Channel equalization by feedforward neural networks

A signal suffers from nonlinear, linear, and additive distortion when transmitted through a channel. Linear equalizers are commonly used in receivers to compensate for linear channel distortion. As an alternative, nonlinear equalizers have the potential to compensate for all three sources of channel distortion. Previous authors have shown that nonlinear feedforward equalizers based on either multilayer perceptron (MLP) or radial basis function (RBF) neural networks can outperform linear equalizers. In this paper, we compare the performance of MLP vs. RBF equalizers in terms of symbol error rate vs. SNR. We design a reduced complexity neural network equalizer by cascading an MLP and a RBF network. In simulation, the new MLP-RBF equalizer outperforms MLP equalizers and RBF equalizers.

[1]  Shun-ichi Amari,et al.  Natural Gradient Works Efficiently in Learning , 1998, Neural Computation.

[2]  Sammy Siu,et al.  Multilayer perceptron structures applied to adaptive equalisers for data communications , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[3]  George W. Irwin,et al.  A hybrid linear/nonlinear training algorithm for feedforward neural networks , 1998, IEEE Trans. Neural Networks.

[4]  Bernie Mulgrew,et al.  Applying radial basis functions , 1996, IEEE Signal Process. Mag..

[5]  N. Tepedelenlioglu,et al.  Channel equalization using radial basis function network , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[6]  Sheng Chen,et al.  Reconstruction of binary signals using an adaptive radial-basis-function equalizer , 1991, Signal Process..

[7]  Jacques de Villiers,et al.  Backpropagation neural nets with one and two hidden layers , 1993, IEEE Trans. Neural Networks.

[8]  S. Amari.  Natural Gradient Works Eciently in Learning , 2022 .

[9]  J. G. Proakis,et al.  Adaptive equalization with neural networks: new multi-layer perceptron structures and their evaluation , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[10]  C.F.N. Cowan,et al.  Adaptive equalization of finite nonlinear channels using multilayer perceptron , 1990 .

[11]  Sheng Chen,et al.  Adaptive Equalisation to finite Non-linear Channels using Multilayer Perceptrons , 1990 .

[12]  Bruce W. Suter,et al.  The multilayer perceptron as an approximation to a Bayes optimal discriminant function , 1990, IEEE Trans. Neural Networks.

[13]  Daniel Roviras,et al.  Equalization of satellite mobile communication channels using combined self-organizing maps and RBF networks , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[14]  H. Lev-Ari,et al.  Performance improvement of neural network equalizers , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[15]  Bing J. Sheu,et al.  1-D compact neural networks for wireless communication and mobile computing , 1996, 1996 IEEE International Symposium on Circuits and Systems. Circuits and Systems Connecting the World. ISCAS 96.

[16]  C.A. Belfiore,et al.  Decision feedback equalization , 1979, Proceedings of the IEEE.

[17]  S. Qureshi,et al.  Adaptive equalization , 1982, Proceedings of the IEEE.

[18]  C.F.N. Cowan,et al.  The application of nonlinear structures to the reconstruction of binary signals , 1991, IEEE Trans. Signal Process..

[19]  Chrysostomos L. Nikias,et al.  Adaptive equalization for PAM and QAM signals with neural networks , 1991, [1991] Conference Record of the Twenty-Fifth Asilomar Conference on Signals, Systems & Computers.