Recursive constrained generalized maximum correntropy algorithms for adaptive filtering

Zhao, J; Zhang, JA; Li, Q; Zhang, H; Wang, X

Recursive constrained generalized maximum correntropy algorithms for adaptive filtering

Zhao, J Zhang, JA Li, Q Zhang, H Wang, X

Permalink

Publisher:: ELSEVIER
Publication Type:: Journal Article
Citation:: Signal Processing, 2022, 199
Issue Date:: 2022-10-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

The embargo period expires on 1 Oct 2024

Adobe PDF

Download Accepted versionAdobe PDF (5.91 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Zhao, J
dc.contributor.author	Zhang, JA
dc.contributor.author	Li, Q
dc.contributor.author	Zhang, H
dc.contributor.author	Wang, X
dc.date.accessioned	2023-01-16T04:34:41Z
dc.date.available	2023-01-16T04:34:41Z
dc.date.issued	2022-10-01
dc.identifier.citation	Signal Processing, 2022, 199
dc.identifier.issn	0165-1684
dc.identifier.issn	1872-7557
dc.identifier.uri	http://hdl.handle.net/10453/165009
dc.description.abstract	Thanks to the ability of preventing the accumulation of errors, constrained adaptive filtering (CAF) algorithms have been widely applied. However, in practice, non-Gaussian noise may significantly degrade the filtering performance of CAFs derived from the second-order signal statistics. In this paper, we propose several constrained generalized maximum correntropy (CGMC) algorithms to overcome this problem, inspired by the robustness and flexibility of GMC to non-Gaussian noises. We first introduce a CGMC algorithm based on the gradient method. To improve its convergence rate with correlated inputs, we further propose a recursive CGMC (RCGMC) algorithm. For RCGMC, we conduct the convergence analysis, and characterize the theoretical transient mean square deviation (MSD) performance. Furthermore, we derive a low-complexity version of RCGMC by using the weighting method and the leading dichotomous coordinate descent (DCD) algorithm. Simulation results demonstrate the effectiveness of our proposed algorithms in non-Gaussian noise environment, and the consistency between the analytical and simulation results.
dc.language	English
dc.publisher	ELSEVIER
dc.relation.ispartof	Signal Processing
dc.relation.isbasedon	10.1016/j.sigpro.2022.108611
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject	08 Information and Computing Sciences, 09 Engineering, 10 Technology
dc.subject.classification	Networking & Telecommunications
dc.title	Recursive constrained generalized maximum correntropy algorithms for adaptive filtering
dc.type	Journal Article
utslib.citation.volume	199
utslib.for	08 Information and Computing Sciences
utslib.for	09 Engineering
utslib.for	10 Technology
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	open_access	*
utslib.copyright.embargo	2024-10-01T00:00:00+1000Z
dc.date.updated	2023-01-16T04:34:38Z
pubs.publication-status	Published
pubs.volume	199

Abstract:

Thanks to the ability of preventing the accumulation of errors, constrained adaptive filtering (CAF) algorithms have been widely applied. However, in practice, non-Gaussian noise may significantly degrade the filtering performance of CAFs derived from the second-order signal statistics. In this paper, we propose several constrained generalized maximum correntropy (CGMC) algorithms to overcome this problem, inspired by the robustness and flexibility of GMC to non-Gaussian noises. We first introduce a CGMC algorithm based on the gradient method. To improve its convergence rate with correlated inputs, we further propose a recursive CGMC (RCGMC) algorithm. For RCGMC, we conduct the convergence analysis, and characterize the theoretical transient mean square deviation (MSD) performance. Furthermore, we derive a low-complexity version of RCGMC by using the weighting method and the leading dichotomous coordinate descent (DCD) algorithm. Simulation results demonstrate the effectiveness of our proposed algorithms in non-Gaussian noise environment, and the consistency between the analytical and simulation results.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/165009