Blind deconvolution by modified Bussgang algorithm
Simone Fiori, Aurelio Uncini, Francesco Piazza · 2003
The 'Bussgang' is one of the best known blind deconvolution algorithms. It requires prior knowledge of the source statistics as well as the deconvolution noise characteristics. In this paper we present a first attempt for making the algorithm 'more blind' by replacing the original Bayesian estimator with a flexible parametric function whose parameters adapt through time. To assess the effectiveness of the proposed method, computer simulations are also presented and discussed.