Inefficient controlling strategies in heating and cooling systems have given rise to a large amount of energy waste and to widespread complaints about the thermal environment in buildings. An intelligentcontrol method based on a support vector machine (SVM) classifier is proposed in this paper. Skin temperatures are the only inputs to the model and have shown attractive prediction power in recognizingsteady state thermal demands. Data were accumulated from two studies to consider potential use for either individuals or a group of occupants. Using a single skin temperature correctly predicts 80% ofthermal demands. Using combined skin temperatures from different body segments can improve the model to over 90% accuracy. Results show that three skin locations contained enough information forclassification and more would cause the curse of dimensionality. Models using different skin temperatures were compared. Optimal parameters for each model were provided using grid search technique. Considering the overfitting possibility and the cases without learning processes, SVM classifiers with a linear kernel are preferred over Gaussian kernel ones.

Heating and cooling in buildings accounts for over 20% of total energy consumption in China. Therefore, it is essential to understand the thermal requirements of building occupants when establishing building energy codes that would save energy while maintaining occupants thermal comfort. This paper introduces the Chinese thermal comfort dataset, established by seven participating institutions under the leadership of Xian University of Architecture and Technology. The dataset comprises 41,977 sets of data collected from 49 cities across five climate zones in China over the past two decades. The raw data underwent careful quality control procedure, including systematic organization, to ensure its reliability. Each dataset contains environmental parameters, occupants subjective responses, building information, and personal information. The dataset has been instrumental in the development of indoor thermal environment evaluation standards and energy codes in China. It can also have broader applications, such as contributing to the international thermal comfort dataset, modeling thermal comfort and adaptive behaviors, investigating regional differences in indoor thermal conditions, and examining occupants thermal comfort responses.