Stress Recognition Based on Multiphysiological Data in High-Pressure Driving VR Scene

Human stress recognition has been used in a variety of contexts, including stress caused by work pressures, mental pressures, trauma, and physical sickness. Meanwhile, the issue of battlefield-induced stress among army veterans has received less attention among researchers. Despite the fact that numerous programs are available to help army soldiers cope with stress, research on physiological behavior as a result of high-pressure combat impacts is still lacking. Since experiencing the same in real time is difficult, we created a virtual reality (VR) technology-based digital battlefield driving scenario and reproduce the stray bullet stimulations within the same in order to mimic the original battlefield environment. The VR scene is then combined with real-time physiological sensors, such as electrocardiography (ECG), Galvanic skin response (GSR) sensor, and an eye-tracking device to analyze the pressure circumstance resulting from the bullet stimulations. The proposed work analyzed the physiological signal individually and as a whole to determine whether the VR stimulation arouse stress in the subject or not. The statistical method and cutting-edge technology, such as the machine learning (ML) and deep learning (DL) models, were used in this work for the classification of the physiological data-induced stress condition. A comprehensive analysis was carried out among the significant features of the physiological signal and the raw signals as well. The observed results reveal that the VR battlefield can effectively arouse stress in humans, and the DL model can predict the stress condition with good accuracy.