Blind Equalization Method Based on Sparse Bayesian Learning

Abstract

A novel adaptive blind equalization method based on sparse Bayesian learning (blind relevance vector machine (RVM) equalizer) is proposed. This letter incorporates a Godard or constant modulus algorithm (CMA)-like error function into a general Bayesian framework. This Bayesian framework can obtain sparse solutions to regression tasks utilizing models linear in the parameters. By exploiting a probabilistic Bayesian learning framework, the sparse Bayesian learning provides the accurate model for the blind equalization, which typically utilizes fewer basis functions than the equalizer based on the popular and state-of-the-art support vector machine (SVM) - blind SVM equalizer. Simulation results show that the proposed blind RVM equalizer provides improved performances in terms of complexity, stability and intersymbol interference (ISI) and bit error rate (BER) in a linear channel and a similar BER performance in a nonlinear channel compared to the blind SVM equalizer.