Prediction of Individual Dynamic Thermal Sensation in Subway Commute Using Smart Face Mask.

Wearable sensors and machine learning algorithms are widely used for predicting an individual's thermal sensation. However, most of the studies are limited to controlled laboratory experiments with inconvenient wearable sensors without considering the dynamic behavior of ambient conditions. In this study, we focused on predicting individual dynamic thermal sensation based on physiological and psychological data. We designed a smart face mask that can measure skin temperature (SKT) and exhaled breath temperature (EBT) and is powered by a rechargeable battery. Real-time human experiments were performed in a subway cabin with twenty male students under natural conditions. The data were collected using a smartphone application, and we created features using the wavelet decomposition technique. The bagged tree algorithm was selected to train the individual model, which showed an overall accuracy and f-1 score of 98.14% and 96.33%, respectively. An individual's thermal sensation was significantly correlated with SKT, EBT, and associated features.

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

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.