Kernel Adaptive Filters With Feedback Based on Maximum Correntropy

This paper presents novel kernel adaptive filters with feedback, namely, kernel recursive maximum correntropy with multiple feedback (KRMC-MF) and its simplified version, a linear recurrent kernel online learning algorithm based on maximum correntropy criterion (LRKOL-MCC). In LRKOL-MCC and KRMC-MF,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shiyuan Wang, Lujuan Dang, Wanli Wang, Guobing Qian, Chi K. Tse
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2018
Materias:	Kernel adaptive filters maximum correntropy minimum mean square error feedback structure convergence Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/5751cd9eb4e14107834ee836091e3196
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5751cd9eb4e14107834ee836091e3196
record_format	dspace
spelling	oai:doaj.org-article:5751cd9eb4e14107834ee836091e31962021-11-12T00:01:37ZKernel Adaptive Filters With Feedback Based on Maximum Correntropy2169-353610.1109/ACCESS.2018.2808218https://doaj.org/article/5751cd9eb4e14107834ee836091e31962018-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/8295208/https://doaj.org/toc/2169-3536This paper presents novel kernel adaptive filters with feedback, namely, kernel recursive maximum correntropy with multiple feedback (KRMC-MF) and its simplified version, a linear recurrent kernel online learning algorithm based on maximum correntropy criterion (LRKOL-MCC). In LRKOL-MCC and KRMC-MF, single output and multiple outputs based on single delay are utilized to construct their feedback structure, respectively. Compared with the minimum mean square error criterion, the maximum correntropy criterion (MCC) adopted by LRKOL-MCC and KRMC-MF captures higher order statistics of errors. The proposed filters are, therefore, robust against outliers. Therefore, the past information can be reused to improve filtering performance in terms of the steady-state mean square error. The convergence characteristics of the filter parameters in LRKOL-MCC and KRMC-MF are also derived. Simulations on chaotic time-series prediction and nonlinear regression illustrate the desirable accuracy and robustness of the proposed filters.Shiyuan WangLujuan DangWanli WangGuobing QianChi K. TseIEEEarticleKernel adaptive filtersmaximum correntropyminimum mean square errorfeedback structureconvergenceElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 6, Pp 10540-10552 (2018)
institution	DOAJ
collection	DOAJ
language	EN
topic	Kernel adaptive filters maximum correntropy minimum mean square error feedback structure convergence Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Kernel adaptive filters maximum correntropy minimum mean square error feedback structure convergence Electrical engineering. Electronics. Nuclear engineering TK1-9971 Shiyuan Wang Lujuan Dang Wanli Wang Guobing Qian Chi K. Tse Kernel Adaptive Filters With Feedback Based on Maximum Correntropy
description	This paper presents novel kernel adaptive filters with feedback, namely, kernel recursive maximum correntropy with multiple feedback (KRMC-MF) and its simplified version, a linear recurrent kernel online learning algorithm based on maximum correntropy criterion (LRKOL-MCC). In LRKOL-MCC and KRMC-MF, single output and multiple outputs based on single delay are utilized to construct their feedback structure, respectively. Compared with the minimum mean square error criterion, the maximum correntropy criterion (MCC) adopted by LRKOL-MCC and KRMC-MF captures higher order statistics of errors. The proposed filters are, therefore, robust against outliers. Therefore, the past information can be reused to improve filtering performance in terms of the steady-state mean square error. The convergence characteristics of the filter parameters in LRKOL-MCC and KRMC-MF are also derived. Simulations on chaotic time-series prediction and nonlinear regression illustrate the desirable accuracy and robustness of the proposed filters.
format	article
author	Shiyuan Wang Lujuan Dang Wanli Wang Guobing Qian Chi K. Tse
author_facet	Shiyuan Wang Lujuan Dang Wanli Wang Guobing Qian Chi K. Tse
author_sort	Shiyuan Wang
title	Kernel Adaptive Filters With Feedback Based on Maximum Correntropy
title_short	Kernel Adaptive Filters With Feedback Based on Maximum Correntropy
title_full	Kernel Adaptive Filters With Feedback Based on Maximum Correntropy
title_fullStr	Kernel Adaptive Filters With Feedback Based on Maximum Correntropy
title_full_unstemmed	Kernel Adaptive Filters With Feedback Based on Maximum Correntropy
title_sort	kernel adaptive filters with feedback based on maximum correntropy
publisher	IEEE
publishDate	2018
url	https://doaj.org/article/5751cd9eb4e14107834ee836091e3196
work_keys_str_mv	AT shiyuanwang kerneladaptivefilterswithfeedbackbasedonmaximumcorrentropy AT lujuandang kerneladaptivefilterswithfeedbackbasedonmaximumcorrentropy AT wanliwang kerneladaptivefilterswithfeedbackbasedonmaximumcorrentropy AT guobingqian kerneladaptivefilterswithfeedbackbasedonmaximumcorrentropy AT chiktse kerneladaptivefilterswithfeedbackbasedonmaximumcorrentropy
_version_	1718431348972060672

Kernel Adaptive Filters With Feedback Based on Maximum Correntropy

Ejemplares similares