Matching Biomedical Ontologies through Adaptive Multi-Modal Multi-Objective Evolutionary Algorithm
To integrate massive amounts of heterogeneous biomedical data in biomedical ontologies and to provide more options for clinical diagnosis, this work proposes an adaptive Multi-modal Multi-Objective Evolutionary Algorithm (aMMOEA) to match two heterogeneous biomedical ontologies by finding the semant...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Biology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-7737/10/12/1287 |
| _version_ | 1797506505211117568 |
|---|---|
| author | Xingsi Xue Pei-Wei Tsai Yucheng Zhuang |
| author_facet | Xingsi Xue Pei-Wei Tsai Yucheng Zhuang |
| author_sort | Xingsi Xue |
| collection | DOAJ |
| description | To integrate massive amounts of heterogeneous biomedical data in biomedical ontologies and to provide more options for clinical diagnosis, this work proposes an adaptive Multi-modal Multi-Objective Evolutionary Algorithm (aMMOEA) to match two heterogeneous biomedical ontologies by finding the semantically identical concepts. In particular, we first propose two evaluation metrics on the alignment’s quality, which calculate the alignment’s statistical and its logical features, i.e., its f-measure and its conservativity. On this basis, we build a novel multi-objective optimization model for the biomedical ontology matching problem. By analyzing the essence of this problem, we point out that it is a large-scale Multi-modal Multi-objective Optimization Problem (MMOP) with sparse Pareto optimal solutions. Then, we propose a problem-specific aMMOEA to solve this problem, which uses the Guiding Matrix (GM) to adaptively guide the algorithm’s convergence and diversity in both objective and decision spaces. The experiment uses Ontology Alignment Evaluation Initiative (OAEI)’s biomedical tracks to test aMMOEA’s performance, and comparisons with two state-of-the-art MOEA-based matching techniques and OAEI’s participants show that aMMOEA is able to effectively determine diverse solutions for decision makers. |
| first_indexed | 2024-03-10T04:34:37Z |
| format | Article |
| id | doaj.art-4ef56b428300436188970b343d06788b |
| institution | Directory Open Access Journal |
| issn | 2079-7737 |
| language | English |
| last_indexed | 2024-03-10T04:34:37Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biology |
| spelling | doaj.art-4ef56b428300436188970b343d06788b2023-11-23T03:53:44ZengMDPI AGBiology2079-77372021-12-011012128710.3390/biology10121287Matching Biomedical Ontologies through Adaptive Multi-Modal Multi-Objective Evolutionary AlgorithmXingsi Xue0Pei-Wei Tsai1Yucheng Zhuang2Fujian Provincial Key Laboratory of Big Data Mining and Applications, Fujian University of Technology, Fuzhou 350118, ChinaDepartment of Computer Science and Software Engineering, Swinburne University of Technology, John Street, Hawthorn, VIC 3122, AustraliaIntelligent Information Processing Research Center, Fujian University of Technology, Fuzhou 350118, ChinaTo integrate massive amounts of heterogeneous biomedical data in biomedical ontologies and to provide more options for clinical diagnosis, this work proposes an adaptive Multi-modal Multi-Objective Evolutionary Algorithm (aMMOEA) to match two heterogeneous biomedical ontologies by finding the semantically identical concepts. In particular, we first propose two evaluation metrics on the alignment’s quality, which calculate the alignment’s statistical and its logical features, i.e., its f-measure and its conservativity. On this basis, we build a novel multi-objective optimization model for the biomedical ontology matching problem. By analyzing the essence of this problem, we point out that it is a large-scale Multi-modal Multi-objective Optimization Problem (MMOP) with sparse Pareto optimal solutions. Then, we propose a problem-specific aMMOEA to solve this problem, which uses the Guiding Matrix (GM) to adaptively guide the algorithm’s convergence and diversity in both objective and decision spaces. The experiment uses Ontology Alignment Evaluation Initiative (OAEI)’s biomedical tracks to test aMMOEA’s performance, and comparisons with two state-of-the-art MOEA-based matching techniques and OAEI’s participants show that aMMOEA is able to effectively determine diverse solutions for decision makers.https://www.mdpi.com/2079-7737/10/12/1287biomedical ontology matchingmulti-modal multi-objective evolutionary algorithmguiding matrix |
| spellingShingle | Xingsi Xue Pei-Wei Tsai Yucheng Zhuang Matching Biomedical Ontologies through Adaptive Multi-Modal Multi-Objective Evolutionary Algorithm Biology biomedical ontology matching multi-modal multi-objective evolutionary algorithm guiding matrix |
| title | Matching Biomedical Ontologies through Adaptive Multi-Modal Multi-Objective Evolutionary Algorithm |
| title_full | Matching Biomedical Ontologies through Adaptive Multi-Modal Multi-Objective Evolutionary Algorithm |
| title_fullStr | Matching Biomedical Ontologies through Adaptive Multi-Modal Multi-Objective Evolutionary Algorithm |
| title_full_unstemmed | Matching Biomedical Ontologies through Adaptive Multi-Modal Multi-Objective Evolutionary Algorithm |
| title_short | Matching Biomedical Ontologies through Adaptive Multi-Modal Multi-Objective Evolutionary Algorithm |
| title_sort | matching biomedical ontologies through adaptive multi modal multi objective evolutionary algorithm |
| topic | biomedical ontology matching multi-modal multi-objective evolutionary algorithm guiding matrix |
| url | https://www.mdpi.com/2079-7737/10/12/1287 |
| work_keys_str_mv | AT xingsixue matchingbiomedicalontologiesthroughadaptivemultimodalmultiobjectiveevolutionaryalgorithm AT peiweitsai matchingbiomedicalontologiesthroughadaptivemultimodalmultiobjectiveevolutionaryalgorithm AT yuchengzhuang matchingbiomedicalontologiesthroughadaptivemultimodalmultiobjectiveevolutionaryalgorithm |