Convolutional Neural Network and Kernel Methods for Occupant Thermal State Detection using Wearable Technology

Tanaya Chaudhuri, Deqing Zhai, Yeng Chai Soh, Hua Li, Lihua Xie, Xianhua Ou

Abstract: Occupant's thermal comfort detection is a significant contributor to building energy efficiency. However, the predictions from the traditional PMV (Predicted Mean Vote) method often deviate from the actual thermal sensation of occupants. This paper proposes two new approaches for TS (thermal state: Discomfort/Comfort) detection, based on personal physiological features extracted using wearable technology. The first approach, CNN-(T sk ) TP , is based on a deep convolutional neural network (CNN) that associates TS with images of hand skin temperature temporal profile (TP). CNN has shown great success in the classification of captured images, however, its application to 2-D sensor data is rather less explored. In this study, the hand skin temperature was observed to show distinct temporal patterns under different TS. Leveraging this high responsiveness of skin temperature, the two-dimensional sensor data was transferred to image domain. A 4-step domain transfer process was adopted to obtain 5-minute TP for the CNN. The second approach, SVM phy is based on a Support Vector Machine (SVM) model with 6 distinct physiological input features. SVM-RBF performed better among four kernel types evaluated (linear, polynomial, radial, sigmoid). Our proposed approaches CNN-(T sk ) TP and SVM phy achieved 93.33% and 90.6% accuracy, outperforming the existing methods (PMV, ePMV, aPMV and PTS models). Additionally, practical advantages of our approaches are discussed.