Detecting activities of daily living using the CONSERT engine

Abstract

Context-awareness is central to many applications in Ambient Intelligence. The paper presents the functionality of a context reasoning engine, called CONSERT, for developing ambient intelligence applications, which builds on semantic complex event processing. The implementation of core rule processing using the DROOLS Fusion framework and the advantages gained through this approach are discussed. The resulting engine capabilities are presented for the case of recognizing activities of daily living (ADL) contained in the CASAS dataset, together with an evaluation of the obtained results.