PREDICTION OF AUTOMOBILE PASSENGERS SKIN TEMPERATURE USING A NEURAL-NETWORK

The purpose of our study is to develop a method for estimating the fac ial skin temperature of an automobile passenger. The facial skin tempe rature is a good index for evaluating the environment. For the estimat ion of skin temperature, the rate of change in facial skin temperature was predicted from environmental data using a neural network. Then th e facial skin temperature was estimated from the late of change in fac ial skin temperature and the initial facial skin temperature calculate d from the environmental data. Furthermore, the level of thermal sensa tion was estimated from the predicted facial skin temperature. BS' use of a neural network, the rate of change in facial skin temperature co uld be predicted from the environmental data easily and accurately, an d the facial skin temperature could be predicted within +/-0.6 degrees C error. This is better than the method in which heat balance equatio ns for the body are used. The thermal sensation could be estimated wit hin +/-0.8 error on the scale used.