Integral framework for acquiring and evolving situations in smart environments

Article type: Research Article

Authors: Brdiczka, Oliver

Affiliations: Computer Science Lab (CSL), Palo Alto Research Center (PARC), 3333 Coyote Hill Road, Palo Alto, CA, USA E-mail: [email protected]

Abstract: Smart environments enhance user capabilities and comfort by providing new services and automated service execution based on sensed user activity. Though, when becoming really “smart”, such environments should not only provide some service automation, but further learn and adapt their behavior during use. This article motivates and investigates learning of situation models in a smart environment, covering knowledge acquisition from observation as well as evolving situation models during use. An integral framework for acquiring and evolving different layers of a situation model is detailed. Different learning methods are presented as part of this framework: role detection per entity, unsupervised extraction of situations from multimodal data, supervised learning of situation representations, and the evolution of a predefined situation model with feedback. The situation model serves as frame and support for the different methods, permitting to stay in an intuitive declarative framework. An implementation of the whole framework for a smart home environment is described, and the results of several evaluations are depicted.

Keywords: Context awareness, situation learning framework, situation split, user preference integration, hidden Markov models

DOI: 10.3233/AIS-2010-0063

Journal: Journal of Ambient Intelligence and Smart Environments, vol. 2, no. 2, pp. 91-108, 2010