An Active Classification System for Context Representation and Acquisition

Fulvio Mastrogiovanni, Antonio Sgorbissa, Renato Zaccaria

Abstract: This work deals with a distributed knowledge representation and active information fusion system suitable for use in Ambient Intelligence applications. The architecture – which is modeled as a multi-agent system – exploits a sound formal model to relate numerical data to symbolic representations, thus being able to reason about predicates, situations and contexts. In particular, agents collaborate to perform an intelligent multi-sensor data fusion according to the guidance of an active classification layer. Experimental results performed both in simulation and in a real set-up are discussed with respect to a number of implications and future directions related to the system approach.