Detection of Points of Interest in a Smart Campus

Understanding users' habits is a critical task in order to develop advanced services, such as personalized recommendation and virtual assistance. In this work, we propose a novel approach to detect Points of Interest visited by users of a campus, by using mobility traces collected through users' smartphones. Our method takes advantage of the intentional and recurrent nature of human movements to build up mobility profiles, and combines different machine learning methods to merge sensory information with the past users' behavior. The proposed approach has been validated on a synthetic dataset and the experimental results show its effectiveness.