A thermal comfort evaluation model based on facial skin temperature

Abstract

This study realized a Fisher discriminant analysis method for thermal comfort evaluation based on facial skin temperature. These models directly determine whether an individual is in a neutral state through neutral facial skin temperature thresholds and have physiological significance. The implementation of the models was based on climate-controlled experimental data. The air temperatures considered included 12, 15, 18, 21, and 24 °C (winter) and 24, 26, 28, 30, and 32 °C (summer). During the experiments, the thermal sensation votes of 40 participants were documented using subjective questionnaires, and facial skin temperatures were continuously measured using high-precision corrected iButtons. The results show that the highest precision of the evaluation model was 80%, and the corresponding false-negative rate (FNR) was 27%. The neutral facial skin temperature ranges were higher during summer than during winter. After 15 min of exposure, the models exhibited higher reliability. The average skin temperature from multiple facial parts was more suitable for evaluating neutral thermal sensations than that from a single facial part. The average skin temperature of the nose, cheeks, and chin is the most appropriate index for future applications of infrared thermal imaging. To a certain extent, the models were further improved by sex. Considering air-conditioning energy conservation, this study provides expanded evaluation models. The recommended average skin temperature exhibited a higher evaluation performance: the highest precision was 86%, and the FNR was 19%. These results provide a theoretical basis for the future use of the facial skin temperature as a feedback signal for air conditioners.