Development of the data-driven thermal satisfaction prediction model as a function of human physiological responses in a built environment

Abstract

The purpose of this study is to investigate and determine the relationship between occupants’ thermal satisfaction and physiological responses in an office environment, and to estimate their thermal satisfaction level via human physiological signals. This study adapted the heart rate and seven local body skin temperatures as physiological signals, as well as human factors (gender, age, BMI), to determine establish a thermal satisfaction prediction model by combining human factors and physiological signals. The results revealed significant correlations between overall thermal satisfaction levels and local body skin temperatures, as well as heart rates. The heart rates showed a negative correlation with overall thermal satisfaction, and the skin temperature of the forehead, arm, wrist (back and front), chest, and belly also revealed a significant correlation with the thermal satisfaction levels of the study participants. This study also determined the order and priority of local skin temperatures (as well as gender and BMI) by their impact on thermal satisfaction. Considering all human physiological factors and practical application of the results, the local skin temperatures of the forehead, wrist (back), and gender demonstrated 88.52% accuracy for estimating thermal satisfaction, which provided significant validation for practical use of this procedure.