Nonlinear multilayer combining techniques for Bayesian equalizers using the radial basis function network as a digital magnetic storage equalizer

摘要

In order to reduce the complexity and enhance the performance of the Bayesian equalizer using the radial basis function (RBF) network, a new equalizer using the RBF network with a nonlinear multilayer combiner (RNEQ) is proposed. The RNEQ is applied to a digital storage system in which the primary element of impairment is nonlinear distortion due to partial erasure. From computer simulation results, the RNEQ with almost 70% reduced structural complexity over the conventional equalizer using RBF network has nearly the same performance in terms of bit-error rate (BER) and mean squared error.