Abstract
This paper presents a method to predict occupants' individual thermal comfort based on indoor and outdoor environmental information using a sensor network. A part of values are chosen from the network and are associated with the value which needs to be predicted. We utilize neural network to associate the values for predicting a human's thermal comfort. In this paper, we use accelerometer and GPS data to determine occupant's activity, while at the same time using a number of temperature and humidity sensors to measure environmental parameters. The experimental results shows that unspecified sensors are chosen properly and used for predicting the desired value.
