A Fuzzy Geospatial Ontology Model and Its Application in Geospatial Semantic Retrieval

Abstract

Geospatial ontology plays a key role in Geospatial Semantic Retrieval (GSR), which provides support for query expansion and disambiguation, relevance ranking and web page annotation. However, existing ontologies are deficient in representing and reasoning fuzzy geospatial information, an important type of information that distributes widely in user’s queries and web pages. This paper proposes a novel fuzzy geospatial ontology model, FGSO. In FGSO, the complex semantic of fuzzy spatial relations are described explicitly by a fuzzy spatial relation ontology which also carries out fuzzy spatial reasoning; a fuzzy geospatial ontology based on our new ontology language, FR-OWL, is developed to represent a variety of geospatial information besides spatial relations in a uniform format; a converting algorithm is developed to integrate these two ontologies to mine more information. Based on FGSO, a fuzzy geospatial semantic retrieval system, FGSRS, is constructed. Experiment results show that it outperforms keyword-based search tools on both Recall and Precision, and supports more types of fuzzy spatial query than existing GSR systems.