Learning cooperative linguistic fuzzy rules using the best–worst ant system algorithm

摘要: Within the field of linguistic fuzzy modeling with rule-based systems, automatic derivation rules from numerical data is an important task. In last few years, a large number contributions based on techniques such as neural networks and genetic algorithms have been proposed to face this problem. article, we introduce novel approach rule learning problem ant colony optimization (ACO) algorithms. To do so, task formulated combinatorial Our process COR methodology in previous works, which provides search space that allows us obtain models good interpretability–accuracy trade-off. A specific ACO-based algorithm, Best–Worst Ant System, used for purpose due performance shown when solving other problems. We analyze behavior method compare it methods two real-world applications. The obtained results lead remark our proposal terms interpretability, accuracy, efficiency. © 2005 Wiley Periodicals, Inc. Int J Syst 20: 433–452, 2005.