Inferring Multiple Activities of Mobile Users with Activity Algebra

This paper proposes a novel multiple activity recognition and reasoning approach where we use on-body sensor information along with other context information to infer mobile user activities which are both concurrent and interleaved. We develop and validate an activity algebra and a complex activity recognition algorithm for detecting these multiple activities. Activities are mapped onto situations using spatio-temporal analysis. We validate our approach by implementing a prototype and performing experiments in different scenarios using mobile devices.