Mental Stress Detection and Classification using SVM Classifier: A Pilot Study

Human stress brings changes in both physical and mental health which leads to chronic illness or injury, hypertension, cardiac arrest. It also causes emotional problems such as anxiety, depression, anger, grief, guilt, low self-esteem which affects normal healthy life. This paper presents the design, development and testing of a biomedical measurement system for detecting human mental stress using machine learning approach. This paper investigates the measure of heart rate variability from am ECG signal for detecting human stress by using Support Vector Machine (SVM) classifier technique and ultra-short term HRV analysis method. MITBIH multi-parameter database is also used in this paper to load ECG signals for extracting the time domain features for detection of human mental stress. The different experiments have been carried out with 60 segments of RR interval in both normal state and stress state condition by ultra-short term HRV analysis method. The implementation of SVM classifier with RBF kernel provides the accurate detection of mental stress level. The measurement result indicates that the proposed techniques achieve the mental stress classification accuracy of 91%. From the results, it was concluded that the proposed methodology provides a promising way to detect mental stress in an individual.