DESIGN FOR CENTERS OF RBF NEURAL NETWORKS FOR FAST TIME-VARYING CHANNEL EQUALIZATION

Authors
GAN Q SUBRAMANIAN R SUNDARARAJAN N SARATCHANDRAN P
Citation
Q. Gan et al., DESIGN FOR CENTERS OF RBF NEURAL NETWORKS FOR FAST TIME-VARYING CHANNEL EQUALIZATION, Electronics Letters, 32(25), 1996, pp. 2333-2334
Citations number
5
Categorie Soggetti
Engineering, Eletrical & Electronic
Journal title
Electronics Letters → ACNP
ISSN journal
00135194
Volume
32
Issue
25
Year of publication
1996
Pages
2333 - 2334
Database
ISI
SICI code
0013-5194(1996)32:25<2333:DFCORN>2.0.ZU;2-Y
Abstract
A radial basis function (RBF) neural network, combined with a channel estimator, is used for fast time-varying channel equalisation. A new m ethod for calculating RBF centres and weights is proposed to reduce th e number of hidden units in the high-order RBF equaliser. A Rayleigh f ading channel model and 10 million random symbols are used in the simu lation studies. Very good equalisation performance is achieved by usin g a high-order RBF network with only eight centres.