Robust Maximum Correntropy Criterion Subband Adaptive Filter Algorithm for Impulsive Noise and Noisy Input

Abstract

Although the known maximum total generalized correntropy (MTGC) and generalized maximum blakezisserman total correntropy (GMBZTC) algorithms can maintain good performance under the errors-in-variables (EIV) model disrupted by generalized Gaussian noise, their requirement for manual adjustment of parameters is excessive, greatly increasing the practical difficulty of use. To solve this problem, the total arctangent based on logical distance metric (TACLDM) algorithm is proposed by utilizing the advantage of few parameters in logical distance metric (LDM) theory and the convergence behavior is improved by the arctangent function. Compared with other competing algorithms, the TACLDM algorithm not only has fewer parameters, but also has better robustness to generalized Gaussian noise and significantly reduces the steady-state error. Furthermore, the analysis of the algorithm in the generalized Gaussian noise environment is analyzed in detail in this paper. Finally, computer simulations demonstrate the outstanding performance of the TACLDM algorithm and the rigorous theoretical deduction in this paper.

Exponential stability of time‐delay systems with flexible delayed impulse

“…Remark The description of the impulsive system in this paper is different from the ones based on the Schwartz–Sobolev theory of distributions [41, 42]. The latter impulsive system is reduced to a special class of nonlinear Volterra integral equations, and impulse control is a solution of multiple integral equations.…”

Conjugate Gradient Adaptive Learning with Tukey's Biweight M-Estimate

“…Such MCC method is also an M-estimator in essence [112]. It has revealed its effectiveness for non-Gaussian signal processing and has been successfully applied in many applications [113], [114], [115]. Note that the above-mentioned algorithms rely on higher-order moments and stochastic gradient (SG) methods to obtain good performance in impulsive noise.…”

Tracking Analysis of Maximum Versoria Criterion Based Adaptive Filter

“…To improve the robustness against non-Gaussian signals such as impulsive noise, other criteria beyond MSE should be considered. Recently, information-theoretic adaptive filters have been developed to optimize the filter coefficients based on information-theoretic measures, such as mutual information, error entropy [3]- [6], correntropy [7]- [11] and risk sensitive loss [12]- [15]. These filters can effectively capture higher-order moments of data, which allows them to better adapt to the changes in signal conditions and improve the performance of signal processing tasks.…”