MetaQ: A knowledge-driven framework for context-aware activity recognition combining SPARQL and OWL 2 activity patterns

In this paper we describe MetaQ, an ontology-based hybrid framework for activity recognition in Ambient Assisted Living (AAL) environments that combines SPARQL queries and OWL 2 activity patterns. SPARQL is used as a standardised declarative language for aggregating, interpreting and enriching low-level contextual RDF knowledge bases with higher level derivations. The proposed SPARQL-based reasoning framework supports key inferencing tasks that are important in activity interpretation domains, but not supported by the standard semantics of OWL 2, such as temporal reasoning and dynamic assertion of structured individuals. In order to promote the extensibility and reuse of the underlying interpretation semantics, the reasoning framework is further enhanced with a conceptual layer that allows the formal representation of activity meta-knowledge by means of DOLCE+DnS Ultralite (DUL) ontology patterns. We illustrate the capabilities of the proposed framework through its deployment in a hospital for monitoring activities of Alzheimer’s disease patients.