Dependable, Autonomic and Secure Computing, IEEE International Symposium on (2011)
Sydney, New South Wales Australia
Dec. 12, 2011 to Dec. 14, 2011
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/DASC.2011.58
Social networks constitute an important research area where users are involved in social interactions and inform each other of activities they perform. In this paper a complex activity recognition system (SEMACT) is proposed, built and validated. Different activities performed by users form an activity hierarchy. We perform semantic reasoning by using ontological constructs and rules to recognize both concurrent and interleaved complex activities at different levels of granularity of this activity hierarchy. Different application domains require activity recognition systems to define and recognize activities at different levels of granularity. Our system tackles this problem by recognizing complex activities which are then shared across application domains using a generic API. A test-bed and prototype are built to validate our SEMACT system. Extensive experimentation is performed which demonstrates that high accuracy of 94.35% was achieved for the recognition of complex activities both concurrent and interleaved within computationally feasible time.
activity recognition, semantic reasoning, ontology, context-awareness, prototype, test-bed
Saguna, Arkady Zaslavsky, Dipanjan Chakraborty, "Recognizing Concurrent and Interleaved Activities in Social Interactions", Dependable, Autonomic and Secure Computing, IEEE International Symposium on, vol. 00, no. , pp. 230-237, 2011, doi:10.1109/DASC.2011.58