OWL 2 modeling and reasoning with complex human activities

In recent years, there has been a growing interest in the adoption of ontologies and ontological reasoning to automatically recognize complex context data such as human activities. In particular, the Web Ontology Language (OWL) emerged as the language of choice, being a standard for the Semantic Web, and supported by a number of tools for knowledge engineering and reasoning. However, the limitations of OWL 1 in terms of expressiveness have been recognized in various fields, and important research efforts have been made to extend the language while preserving decidability of its OWL 1 DL fragment. The result of such work is OWL 2. In this paper we investigate the use of OWL 2 for modeling complex activities and reasoning with them. We show that the new language constructors of OWL 2 overcome the main limitations of OWL 1 for the representation of activities; OWL 2 axioms can be used to represent certain rules and rule-based reasoning previously demanded to hybrid approaches, with the advantage of having a unique semantics, avoiding potential inconsistencies. Then, we propose a system architecture showing the integration of a novel OWL 2 activity ontology and reasoning modules with distributed modules for sensor data aggregation and reasoning. The feasibility of our solution is shown by an extensive experimental evaluation with simulations of different intelligent environments.