A data analytics schema for activity recognition in smart home environments

Recent advancements in the fields of embedded systems, communication technologies and computer science open up to new application scenarios in the home environment. Anyway, many issues raised from the inherent complexity of this new application domain need to be properly tackled. This paper proposes the Cloud-assisted Agent-based Smart home Environment (CASE) architecture for activity recognition with sensors capturing the data related to activities being performed by humans and objects in the environment. Moreover, the potential of analytics methods for discovering activity recognition in such environment has been investigated. CASE easily allows to implement Smart Home applications exploiting a distributed multi-agent system and the cloud technology. The work is mainly focused on activity recognition albeit CASE architecture permits an easy integration of other kinds of smart home applications such as home automation and energy optimization. The CASE effectiveness is shown through the design of a case study consisting of a daily activity recognition of an elder person in its home environment.