Adaptive decision-feedback equalizer using forward-only counterpropagation networks for Rayleigh fading channels

Abstract

A forward-only counterpropagation network (FCPN) is proposed for nonlinear equalization of digital transmission channels. The FCPN is a type of multilayer feedforward network proposed by Hecht-Nielsen. Its learning mechanism is a combination of unsupervised self-organizing and supervised training. A decision-feedback equalizer based on FCPN was simulated on a digital computer. The results show that an FCPN-based equalizer can equalize transmission channels with time-varying characteristics modeled by Rayleigh fading adaptively by using the self-organization mechanism. The bit-error rate is lower than for the conventional equalizer using a linear transversal filter.<>