Title: Function approximation using robust fuzzy-GreyCMAC method

Authors: Hen-Kung Wang; Jonq-Chin Hwang; Po-Lun Chang; Fei-Hu Hsieh

Addresses: Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei City, Taiwan; Lunghwa University of Science and Technology, Taoyuan County, Taiwan. ' Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei City, Taiwan. ' Department of Electrical Engineering, Lunghwa University of Science and Technology, Taoyuan County, Taiwan. ' Department of Electrical Engineering, Lunghwa University of Science and Technology, Taoyuan County, Taiwan

Abstract: A novel GreyCMAC model combined with robust FCM (RFCM) approach for function approximation is proposed in this paper. In order to overcome the problems of function approximation for a non-linear system with noises and outliers, a robust fuzzy clustering method is proposed to mitigate the influence of noises and outliers and then a novel GreyCMAC model is proposed to learn the non-linear system|s features for fast and accurate function approximation. There are two core ideas in the proposed approach: 1) the robust fuzzy c-means algorithm (RFCM) is proposed to greatly mitigate the influence of data noises and outliers; 2) a grey-based CMAC (GreyCMAC) is proposed to locate a given fine piecewise linear data domain by RFCM so that a CMAC neural network can be constructed for function approximation. The conducted simulation results clearly indicate that the proposed approach provides good performance.

Keywords: GreyCMAC; robust FCM; fuzzy c-means; RFCM; noises; outliers; function approximation; fuzzy clustering.

DOI: 10.1504/IJMIC.2011.043144

International Journal of Modelling, Identification and Control, 2011 Vol.14 No.4, pp.227 - 234

Published online: 21 Mar 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article