A Hybrid Central Force Optimization Algorithm for Optimizing Ontology Alignment

Abstract

Ontology is regarded as an effective solution to data heterogeneity on the semantic web. However, different ontology engineers might use different ways to define the concept, which causes the ontology heterogeneity problem and raises the heterogeneous problem to a higher level. Ontology matching technology, which is able to identify the same concepts in two heterogeneous ontologies, is recognized as a ground solution to tackle the ontology heterogeneity problem. Since different ontology matchers do not necessarily find the same correct correspondences, usually several competing matchers are applied to the same pair of entities in order to increase evidence towards a potential match or mismatch. How to select, combine and tune various ontology matchers to obtain the high quality ontology alignment becomes a crucial challenges in ontology matching domain. Recently, swarm intelligent algorithms are appearing as a suitable methodology to face this challenge, but the slow convergence and premature convergence are two main shortcomings that makes them incapable of effectively searching the optimal solution for large scale and complex ontology matching problems. To improve the ontology alignment’s quality, our work investigates a new emergent class of swarm intelligent algorithm, named Central Force Optimization (CFO) algorithm. To balance CFO’s exploration and exploitation, we proposes a Hybrid CFO (HCFO) by introducing the local search strategy into CFO’s evolving process, and utilize HCFO to automatically select, combine and tune various ontology matchers to optimize the ontology alignment. The experimental results show that our approach can significantly improve the ontology alignment’s quality of existing swarm intelligent algorithm based ontology matching technologies.