A Knowledge-Driven Approach to Composite Activity Recognition in Smart Environments

Knowledge-driven activity recognition has recently attracted increasing attention but mainly focused on simple activities. This paper extends previous work to introduce a knowledge-driven approach to recognition of composite activities such as interleaved and concurrent activities. The approach combines ontological and temporal knowledge modelling formalisms for composite activity modelling. It exploits ontological reasoning for simple activity recognition and rule-based temporal inference to support composite activity recognition. The presented approach has been implemented in a prototype system and evaluated in a number of experiments. The initial experimental results have shown that average recognition accuracy for simple and composite activities is 100% and 88.26%, respectively.

[1]  Ian Horrocks,et al.  OWL rules: A proposal and prototype implementation , 2005, J. Web Semant..

[2]  James F. Allen.  Maintaining knowledge about temporal intervals , 1983, CACM.

[3]  Boris Motik,et al.  OWL 2: The next step for OWL , 2008, J. Web Semant..

[4]  Jian Lu,et al.  A Pattern Mining Approach to Sensor-Based Human Activity Recognition , 2011, IEEE Transactions on Knowledge and Data Engineering.

[5]  Henry A. Kautz,et al.  Improving the recognition of interleaved activities , 2008, UbiComp.

[6]  Liming Chen,et al.  A Hybrid Ontological and Temporal Approach for Composite Activity Modelling , 2012, 2012 IEEE 11th International Conference on Trust, Security and Privacy in Computing and Communications.

[7]  Chris D. Nugent,et al.  Using Event Calculus for Behaviour Reasoning and Assistance in a Smart Home , 2008, ICOST.

[8]  Arkady B. Zaslavsky,et al.  Recognizing Concurrent and Interleaved Activities in Social Interactions , 2011, 2011 IEEE Ninth International Conference on Dependable, Autonomic and Secure Computing.

[9]  Chris D. Nugent,et al.  Ontology-based activity recognition in intelligent pervasive environments , 2009, Int. J. Web Inf. Syst..

[10]  Hans W. Guesgen,et al.  Utilising Temporal Information in Behaviour Recognition , 2010, AAAI Spring Symposium: It's All in the Timing.

[11]  Henry A. Kautz,et al.  Fine-grained activity recognition by aggregating abstract object usage , 2005, Ninth IEEE International Symposium on Wearable Computers (ISWC'05).

[12]  Richard Fikes,et al.  A Reusable Ontology for Fluents in OWL , 2006, FOIS.

[13]  Heiner Stuckenschmidt,et al.  Recognizing interleaved and concurrent activities using qualitative and quantitative temporal relationships , 2011, Pervasive Mob. Comput..

[14]  Martin Becker,et al.  Rule-based activity recognition framework: Challenges, technique and learning , 2009, 2009 3rd International Conference on Pervasive Computing Technologies for Healthcare.

[15]  Chris D. Nugent,et al.  A Knowledge-Driven Approach to Activity Recognition in Smart Homes , 2012, IEEE Transactions on Knowledge and Data Engineering.