mental stress level based on physiological parameters. In this method an electroencephalogram (EEG) parameter based binary stress classifier is developed which is validated through probabilistic stress profiler of differential stress inventory questionnaire. A non-invasive 9 channel EEG is used to extract physiological signal and an EEG-metric based cognitive state and workload outputs is generated for 41 healthy volunteers (37 males and 4 females, age; 24±5 years). All subjects were performed three simple tasks of closed eye, focusing vision on a red dot on center of dark screen and focusing on a white screen. Central tendencies (mean, median and mode) are extracted from of EEG-metric (sleep onset, distraction, low engagement, high engagement and cognitive states) as features. Either of the two classes as low stress or high stress are evaluated from probabilistic stress profiler of differential stress inventory and used as training output classes. A supervisory training of multiple layer perceptron based binary support vector machine classifier was used to detect stress class one by one. 40 subject's samples were used for training and interchanging one-by one 41th subject's stress class is determined from the designed classifier. Out of 41 subjects, stress level of 30 subjects is correctly identified.