Assimilation-accommodation mixed continuous ant colony optimization for fuzzy system design

Purpose The purpose of this paper is to propose a new population-based metaheuristic optimization algorithm, assimilation-accommodation mixed continuous ant colony optimization (ACACO), to improve the accuracy of Takagi-Sugeno-Kang-type fuzzy systems design. Design/methodology/approach The original...

Full description

Saved in:
Bibliographic Details
Published in:Engineering computations 2016-10, Vol.33 (7), p.1882-1898
Main Authors: Chen, Chi-Chung, Shen, Li Ping, Huang, Chien-Feng, Chang, Bao-Rong
Format: Article
Language:English
Subjects:
Accommodation
Accuracy
Algorithms
Ant colony optimization
Assimilation
Cognitive psychology
Design
Design engineering
Design optimization
Fuzzy logic
Fuzzy sets
Fuzzy systems
Genetic algorithms
Heuristic methods
Machine learning
Neural networks
Optimization algorithms
Systems design
Time series
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Purpose The purpose of this paper is to propose a new population-based metaheuristic optimization algorithm, assimilation-accommodation mixed continuous ant colony optimization (ACACO), to improve the accuracy of Takagi-Sugeno-Kang-type fuzzy systems design. Design/methodology/approach The original N solution vectors in ACACO are sorted and categorized into three groups according to their ranks. The Research Learning scheme provides the local search capability for the best-ranked group. The Basic Learning scheme uses the ant colony optimization (ACO) technique for the worst-ranked group to approach the best solution. The operations of assimilation, accommodation, and mutation in Mutual Learning scheme are used for the middle-ranked group to exchange and accommodate the partial information between groups and, globally, search information. Only the N top-best-performance solutions are reserved after each iteration of learning. Findings The proposed algorithm outperforms some reported ACO algorithms for the fuzzy system design with the same number of rules. The performance comparison with various previously published neural fuzzy systems also shows its superiority even with a smaller number of fuzzy rules to those neural fuzzy systems. Research limitations/implications Future work will consider the application of the proposed ACACO to the recurrent fuzzy network. Originality/value The originality of this work is to mix the work of the well-known psychologist Jean Piaget and the continuous ACO to propose a new population-based optimization algorithm whose superiority is demonstrated.
ISSN:0264-4401
1758-7077
DOI:10.1108/EC-08-2015-0248