Comments on "A Recursive Least M-Estimate Algorithm for Robust Adaptive Filtering in Impulsive Noise: Fast Algorithm and Convergence Performance Analysis

Abstract

recent paper [S. C. Chan and Y. X. Zou, A Recursive Least M-Estimate Algorithm for Robust Adaptive Filtering in Impulsive Noise: Fast Algorithm and Convergence Performance Analysis, IEEE Transactions on Signal Processing, vol. 57, no. 1, Jaunary 2008] studied the behavior of a recursive least M-estimate (RLM) adaptive filtering algorithm in an additive impulsive noise environment. The mean and mean-square behavior of the algorithm was analyzed using a joint Gaussian assumption for the input and the error signal. This note points out that this assumption contradicts the probability model for the impulsive noise [contaminated Gaussian (CG) noise]. Hence, the analytic results presented in Chan and Zou are of limited interest.