Predicting collective user preference for optimal comfort level in smart buildings

The idea of smart building has become closer to reality due to the recent advances in ubiquitous computing technologies. However, it still remains an open question how a computational system can optimize user comfort levels in buildings, which is crucial because it affects the quality of life and work of all occupants. Since multiple users share building spaces and they have hierarchical relationship to each other, it is not ideal to decide controllable comfort parameters based on a single users' preferences, and so collective users' preferences have to be considered. In this paper, we propose an algorithm to predict users' preferences based on the organizational hierarchy of the occupants, which can be used as a decision mechanism in smart building environments. To evaluate the proposed algorithm, we conducted experiment in real smart building environment, and recorded the number of manual interventions to control device settings before and after the deployment of the proposed algorithm. Our algorithm could successfully decrease the number of manual interventions by 64.2%.