Wavelet neural networks for adaptive equalization

Author

Jiang, Minghu ; Gielen, Georges ; Deng, Beixing ; Tang, Xiaofang ; Ruan, Qiuqi ; Yuan, Baozong

Author_Institution

Dept. of Electr. Eng, Katholieke Univ., Leuven, Heverlee, Belgium

Volume

2

fYear

2002

fDate

26-30 Aug. 2002

Firstpage

1251

Abstract

A structure based on the wavelet neural networks is proposed for nonlinear channel equalization in a digital communication system, the minimum error probability (MEP) is applied as performance criterion to update the weighting matrix of wavelet networks. Our experimental results show that performance of the proposed wavelet networks based on equalizer can significantly improve the neural modeling accuracy and outperform the conventional neural networks in signal to noise ratio and channel non-linearity.

Keywords

adaptive equalisers; digital communication; error statistics; learning (artificial intelligence); matrix algebra; neural nets; wavelet transforms; SNR; adaptive equalization; channel nonlinearity; digital communication system; learning algorithm; minimum error probability; neural modeling accuracy; nonlinear channel equalization; nonlinear distortion compensation; performance criterion; signal to noise ratio; wavelet neural networks; weighting matrix updating; Adaptive equalizers; Adaptive systems; Bit error rate; Digital communication; Error probability; Feature extraction; Multi-layer neural network; Neural networks; Signal processing; Wavelet domain;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 2002 6th International Conference on

Print_ISBN

0-7803-7488-6

Type

conf

DOI

10.1109/ICOSP.2002.1180018

Filename

1180018