A variable step size algorithm using evolution strategies for adaptive filtering

S. C. Ng; C. Y. Chung; S. H. Leung; A. Luk

doi:10.1109/CEC.1999.781980

A variable step size algorithm using evolution strategies for adaptive filtering

S. C. Ng
, C. Y. Chung
, S. H. Leung
, A. Luk

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

5 Citations (Scopus)

Abstract

A new variable step size scheme for the least-mean-square (LMS) algorithm is proposed in this paper. The idea is basically a kind of evolutionary strategies. The step size candidates are generated and evaluated by calculating a square error measure based on a priori and a posteriori errors. The fittest candidate is selected for subsequent adaptation. The composition of the square error measure is regulated according to the mean square error so as to provide fast converging and tracking capability. The convergence performance is significantly improved and is less sensitive to eigenvalue spread. © 1999 IEEE.

Original language	English
Title of host publication	Proceedings of the 1999 Congress on Evolutionary Computation, CEC 1999
Publisher	IEEE
Pages	542-545
ISBN (Print)	0-7803-5536-9
DOIs	https://doi.org/10.1109/CEC.1999.781980
Publication status	Published - Jul 1999
Event	1999 Congress on Evolutionary Computation (CEC 1999) - Mayflower Hotel, Washington, United States Duration: 6 Jul 1999 → 9 Jul 1999 https://ieeexplore.ieee.org/document/781900

Conference

Conference	1999 Congress on Evolutionary Computation (CEC 1999)
Place	United States
City	Washington
Period	6/07/99 → 9/07/99
Internet address	https://ieeexplore.ieee.org/document/781900

Access Output

10.1109/CEC.1999.781980

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{69d1cc8fdf0f415e96816a088ab33600,

title = "A variable step size algorithm using evolution strategies for adaptive filtering",

abstract = "A new variable step size scheme for the least-mean-square (LMS) algorithm is proposed in this paper. The idea is basically a kind of evolutionary strategies. The step size candidates are generated and evaluated by calculating a square error measure based on a priori and a posteriori errors. The fittest candidate is selected for subsequent adaptation. The composition of the square error measure is regulated according to the mean square error so as to provide fast converging and tracking capability. The convergence performance is significantly improved and is less sensitive to eigenvalue spread. {\textcopyright} 1999 IEEE.",

author = "Ng, \{S. C.\} and Chung, \{C. Y.\} and Leung, \{S. H.\} and A. Luk",

year = "1999",

month = jul,

doi = "10.1109/CEC.1999.781980",

language = "English",

isbn = "0-7803-5536-9",

pages = "542--545",

booktitle = "Proceedings of the 1999 Congress on Evolutionary Computation, CEC 1999",

publisher = "IEEE",

address = "United States",

note = "1999 Congress on Evolutionary Computation (CEC 1999) ; Conference date: 06-07-1999 Through 09-07-1999",

url = "https://ieeexplore.ieee.org/document/781900",

}

Ng, SC, Chung, CY, Leung, SH & Luk, A 1999, A variable step size algorithm using evolution strategies for adaptive filtering. in Proceedings of the 1999 Congress on Evolutionary Computation, CEC 1999. IEEE, pp. 542-545, 1999 Congress on Evolutionary Computation (CEC 1999), Washington, District of Columbia, United States, 6/07/99. https://doi.org/10.1109/CEC.1999.781980

A variable step size algorithm using evolution strategies for adaptive filtering. / Ng, S. C.; Chung, C. Y.; Leung, S. H. et al.
Proceedings of the 1999 Congress on Evolutionary Computation, CEC 1999. IEEE, 1999. p. 542-545.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - A variable step size algorithm using evolution strategies for adaptive filtering

AU - Ng, S. C.

AU - Chung, C. Y.

AU - Leung, S. H.

AU - Luk, A.

PY - 1999/7

Y1 - 1999/7

N2 - A new variable step size scheme for the least-mean-square (LMS) algorithm is proposed in this paper. The idea is basically a kind of evolutionary strategies. The step size candidates are generated and evaluated by calculating a square error measure based on a priori and a posteriori errors. The fittest candidate is selected for subsequent adaptation. The composition of the square error measure is regulated according to the mean square error so as to provide fast converging and tracking capability. The convergence performance is significantly improved and is less sensitive to eigenvalue spread. © 1999 IEEE.

AB - A new variable step size scheme for the least-mean-square (LMS) algorithm is proposed in this paper. The idea is basically a kind of evolutionary strategies. The step size candidates are generated and evaluated by calculating a square error measure based on a priori and a posteriori errors. The fittest candidate is selected for subsequent adaptation. The composition of the square error measure is regulated according to the mean square error so as to provide fast converging and tracking capability. The convergence performance is significantly improved and is less sensitive to eigenvalue spread. © 1999 IEEE.

UR - https://www.scopus.com/pages/publications/0005374732

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0005374732&origin=recordpage

U2 - 10.1109/CEC.1999.781980

DO - 10.1109/CEC.1999.781980

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 0-7803-5536-9

SP - 542

EP - 545

BT - Proceedings of the 1999 Congress on Evolutionary Computation, CEC 1999

PB - IEEE

T2 - 1999 Congress on Evolutionary Computation (CEC 1999)

Y2 - 6 July 1999 through 9 July 1999

ER -

A variable step size algorithm using evolution strategies for adaptive filtering

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this