Activity and behaviour modelling are significant for activity recognition and personalizedassistance, respectively, in smart home based assisted living. Ontology-based activity andbehaviour modelling is able to leverage domain knowledge and heuristics to create Activities of Daily Living (ADL) and behaviour models with rich semantics. However, theysuffer from incompleteness, inflexibility, and lack of adaptation. In this article, we proposea novel approach for learning and evolving activity and behaviour models. The approachuses predefined “seed” ADL ontologies to identify activities from sensor activationstreams. Similarly, we provide predefined, but initially unpopulated behaviour ontologiesto aid behaviour recognition. First, we develop algorithms that analyze logs of activitydata to discover new activities as well as the conditions for evolving the seed ADL ontologies. Consequently, we provide an algorithm for learning and evolving behaviours (or life habits) from these logs. We illustrate our approach through scenarios. The first scenarioshows how ADL models can be evolved to accommodate new ADL activities and peculiarities of individual smart home’s inhabitants. The second scenario describes how, subsequent to ADL learning and evolution, behaviours can be learned and evolved.
|Title of host publication||Activity Recognition in Pervasive Intelligent Environments, Atlantis Ambient and Pervasive Intelligence|
|Editors||Liming Chen, CD Nugent, Jit Biswas, Jesse Hoey|
|Publication status||Published - Feb 2011|