Optimal symbol-by-symbol detector for linear dispersive AWGN channels

Abstract

In this study, symbol detection in the presence of intersymbol interference and additive white Gaussian noise is considered. The optimal solution, in the sense of minimizing the symbol error, is obtained through the Bayes decision theory. It is shown that the optimal Bayesian detector has two different but equivalent realizations in the form of a multi-layer perceptron and a radial basis function network. The parameters of these networks can be optimally set if the channel characteristics are known. For unknown channel cases, a simple adaptive structure, which employs a channel estimator, is proposed.