Cognitive smart environment: an approach based on concept hierarchies and sensor data fusion

Sensor data fusion gathers technological solutions for collecting, classifying and combining data from multiple sensors in a smart environment for augmenting knowledge about the system and realising cognitive behaviours. The goal is to make effective the management of acquired data and to promote the realisation of cognitive systems which can sense the environment, reason, and properly (re)act for reaching some purposes. Anyway, the development of such systems asks for suitable approaches able to deal with issues like heterogeneity, sensor/actuator management, system reactivity, behavioural modelling, and context awareness. This paper proposes a multi-tier approach, based on concept hierarchies and sensor data fusion, dealing with the above aspects. The approach favours separation of concerns and abstractions. It relies on the use of the agent metaphor and statecharts. The iSapiens platform is suggested for implementation purposes. As a significant case study, the development of a smart museum located in Cosenza (Italy) is proposed.