Adaptive Equalisation using Neural Networks
Adaptive signal processing plays a crucial role in many modern communication systems. A particular example of adaptive signal processing is known as adaptive equalisation, which is an important technique for combatting distortion and interference in communication links. The conventional approach to communication channel equalisation is based on adaptive linear system theory. In the past few years, artificial neural networks have been applied to this important area of signal processing. The results obtained have indicated that the neural network approach offers superior performance over the conventional equalisation approach. This chapter continues this theme and investigates the application of neural networks to adaptive channel equalisation with the emphasis on what a neural network attempts to achieve and why it outperforms a conventional equaliser. This allows us to choose the most appropriate neural network structure for the task of equalisation. Issues of adaptive implementation and computational complexity are also addressed.
KeywordsLess Mean Square Radial Basis Function Network Volterra Series Bayesian Decision Less Mean Square Algorithm
Unable to display preview. Download preview PDF.
- J.G. Proakis, Digital Communications. New York: McGraw-Hill, 1983.Google Scholar
- G.J. Gibson, S. Siu and CRN. Cowan, “Application of multilayer perceptrons as adaptive channel equalisers,” in Proc. ICASSP (Glasgow, Scotland), 1989, pp.1183–1186.Google Scholar
- S. Chen, G.J. Gibson and CRN. Cowan, “Adaptive channel equalisation using a polynomial-perceptron structure,” Proc. IEE, Pt.I, Vol.137, No.5, pp.257–264, 1990.Google Scholar
- S. Siu, G.J. Gibson and CRN. Cowan, “Decision feedback equalization using neural network structures,” in Proc. 1st IEE Int. Conf. Artificial Neural Networks (London), 1989, pp. 125-128.Google Scholar
- M. Peng, C.L. Nikias and J.G. Proakis, “Adaptive equalization with neural networks: new multilayer perceptron structures and their evaluation,” in Proc. ICASSP (San Francisco), 1992, Vol.II, pp.301-304.Google Scholar
- S. Chen, B. Mulgrew and P.M. Grant, “A clustering technique for digital communications channel equalisation using radial basis function networks,” IEEE Trans. Neural Networks, to appear, 1992.Google Scholar
- S. Chen, B. Mulgrew and S. McLaughlin, “Adaptive Bayesian decision feedback equaliser based on a radial basis function network,” in Proc. ICC (Chicago), 1992, pp.343.3.1-343.3.5.Google Scholar
- S. Chen, S. McLaughlin and B. Mulgrew, “Complex-valued radial basis function network, Part II: application to digital communications channel equalisation,” submitted to Signal Processing, 1992.Google Scholar
- S. Chen, S. McLaughlin, B. Mulgrew and P.M. Grant, “Adaptive Bayesian decision feedback equaliser for dispersive mobile radio channels,” submitted to IEEE Trans. Communications, 1992.Google Scholar
- M.V. Eyuboglu and S.U.H. Qureshi, “Reduced-state sequence estimation with set partitioning and decision feedback,” IEEE Trans.Google Scholar
- R.P. Lippmann, “An introduction to computing with neural nets,” IEEE ASSP Magazine, Vol.4, 1987.Google Scholar
- D.E. Rumelhart, G.E. Hinton and R.J. Williams, “Learning internal representations by error propagation,” in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, D.E. Rumelhart and J.L. McClelland, Eds., Cambridge, MA: MIT Press, 1986, pp.318–362.Google Scholar