IJARCCE adheres to the suggestive parameters outlined by the University Grants Commission (UGC) for peer-reviewed journals, upholding high standards of research quality, ethical publishing, and academic excellence.
A Relative Structure Similarity Method For Multiple Ontologies Alignment
ALI I.EL-DESOUKY, HESHAM A.ALI, RABAB S.RASHED Computers and Systems Department, Faculty of Engineering, Mansoura University, Egypt Computers and Systems Department, Faculty of Engineering, Mansoura University, Egypt Electrical Engineering Department, Faculty of Engineering, Kafr Elsheikh University, Egypt
Abstract: Knowledge in domain is expressed with the help of ontology which is scattered all over its space. Using ontology gives a share in increasing precision. Different ontologies may represent the same domain, thus includes different terms that equivalently refer to the same meaning and vice versa. This results in different structures for ontologies. That's why it is necessary to relate concepts and keywords within the same domain. One of the efficient ways to relating domain knowledge representation is ontology alignment and mapping. The main objective of ontology mapping is to determine the relationship between concepts and find the semantic mapping between ontologies. This problem lies at the heart of numerous information processing applications. As the same domain knowledge are described by different ontologies differ in modeling or structure or language which leads to heterogeneity. To overcome this problem, this paper uses different similarities to find the relationships between ontologies. String similarity but it only considers the same term that represents different meaning. So semantic similarity is needed to be employed for higher efficiency, so semantic similarity using WorldNet database is explored and the results of pervious similarities are considered the primitive similarity to overcome all heterogeneity problems by structure similarity based on common subsume concepts and semantic similarity by IC(information content) and modify calculation of IC to consider all concept attributes. Structure similarity and semantic similarity are combined and called relative similarity. This paper suggests a modified structural similarity method called a relative structure similarity that present a way for solving the heterogeneity between ontologies based on entities that have a common subsumed which have a relationship and information content(IC). The proposed method presents a scheme based on the real relationships across ontologies, and modification of calculation of information content using intrinsic information of ontologies to overcome of drawbacks of the methods by taking into account entity attributes. Comparison studies are made to test the validity of the proposed method.
Keywords: ontology Alignment, mapping, structure similarity, Information content(IC), Lowest Common Subsumer (LCS).
How to Cite:
[1] ALI I.EL-DESOUKY, HESHAM A.ALI, RABAB S.RASHED Computers and Systems Department, Faculty of Engineering, Mansoura University, Egypt Computers and Systems Department, Faculty of Engineering, Mansoura University, Egypt Electrical Engineering Department, Faculty of Engineering, Kafr Elsheikh University, Egypt, âA Relative Structure Similarity Method For Multiple Ontologies Alignment,â International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE)
This work is licensed under a Creative Commons Attribution 4.0 International License.