Research Area:  Machine Learning
Semantic similarity plays a critical role in geospatial cognition, semantic interoperability, information integration and information retrieval and reasoning in geographic information science. Although some computational models for semantic similarity measurement have been proposed in literature, these models overlook spatial distribution characteristics or geometric features and pay little attention to the types and ranges of properties. This paper presents a novel semantic similarity measurement approach that employs a richer structured semantic description containing properties as well as relations. This approach captures the geo-semantic similarity more accurately and effectively by evaluating the contributions for ontological properties, measuring the effect of the relative position in the ontology hierarchy structure and computing the geometric feature similarity for geospatial entities. A water body ontology is used to illustrate the approach in a case study. A human-subject experiment was carried out and the experiment results shows that this proposed approach has a good performance based on the high correlation between its computed similarity results and humans judgements of similarity.
Keywords:  
Author(s) Name:  Liangang Wang, Feng Zhang, Zhenhong Du, Yongpei Chen, Chuanrong Zhang, Renyi Liu
Journal name:  Microprocessors and Microsystems
Conferrence name:  
Publisher name:  Elsevier
DOI:  10.1016/j.micpro.2020.103526
Volume Information:   Volume 80, February 2021, 103526
Paper Link:   https://www.sciencedirect.com/science/article/abs/pii/S0141933120306761