标题: | A global optimized neuro-fuzzy system using artificial bee colony evolutionary algorithm |
作者: | Liu, Yu-Ting Lin, Yang-Yin Hsieh, Tsung-Yu Wu, Shang-Lin Lin, Chin-Teng 电控工程研究所 脑科学研究中心 Institute of Electrical and Control Engineering Brain Research Center |
关键字: | Neuro-fuzzy systems (NFS);artificial bee colony (ABC) algorithm;Swarm intelligence;Evolutionary algorithm (EA) |
公开日期: | 1-一月-2015 |
摘要: | This paper proposes a novel Takagi-Sugeno-Kang-type (TSK-type) neuro-fuzzy system (NFS), which utilizes the artificial bee colony (ABC) evolutionary algorithm for parameter optimization. The ABC evolutionary algorithm was developed based on imitating foraging behavior of natural bees for numerical optimization problems, and it has been proved to outperform other metaheuristic approaches on different constrain optimization problems in previous studies. The proposed NFS in this paper adopts an adaptive clustering method to generate fuzzy rules for determining the system architecture, and the TSK-type reasoning is employed for the consequent part of each rule. Subsequently, all free parameters in the NFS designed, including the premise and the consequent parameters, will be optimized by ABC algorithm. This study compares the performance of ABC algorithm with that of Genetic Algorithm (GA), Particle Swarm Optimization (PSO) and Differential Evolution (DE). The simulation results show that the performance of ABC algorithm is superior to that of the mentioned algorithms for solving dynamic system problems. |
URI: | http://dx.doi.org/10.3233/978-1-61499-484-8-140 http://hdl.handle.net/11536/150895 |
ISSN: | 0922-6389 |
DOI: | 10.3233/978-1-61499-484-8-140 |
期刊: | INTELLIGENT SYSTEMS AND APPLICATIONS (ICS 2014) |
Volume: | 274 |
起始页: | 140 |
结束页: | 149 |
显示于类别: | Conferences Paper |