Construction of semantic location model based on typonym ontology

Location is becoming kind of context fundamental information in ubiquitous computing environment. Location aware applications require a well-formed location model. Current location models can be classified into geometric location models and semantic location models. The former only represents the geometric coordinates without the location semantics. The later represents logical features and their semantics, but requires a large amount of manual effort. In this paper, we present a semantic location model based on toponym ontology, which combines location semantics and spatial information. In order to support computer understanding and inference based on rules, semantic location is formalized by using typonym ontology, which incorporates location semaitic properties and rules. Through model construction and location instance maintenance in ArcGIS geodatabase, we show that our model is simple but powerful enough to express location semantics to support location-based applications. Furthermore, the location model can be used in machine learning and rule based applications.