Visible to the public Rule-Based Cooperative Continuous Ant Colony Optimization to Improve the Accuracy of Fuzzy System Design

TitleRule-Based Cooperative Continuous Ant Colony Optimization to Improve the Accuracy of Fuzzy System Design
Publication TypeJournal Article
Year of Publication2014
AuthorsChia-Feng Juang, Chi-Wei Hung, Chia-Hung Hsu
JournalFuzzy Systems, IEEE Transactions on
Date PublishedAug
Keywordsaccuracy-oriented fuzzy system design problems, Algorithm design and analysis, ant colony optimisation, Ant colony optimization, ant wandering operation, best-ant-attraction refinement, CCACO algorithm, control system synthesis, cooperative evolution, evolutionary fuzzy systems, Frequency selective surfaces, FSs, fuzzy control, fuzzy controller, fuzzy systems, Optimization, parameter solution vector, pheromone-based tournament ant path selection, predictor design problems, Probability density function, rule-based cooperative continuous ant colony optimization, subsolution component, swarm intelligence (SI), Takagi-Sugeno-Kang fuzzy systems, TSK FS, Vectors

This paper proposes a cooperative continuous ant colony optimization (CCACO) algorithm and applies it to address the accuracy-oriented fuzzy systems (FSs) design problems. All of the free parameters in a zero- or first-order Takagi-Sugeno-Kang (TSK) FS are optimized through CCACO. The CCACO algorithm performs optimization through multiple ant colonies, where each ant colony is only responsible for optimizing the free parameters in a single fuzzy rule. The ant colonies cooperate to design a complete FS, with a complete parameter solution vector (encoding a complete FS) that is formed by selecting a subsolution component (encoding a single fuzzy rule) from each colony. Subsolutions in each ant colony are evolved independently using a new continuous ant colony optimization algorithm. In the CCACO, solutions are updated via the techniques of pheromone-based tournament ant path selection, ant wandering operation, and best-ant-attraction refinement. The performance of the CCACO is verified through applications to fuzzy controller and predictor design problems. Comparisons with other population-based optimization algorithms verify the superiority of the CCACO.

Citation Key6555815