Evaluating Taxonomic Relationships Using Semantic Similarity Measures on Sensor Domain Ontologies

The importance of sensors nowadays is all about the boom of internet of things. Sensors produce a mass of heterogeneous data continuously, and just like the data produced on the web, sensor data lack semantic information. This problem can be overcome with semantic web technologies by designing ontologies to provide a semantic structure of sensor data as well as machine readable data improving the interoperability. Those ontologies must be evaluated to verify their semantic quality and this is where semantic similarity plays its function. Semantic similarity is a metric used to know the similarity degree of two concepts in an ontology. In this research, we propose a system which evaluates taxonomic relationships in ontologies using semantic similarity through an algorithm and the accuracy measure. The applied semantic similarity measures are classified in four categories: structure-based, feature-based, content information and hybrid measures. In this research, we evaluate sensors domain ontologies using semantic similarity measures and we obtained promising results in the evaluation of the taxonomic relationships.