Prediction of individual thermal sensation from exhaled breath temperature using a smart face mask

Abstract

This study developed a thermal-sensation prediction model for individuals by incorporating sensors into a face mask. Conventional prediction of thermal sensation relies on population models, which do not satisfy the requirements of modeling an individual. Developing a model for individuals opens the door to control personalized microclimates. The COVID-19 pandemic has normalized the wearing of face masks; however, their comfort is variable and subjective. We embedded wearable sensors into a face mask to monitor heart rate, skin temperature, and exhalation temperature, determining factors in thermal sensation. Skin temperature, through its thermoregulatory mechanism, plays a vital role in regulating body temperature. As heart rate and exhalation temperature change with metabolic activity, they can predict these temperature changes. During our experiments, we collected physiological and psychological data from human participants at various room temperatures. From this, we found skin temperature and exhalation temperature to show a significant (p < 0.05) positive correlation with perceived thermal sensation. We also developed a random forest classification model for each participant to assess the accuracy of our modeling. We found that smart face masks present a nonintrusive method of measuring physiological data relevant to developing individualized thermal-sensation prediction models, which can be used to improve comfort in indoor environments. The mask we developed could also be adapted further to measure respiration rate, monitor activity, and record other physiological data.