Xiaoping Chen

TL;DR: The adapt-then-combine diffusion LMS algorithm is modified by applying the sign operation to the error signals at all agents to develop a diffusion sign-error LMS (DSE-LMS) algorithm, which is robust against impulsive interferences and analyzed for Gaussian inputs and contaminated Gaussian noise based on Price's theorem.

TL;DR: Two variants of the sign subband adaptive filter, called the affine projection SSAF (AP-SSAF) and the proportionate SSAf (P-S SAF), are proposed to solve the problem of convergence rate and robustness against impulsive interference.

TL;DR: This paper analyzes the steady-state mean-square error (MSE) of regularized NSAFs based on the derivation of a variable regularization matrix NSAF (VRM-NSAF).

TL;DR: This paper complements previous works by achieving this analysis with the same noise model of Diffusion sign-error LMS of mean-square stability condition and second-order steady-state performance for both theoretical understanding and practical implementation of the algorithm.

TL;DR: In this paper, an affine projection sign subband adaptive filter (APSSAF) is proposed, which updates the tap-weight vector based on several previous input vectors to maintain the robustness against impulsive interference, and also increases the convergence rate.