From activity recognition to situation recognition

Abstract

Activity recognition is important to many critical human-centric applications. Despite success in activity recognition research, there seems to be a quest for a richer sentience that is more expressive than human activity. In particular, situation has received intense attention lately with a multitude of overlapping definitions motivated by a variety of different goals. With the goal of assessing user behavior response (compliance) in persuasive systems, we propose a specific definition of situation along with a framework for designing situation recognition algorithms. © 2013 Springer-Verlag Berlin Heidelberg.