Semantic place recognition for context aware services

Abstract

Extracting the meaning of the most significant places, which are frequently visited by a mobile user, is a relevant problem in mobile computing. Predicting semantic meaning of such places is useful in many areas. The problem of place semantic annotation of a user location can be challenging for service providers. Awareness of user activities is very important for development of personalized applications, which can be used in health care systems, living systems, etc. Predicting location of mobile users not only enables development of high quality location-based services and applications, but also improves resource reservation in wireless networks. In this research several solutions for semantic place prediction from mobile phone data are suggested and analyzed. Presented approaches have been tested on a real dataset collected during long period of time involving more than a hundred of participants.