[KSCI] Korea Science Citation Index Service

Step-Size Control for Width Adaptation in Radial Basis Function Networks for Nonlinear Channel Equalization

Kim, Nam-Yong (Department of Information & Communication Engineering, Kangwon National University)

Publication Information

Journal of Communications and Networks / v.12, no.6, 2010 , pp. 600-604 More about this Journal

Abstract

A method of width adaptation in the radial basis function network (RBFN) using stochastic gradient (SG) algorithm is introduced. Using Taylor's expansion of error signal and differentiating the error with respect to the step-size, the optimal time-varying step-size of the width in RBFN is derived. The proposed approach to adjusting widths in RBFN achieves superior learning speed and the steady-state mean square error (MSE) performance in nonlinear channel environment. The proposed method has shown enhanced steady-state MSE performance by more than 3 dB in both nonlinear channel environments. The results confirm that controlling over step-size of the width in RBFN by the proposed algorithm can be an effective approach to enhancement of convergence speed and the steady-state value of MSE.

Keywords

Equalization; nonlinear channel; radial basis function network (RBFN); step-size; stochastic gradient (SG); width;

Citations & Related Records

Times Cited By Web Of Science : 0 (Related Records In Web of Science)
Times Cited By SCOPUS : 0

Reference

1	N. Mai-Duy and T. Tran-Cong, "Numerical solution of differential equations using multiquadratic radial basis function networks," Neural Netw., vol. 14, pp. 185-199, 2001. DOI ScienceOn
2	D. Havelock, S. Kuwano, and M. Vorlander, Handbook of Signal Processing in Acoustics, Springer, 2008.
3	S. Chen, G. Gibson, C. Cowan, and P. Grant, "Adaptive equalization of finite nonlinear channels using multilayer perceptrons," in Proc. IEEE Signal Process., vol. 20, 1990, pp. 107-119.
4	D. Sebald and Bucklew, "Support vector machine techniques for nonlinear equalization," IEEE Trans. Signal Process., vol. 48, pp. 3217-3226, 2000. DOI ScienceOn
5	S.McLoone and G. Irwin, "Nonlinear optimization of RBF networks", Int. J. Syst. Sci., vol. 29, pp. 179-189, 1998. DOI ScienceOn
6	S. Haykin, Neural Networks: A Comprehensive Foundation, Prentice-Hall, 1999.
7	I. Cha and S. A. Kassam, "Time-series prediction by adaptive radial basis function networks," in Proc. IEEE Twenty-Sixth Ann. Conf. Inf. Sci., Syst., 1993, pp. 818-823.
8	K. H. Kwon, N. Kim, and H. G. Byun, "On training neural network algorithms for odor identification for future multimedia communication system," in Proc. IEEE ICME2, July 2006, pp. 1309-1312.
9	I. Cha and S. A. Kassam, "Interference cancellation using radial basis function networks," in Proc. IEEE Signal processing, vol. 47, 1995, pp. 247-268.