Poster: A Virtual Sensing Framework For Mobile Phones

ABSTRACTThis work presents a virtual sensing framework by exploiting operating system events for energy efficient context inference. Specifically, we present a novel set of features that can be extracted from virtual sensors and used to infer the logical status of mobile users, such as isWorking, isSocial, and isStressful. The preliminary results indicate promising inference performance and suggest a wide range of applications of the proposed framework.