Modelling hand skin temperature in relation to body composition.

Skin temperature is a challenging parameter to predict due to the complex interaction of physical and physiological variations. Previous studies concerning the correlation of regional physiological characteristics and body composition showed that obese people have higher hand skin temperature compared to the normal weight people. To predict hand skin temperature in a different environment, a two-node hand thermophysiological model was developed and validated with published experimental data. In addition, a sensitivity analysis was performed which showed that the variations in skin blood flow and blood temperature are most influential on hand skin temperature. The hand model was applied to simulate the hand skin temperature of the obese and normal weight subgroup in different ambient conditions. Higher skin blood flow and blood temperature were used in the simulation of obese people. The results showed a good agreement with experimental data from the literature, with the maximum difference of 0.31°C. If the difference between blood flow and blood temperature of obese and normal weight people was not taken into account, the hand skin temperature of obese people was predicted with an average deviation of 1.42°C. In conclusion, when modelling hand skin temperatures, it should be considered that regional skin temperature distribution differs in obese and normal weight people.

Machine learning algorithms applied to a prediction of personal overall thermal comfort using skin temperatures and occupants' heating behavior.

Thermal comfort modeling has been of interest in built environment research for decades. Mostly the modeling approaches focused on an average response of a large group of building occupants. Recently, the focus has been shifted towards personal comfort models that predict individuals' thermal comfort responses. Currently, thermal comfort responses are collected from the occupants via survey. This study explored if the thermal comfort of individuals could be predicted using machine learning algorithms while relaying on the set of collected inputs from an experiment. The model was developed using experimental data including collected from a previously performed experiment in the climate chamber. Two different approaches based on the output data (thermal sensation and thermal comfort votes) and five different sets of input variables were explored. The algorithms tested were Support Vector Machine with four different Kernel functions (Linear, Quadratic, Cubic and Gaussian) and Ensemble Algorithms (Boosted trees, Bagged trees and RUSBoosted trees). The combination of occupants' heating behavior with a personal comfort system (PCS), skin temperatures, time and environmental data were used for the development of personal comfort models to predict individuals' thermal preference. The study investigated the novel combination of inputs such as the use of skin temperature and settings of the personalized heating system as parameters in predicting personal thermal comfort. The results showed that personal comfort models among all tested approaches and subjects showed the best median accuracy of 0.84 using RUSBoosted trees. Individually looking, the approach using thermal sensation output produced better prediction accuracy. On the other hand, the models based on inputs that consisted of PCS control behavior and mean and hand skin temperatures produced the best prediction accuracy when assessing all tested algorithms. The main limitation of the study is the number of test subjects, and further recommendation is to perform more experiments.