Channel equalization using adaptive complex radial basis function networks

Author

Cha, Inhyok ; Kassam, Saleem A.

Author_Institution

Dept. of Electr. Eng., Pennsylvania Univ., Philadelphia, PA, USA

Volume

13

Issue

1

fYear

1995

fDate

1/1/1995 12:00:00 AM

Firstpage

122

Lastpage

131

Abstract

It is generally recognized that digital channel equalization can be interpreted as a problem of nonlinear classification. Networks capable of approximating nonlinear mappings can be quite useful in such applications. The radial basis function network (RBFN) is one such network. We consider an extension of the RBFN for complex-valued signals (the complex RBFN or CRBFN). We also propose a stochastic-gradient (SG) training algorithm that adapts all free parameters of the network. We then consider the problem of equalization of complex nonlinear channels using the CRBFN as part of an equalizer. Results of simulations we have carried out show that the CRBFN with the SG algorithm can be quite effective in channel equalization

Keywords

equalisers; feedforward neural nets; learning (artificial intelligence); multilayer perceptrons; signal processing; telecommunication channels; CRBFN; RBFN; adaptive complex radial basis function networks; channel equalization; complex-valued signals; network parameters; nonlinear classification; nonlinear mappings; simulations; stochastic-gradient training algorithm; Adaptive equalizers; Additive noise; Communication standards; Decision feedback equalizers; Delay estimation; Filtering; Finite impulse response filter; Gaussian noise; Nonlinear filters; Radial basis function networks;

fLanguage

English

Journal_Title

Selected Areas in Communications, IEEE Journal on

Publisher

ieee

ISSN

0733-8716

Type

jour

DOI

10.1109/49.363139

Filename

363139