A Unified Context Model: Bringing Probabilistic Models to Context Ontology

Ontology is a promising tool to model and reason about context information in pervasive computing environment. However, ontology does not support representation and reasoning about uncertainty. Besides, the underlying rule-based reasoning mechanism of current context-aware systems obviously can not reason about ambiguity and vagueness in context information. In this paper, we present an ongoing research on context modeling which follows the ontology-based approach while supports representation and reasoning about uncertain context. This unified context model then is used as a framework in our implementation of the context management and reasoning module of our context-aware middleware for ubiquitous systems.