Reducing Criteria in Multicriteria Group Decision-Making Methods Using Hierarchical Clustering Methods and Fuzzy Ontologies
| Autor: | Juan Antonio Morente-Molinera, Ali Morfeq, Zaiwu Gong, Yinglin Wang, Rami Al-Hmouz, Enrique Herrera-Viedma |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Focus (computing)
Process (engineering) business.industry Computer science Applied Mathematics Fuzzy ontology Machine learning computer.software_genre Hierarchical clustering Group decision-making Computational Theory and Mathematics Ranking Artificial Intelligence Control and Systems Engineering Order (business) Artificial intelligence business Set (psychology) computer |
| Zdroj: | IEEE Transactions on Fuzzy Systems. 30:1585-1598 |
| ISSN: | 1941-0034 1063-6706 |
| DOI: | 10.1109/tfuzz.2021.3062145 |
| Popis: | Multi-criteria group decision making environments that have a high number of criteria values can be difficult for the experts to handle. This is due to the fact that the experts have to take too much information into account. Thus, they get lost among all the possibilities and have difficulties making the right decision. In order to solve this problem we present a novel multi-criteria group decision making method that reduces the initial set of criteria values in an organized way. Hierarchical clustering methods are used in order to generate a new reduced criteria set that can be handled by the experts. Fuzzy ontologies are used as an aid system that stores how much each alternative fulfills each criterion. The presented method makes it possible for the experts to carry out the group decision making process by focusing on ranking the reduced set of criteria values. As a result, a comfortable decision environment is generated, in which the experts can make decisions by managing a fair amount of information. The aid provided by fuzzy ontologies allow the experts to focus on establishing the importance of the criteria values, leaving the rest to the computational system. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|