Analysis of spatial distribution characteristics of facial skin temperature on stress coping

Abstract

Individuals exhibit two types of responses when exposed to external stimuli. These are called stress-coping responses, or active and passive coping responses, respectively. These stress-coping responses are discriminated by differences in the fluctuations of hemodynamic parameters, such as cardiac output (CO), total peripheral resistance (TPR), and mean blood pressure (MBP), and others. However, the existing method for measuring hemodynamic parameters is contact measurement, which involves wearing a continuous blood pressure cuff; thus, a remote measurement method is required. Therefore, we focused on facial thermal imaging, remotely measurable indicator of the cardiovascular system. We constructed a model to estimate stress-coping responses from the spatial characteristics of facial thermal images using a CNN and sparse coding. However, the standard spatial distribution of facial thermal images of stress-coping response states has not yet been examined. Therefore, in this study, we analyzed the standard spatial distribution of facial thermal images of stress-coping response states. To elicit each stress-coping response, a cold pressure task and a game task were performed. Facial thermal images and hemodynamic parameters were recorded during the experiments. The measured hemodynamic parameters confirmed the elicitation of a stress-coping response. Additionally, using the measured facial thermal images, we evaluated the deviation of the stress-coping response states from a person’s normal state and the standard spatial distribution of each stress-coping response. The results showed that the stress-coping response states deviated from a person’s normal state. In addition, the standard spatial distribution differed for each stress-coping response.