Shuffled Frog Leaping Algorithm combined with Fuzzy Wavelet Neural Network for Function Learning

摘要：

In this paper an efficient shuffled frog leaping algorithm (SFLA) is proposed to improve the function approximation accuracy and general capability of the fuzzy wavelet neural network (FVVNN) system.In presented FVVNN,the fuzzy rules that contain wavelets are constructed.Each fuzzy rule corresponds to a subwavelet neural network (sub-WNN) consisting of wavelets with a specified dilation value.Orthogonal least square (OLS) algorithm is used to determine the number of fuzzy rules and to purify the wavelets for each rule and SFLA is suggested for learning of FVVNN parameters.Simulation results demonstrate effectiveness and ability of proposed approach.Also,to validate the results obtained by SFL algorithm,Genetic Algorithm (GA) is applied for comparison.The simulation study shows SFLA performs well in finding the solution.

关键词： shuffled frog leaping fuzzy wavelet neural network function learning

作者: Ehsan Bijami Maryam Shahriari-kahkeshi Maryam Zekri

作者单位: Dep.of Electrical Engineering,Isfahan University of Technology Isfahan,Iran

会议类型: 国际会议

会议名称: 2010 4th International Conference on Intelligent Information Techonlogy Application(第四届智能信息技术应用国际学术研讨会 IITA 2010)

会议地点: 秦皇岛

会议语种:英文

页码: 104-107

在线出版日期: 2010-11-05（万方平台首次上网日期，不代表论文的发表时间）