Stopping and restarting adaptive updates to recursive least-squares lattice adaptive filtering algorithms

Jake Gunther; Wang Song; Tamal Bose

doi:10.1109/SMCALS.2006.250683

Stopping and restarting adaptive updates to recursive least-squares lattice adaptive filtering algorithms

Jake Gunther, Wang Song, Tamal Bose

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

This paper reports several observations about stopping and restarting adaptive updates to recursive least-squares lattice (LSL) adaptive filtering algorithms. When updates are stopped, the adaptive filter becomes a fixed filter. Simulation examples demonstrate that large output error results from abruptly stopping or restarting adaptive updates. A remedy to the problem is to transition the adaptive updates to an off or on state gradually by driving the unknown system and the adaptive filter simultaneously to the all zero state. This is accomplished by setting the input signal to zero. The length (in number of samples) of the transition period is equal to the length of the adaptive filter. Simulation examples are given to illustrate the problem and the effectiveness of the proposed remedy.

Original language	English (US)
Title of host publication	2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006
Pages	1-6
Number of pages	6
DOIs	https://doi.org/10.1109/SMCALS.2006.250683
State	Published - 2006
Externally published	Yes
Event	2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006 - Logan, Utah, United States Duration: Jul 24 2006 → Jul 26 2006

Publication series

Name	2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006

Other

Other	2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006
Country/Territory	United States
City	Logan, Utah
Period	7/24/06 → 7/26/06

ASJC Scopus subject areas

Computational Mathematics
Education

Access to Document

10.1109/SMCALS.2006.250683

Cite this

Gunther, J., Song, W., & Bose, T. (2006). Stopping and restarting adaptive updates to recursive least-squares lattice adaptive filtering algorithms. In 2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006 (pp. 1-6). Article 4016753 (2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006). https://doi.org/10.1109/SMCALS.2006.250683

Stopping and restarting adaptive updates to recursive least-squares lattice adaptive filtering algorithms. / Gunther, Jake; Song, Wang; Bose, Tamal.
2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006. 2006. p. 1-6 4016753 (2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Gunther, J, Song, W & Bose, T 2006, Stopping and restarting adaptive updates to recursive least-squares lattice adaptive filtering algorithms. in 2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006., 4016753, 2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006, pp. 1-6, 2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006, Logan, Utah, United States, 7/24/06. https://doi.org/10.1109/SMCALS.2006.250683

@inproceedings{a806d74f7b1047eb9437aec0d69e535e,

title = "Stopping and restarting adaptive updates to recursive least-squares lattice adaptive filtering algorithms",

abstract = "This paper reports several observations about stopping and restarting adaptive updates to recursive least-squares lattice (LSL) adaptive filtering algorithms. When updates are stopped, the adaptive filter becomes a fixed filter. Simulation examples demonstrate that large output error results from abruptly stopping or restarting adaptive updates. A remedy to the problem is to transition the adaptive updates to an off or on state gradually by driving the unknown system and the adaptive filter simultaneously to the all zero state. This is accomplished by setting the input signal to zero. The length (in number of samples) of the transition period is equal to the length of the adaptive filter. Simulation examples are given to illustrate the problem and the effectiveness of the proposed remedy.",

author = "Jake Gunther and Wang Song and Tamal Bose",

year = "2006",

doi = "10.1109/SMCALS.2006.250683",

language = "English (US)",

isbn = "1424401666",

series = "2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006",

pages = "1--6",

booktitle = "2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006",

note = "2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006 ; Conference date: 24-07-2006 Through 26-07-2006",

}

TY - GEN

T1 - Stopping and restarting adaptive updates to recursive least-squares lattice adaptive filtering algorithms

AU - Gunther, Jake

AU - Song, Wang

AU - Bose, Tamal

PY - 2006

Y1 - 2006

N2 - This paper reports several observations about stopping and restarting adaptive updates to recursive least-squares lattice (LSL) adaptive filtering algorithms. When updates are stopped, the adaptive filter becomes a fixed filter. Simulation examples demonstrate that large output error results from abruptly stopping or restarting adaptive updates. A remedy to the problem is to transition the adaptive updates to an off or on state gradually by driving the unknown system and the adaptive filter simultaneously to the all zero state. This is accomplished by setting the input signal to zero. The length (in number of samples) of the transition period is equal to the length of the adaptive filter. Simulation examples are given to illustrate the problem and the effectiveness of the proposed remedy.

AB - This paper reports several observations about stopping and restarting adaptive updates to recursive least-squares lattice (LSL) adaptive filtering algorithms. When updates are stopped, the adaptive filter becomes a fixed filter. Simulation examples demonstrate that large output error results from abruptly stopping or restarting adaptive updates. A remedy to the problem is to transition the adaptive updates to an off or on state gradually by driving the unknown system and the adaptive filter simultaneously to the all zero state. This is accomplished by setting the input signal to zero. The length (in number of samples) of the transition period is equal to the length of the adaptive filter. Simulation examples are given to illustrate the problem and the effectiveness of the proposed remedy.

UR - http://www.scopus.com/inward/record.url?scp=34250704255&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250704255&partnerID=8YFLogxK

U2 - 10.1109/SMCALS.2006.250683

DO - 10.1109/SMCALS.2006.250683

M3 - Conference contribution

AN - SCOPUS:34250704255

SN - 1424401666

SN - 9781424401666

T3 - 2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006

SP - 1

EP - 6

BT - 2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006

T2 - 2006 IEEE Mountain Workshop on Adaptive and Learning Systems, SMCals 2006

Y2 - 24 July 2006 through 26 July 2006

ER -

Stopping and restarting adaptive updates to recursive least-squares lattice adaptive filtering algorithms

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this