Optimized FCM-Based radial basis function neural networks: a comparative analysis of LSE and WLSE method

Authors:
Wook-Dong Kim;Sung-Kwun Oh;Wei Huang
Affiliations:
Department of Electrical Engineering, The University of Suwon, Gyeonggi-do, South Korea;Department of Electrical Engineering, The University of Suwon, Gyeonggi-do, South Korea;State Key Lab of Software Engineering, Wuhan University, Wuhan, China
Venue:
ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part I
Year:
2010

Citing 5
Cited 0

Identifying fuzzy models utilizing genetic programming

Fuzzy Sets and Systems
Fuzzy Models and Algorithms for Pattern Recognition and Image Processing

Fuzzy Models and Algorithms for Pattern Recognition and Image Processing
Evolutionary algorithms for constrained parameter optimization problems

Evolutionary Computation
Linguistic models as a framework of user-centric system modeling

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
A highly interpretable form of Sugeno inference systems

IEEE Transactions on Fuzzy Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we introduce a new architecture of optimized FCM-based Radial Basis function Neural Network by using space search algorithm and discuss its comprehensive design methodology As the consequent part of rules of the FCM-based RBFNN model, four types of polynomials are considered The performance of the FCM-based RBFNN model is affected by some parameters such as the number of cluster and the fuzzification coefficient of the fuzzy clustering (FCM) and the order of polynomial standing in the consequent part of rules, we are required to carry out parametric optimization of network The space evolutionary algorithm(SEA) being applied to each receptive fields of FCM-based RBFNN leads to the selection of preferred receptive fields with specific local characteristics available within the FCM-based RBFNN The performance of the proposed model and the comparative analysis between WLSE and LSE are illustrated with by using two kinds of representative numerical dataset.