JournalVolume 25, No.2, Special Issue on Artificial Intelligence and Computational Methods for the Medical Cyber-Physical SystemsEfficient Biomedical Ontology Matching for Medical Cyber-Physical Systems through Genetic Algorithm with Semantic Search and Adaptive Similarity Measure (pp.270-298) X. Xue1,2,*, S.M. Waqas1, C.-M. Chen3, M. Amoon4 https://doi.org/10.30546/1683-6154.25.2.2026.2701College of Artificial Intelligence, Yango University, Fuzhou, Fujian, 350015, China, e-mail: waqas@ygu.edu.cn
Abstract. In this paper, we introduce a novel Genetic Algorithm with Semantic Search (GASS) to efficiently match biomedical ontologies. First, we use a new reference-free evaluation metric that combines an approximated F-measure estimator with a local consistency measure, enabling effective fitness evaluation without requiring gold-standard alignments. Second, we develop a semantic search mechanism that exploits structural regularities to efficiently refine promising solutions. Third, we design an adaptive similarity measure that integrates syntactic, linguistic, and taxonomic features and dynamically adjusts their weights based on their relevance to the matching context. The proposed GA-SS is compared with the state-of-the-art ontology matching methods on the Ontology Alignment Evaluation Initiative’s Benchmark and Anatomy datasets, and the experimental results demonstrate that GA-SS is able to identify high-quality alignments while achieving superior matching efficiency, outperforming the state of-the-art matching methods. Keywords: Medical Cyber-Physical System, Biomedical Ontology Matching, Genetic Algorithm, Semantic Search, Adaptive Similarity Measure. AMS Subject Classification: 68W50, 68T35, 92C50. |
|