Efficient reasoning techniques of ontologies in relational databases

Abstract

The Semantic Web is believed to be the next generation of the World Wide Web having a vision that machines can comprehend the semantics of Web data. Ontologies are the back-bones that provide semantics to the Semantic Web by defining shared and common vocabularies. The Web Ontology Language (OWL) has become a W3C recommendation to publish and share ontologies on the Web. To derive hidden information of OWL data, a number of OWL reasoners have been proposed to manage OWL data. Since OWL reasoners are memory based, they cannot handle large-sized OWL data. To overcome the scalability problem, RDBMS based systems have been proposed. These systems store OWL data into a database and perform reasoning of them in the database. However, they do not consider complete reasoning about all types of properties defined in OWL and the database schemas used by them are ineffective for reasoning. In addition, they do not manage the changes of OWL data which happen frequently in real applications. In this thesis, we compare different database schemas used by the RDBMS based systems and propose an improved schema for efficient reasoning. Also, to support reasoning for all types of properties defined in OWL, we propose a complete and efficient reasoning algorithm. Last, regarding the changes of OWL data, we suggest efficient approaches to manage the changes. Experimental results show that the improved schema has the best performance in OWL data storage and reasoning and the approaches to manage the changes of OWL data are more efficient than existing approaches.