Towards a Robust Concurrent and Interleaved Activity Recognition of Mobile Users

Abstract

Abstract-This paper proposes a situation and context-aware complex activity recognition system 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 our complex activity recognition algorithm for detecting these multiple complex activities. Activities are mapped onto situations using spatio-temporal analysis. We further build a test-bed in the social-networking domain to test and validate our approach in different scenarios using mobile devices.

Building Activity Definitions to Recognize Complex Activities Using an Online Activity Toolkit

“…This may be when different users perform an activity or when the same user performs it multiple times. Users also tend to interleave between different activities or perform them concurrently [6]. In [5], [7], a context-driven activity theory (CDAT) is used to address the aforementioned challenges such as variation in sequence, concurrency and interleaving to recognize complex activities in home, office and outdoor environments.…”