Equalization of satellite mobile communication channels using combined self-organizing maps and RBF networks

Author

Bouchired, Steven ; Ibnkahla, Mohamed ; Roviras, Daniel ; Castanié, Francis

Author_Institution

Nat. Polytech. Inst., Toulouse, France

Volume

6

fYear

1998

fDate

12-15 May 1998

Firstpage

3377

Abstract

The paper proposes a neural network approach to equalize time varying nonlinear channels. The approach is applied to a satellite UMTS channel composed of time invariant linear filters, a non-linear memoryless amplifier and a time varying multipath propagation channel. The neural network equalizer has a radial basis function structure. The usual k-mean clustering algorithm is replaced by a Kohonen (1995) learning rule. This results in an RBF-SOM equalizer which outperforms the LMS equalizer, and which has better recovering abilities (after passing through a high fading area) than the former RBF equalizer

Keywords

fading; feedforward neural nets; filtering theory; mobile satellite communication; multipath channels; radiofrequency amplifiers; self-organising feature maps; telecommunication computing; time-varying channels; Kohonen learning rule; LMS equalizer; RBF networks; channel equalization; fading; neural network equalizer; nonlinear memoryless amplifier; radial basis function structure; satellite UMTS channel; satellite mobile communication channels; self-organizing maps; signal processing; time invariant linear filters; time varying multipath propagation channel; time varying nonlinear channels; Artificial satellites; Clustering algorithms; Equalizers; Least squares approximation; Mobile communication; Neural networks; Neurons; Radial basis function networks; Self organizing feature maps; Signal processing algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on

Conference_Location

Seattle, WA

ISSN

1520-6149

Print_ISBN

0-7803-4428-6

Type

conf

DOI

10.1109/ICASSP.1998.679589

Filename

679589