An approach to improve semantics in Smart Spaces using reactive fuzzy rules

Human behaviour representation and modelling in Smart Spaces are crucial tasks in Ambient Intelligence environments. A problem found among existing technologies is that the environment sensor data is always provided as crisp events. However, to model behaviour in reactive Smart Spaces we need to identify user patterns, which are not always performed in the same way or happening at the same time/frequency. Hence, the handling of imprecision is essential to model human behaviour in a realistic way. In order to connect these two paradigms, we suggest a combined architecture to fill the gap between quantitative Smart Space architectures (which provide raw crisp events) and qualitative aspects such as fuzzy reasoning and learning algorithms, that extract intelligence from data. With this aim, we propose to use Semantic Web principles of independence and interoperability to build an integrated framework to take advantage of the benefits of both crisp and fuzzy models. Our contribution in this work is a proof of concept to demonstrate how a hybrid architecture, with a reactive rule-based subscription mechanism, can empower users to model everyday activities semantically or control what happens on their surroundings, among other advantages.