Mental Stress Detection Using Physiological Signals Based on Soft Computing Techniques

This paper presents a novel approach for mentalstress detection. In proposed system, three signals includingPupil Diameter (PD), Electrocardiogram (ECG) andPhotoplethysmogram (PPG) are analyzed using the softcomputing techniques, and most relevant features are extractedfrom each one. Then, the optimized features are selected byusing the Genetic Algorithm (GA) and imported into the FuzzySVM (FSVM) to classify stress” and relaxation” states. Inorder to evaluate the performance of proposed system, amultimodal dataset consisting of pupil video, ECG and PPGsignals are constructed; a Stroop color-word (SCW) test isdesigned to act as the stimulus to induce stress in healthysubjects. The experimental results demonstrate thephysiological signals have great potential for stress detection,and the proposed system provides high classificationperformance.