论文信息 - Design for centres of RBF neural networks for fast time-varying channel equalisation

Design for centres of RBF neural networks for fast time-varying channel equalisation

A radial basis function (RBF) neural network, combined with a channel estimator, is used for fast time-varying channel equalisation. A new method for calculating RBF centres and weights is proposed to reduce the number of hidden units in the high-order RBF equaliser. A Rayleigh fading channel model and 10 million random symbols are used in the simulation studies. Very good equalisation performance is achieved by using a high-order RBF network with only eight centres.

N. Sundararajan | P. Saratchandran | R. Subramanian | Q. Gan

[1] Sheng Chen,et al. A clustering technique for digital communications channel equalization using radial basis function networks , 1993, IEEE Trans. Neural Networks.

[2] Tadashi Fujino,et al. An adaptive maximum-likelihood sequence estimator for fast time-varying intersymbol interference channels , 1994, IEEE Trans. Commun..

[3] W. C. Jakes,et al. Microwave Mobile Communications , 1974 .

[4] John G. Proakis,et al. Digital Communications , 1983 .

[5] Jagdish C. Patra,et al. A functional link artificial neural network for adaptive channel equalization , 1995, Signal Process..