Skip to Main Content
Context aware computing relies on sensing environmental parameters-context (e.g., illumination, location), classifying context, and inferring further knowledge about context, i.e., the user's situation. Therefore, the relevant applications cannot handle context as flexibly as their users would expect. To overcome this deficiency, we propose an extension of context representation, classification, and inference. Our model relies on fuzzy set theory to accommodate the imperfect nature of sensed context. We develop two fuzzy inference engines dealing with context specialization and compatibility relations. We evaluate such engines through a series of experiments involving real users. Our findings indicate the efficiency of the proposed context classification and inference processes.