A bayesian approach for dealing with uncertain contexts

Abstract

Building of context-aware applications in pervasive computing environments faces the difficult problem of dealing with uncertain context information. In this paper, we propose a probability extension to our ontology-based model for representing uncertain contexts; and use Bayesian networks to reason about uncertainty. In addition, the supports of probabilistic markups and Bayesian networks have been incorporated into our contextaware middleware system to enable the building of context-aware services by using various uncertain contexts. We also present our experiences and discussions.