A Knowledge-Based Approach for Multiagent Collaboration in Smart Home: From Activity Recognition to Guidance Service

Smart home (SH) as an emerging paradigm for alleviating the overstretched healthcare resources, and enhancing the quality of life has received increasing attention. While the remarkable progress has been made for the development of SH, it still suffers from a number of issues (e.g., device heterogeneity, composite activities recognition, and providing appropriate services). To address these issues, this paper proposes a knowledge-based approach for multiagent (MA) collaboration. Specifically, a layered architecture of SH that combines ontology and MA technologies is designed to automatically acquire semantic knowledge, and support heterogeneity and interoperability services. In such architecture, a generic inference algorithm is presented based on unordered actions and temporal property of activity for inferring both continuous composite activity and personalized service in real time. Then a novel idea is introduced for agent to learn the knowledge of human activity (HA) autonomously and translate into itself knowledge, the purpose of which is to guide agent for performing services in a way that is compatible with HA. The proposed schemes have been implemented in an SH, and evaluated through extensive experiments. The results are provided to show the feasibility, effectiveness, and robustness of our proposal.