An ontology-based autonomic system for Ambient Intelligence scenarios

Abstract

Pervasive computing and Ambient Intelligence (AmI) demonstrate that computer systems which directly interact with users are characterized by increasing size and complexity, so that the human user will still not be able to adequately manage them for a long time to come. As a response to this trend, the Autonomic Computing paradigm aims to design and develop systems able to self-configure and self-manage. The research reported here is part of an AmI project that proposes a multi-tier cognitive architecture for aggregating sensory information at different levels of abstraction. In such an architecture, a central reasoning component is able to understand the environmental state and the user's preferences and consequently to plan the opportune actions to be performed. This chapter describes an ontology able to provide a formal representation of the environment in which the AmI system is placed, as well as a representation of the system itself and of its interaction with the environment. By exploiting this knowledge, the AmI system can develop consciousness of itself and of its cognitive processes, and consequently the capability of autonomously managing its own functioning. In particular, this task is performed by a rule-based planning module, integrated within the multi-level architecture, and capable of managing and configuring the sensory infrastructure. By means of this module, the AmI system can manage its own monitoring activity to obtain a good understanding of the context while minimizing system energy consumption. © Springer International Publishing Switzerland 2014.