ℓ1-regularized recursive total least squares based sparse system identification for the error-in-variables

In this paper an ℓ 1 -regularized recursive total least squares (RTLS) algorithm is considered for the sparse system identification. Although recursive least squares (RLS) has been successfully applied in sparse system identification, the estimation performance in RLS based algorithms becomes worse,...

Full description

Saved in:
Bibliographic Details
Published in:SpringerPlus Vol. 5; no. 1
Main Authors: Lim, Jun-seok, Pang, Hee-Suk
Format: Journal Article
Language:English
Published: Cham Springer International Publishing 31.08.2016
Subjects:
ISSN:2193-1801
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract In this paper an ℓ 1 -regularized recursive total least squares (RTLS) algorithm is considered for the sparse system identification. Although recursive least squares (RLS) has been successfully applied in sparse system identification, the estimation performance in RLS based algorithms becomes worse, when both input and output are contaminated by noise (the error-in-variables problem). We proposed an algorithm to handle the error-in-variables problem. The proposed ℓ 1 -RTLS algorithm is an RLS like iteration using the ℓ 1 regularization. The proposed algorithm not only gives excellent performance but also reduces the required complexity through the effective inversion matrix handling. Simulations demonstrate the superiority of the proposed ℓ 1 -regularized RTLS for the sparse system identification setting.
AbstractList In this paper an ℓ 1 -regularized recursive total least squares (RTLS) algorithm is considered for the sparse system identification. Although recursive least squares (RLS) has been successfully applied in sparse system identification, the estimation performance in RLS based algorithms becomes worse, when both input and output are contaminated by noise (the error-in-variables problem). We proposed an algorithm to handle the error-in-variables problem. The proposed ℓ 1 -RTLS algorithm is an RLS like iteration using the ℓ 1 regularization. The proposed algorithm not only gives excellent performance but also reduces the required complexity through the effective inversion matrix handling. Simulations demonstrate the superiority of the proposed ℓ 1 -regularized RTLS for the sparse system identification setting.
Author Pang, Hee-Suk
Lim, Jun-seok
Author_xml – sequence: 1
  givenname: Jun-seok
  surname: Lim
  fullname: Lim, Jun-seok
  email: jslim@sejong.ac.kr
  organization: Department of Electronics Engineering, Sejong University
– sequence: 2
  givenname: Hee-Suk
  surname: Pang
  fullname: Pang, Hee-Suk
  organization: Department of Electronics Engineering, Sejong University
BookMark eNotkE1OwzAUhC0EEqX0AOx8AYOfkzjOElX8SZXYwNqyk-fiKiTFz60Ea27ADTkJqcpsZjGjGem7YKfDOCBjVyCvAYy-oVJKXQoJWhSgpNAnbKagKQQYCedsQbSRk3QNZS1nrP_9_gGRcL3rXYpf2PGE7S5R3CPPY3Y979FR5vSxcwmJe0dTh7YuEXL6pIzvPHY45Bhi63IcBx7GxPMbckxpTCIOYj8tO98jXbKz4HrCxb_P2ev93cvyUayeH56WtytB0JgsOuNrj62SpvSoq9qbUEFwrmqDKVrQplRYd7KaQgwKPDbBtcrVvglQtrUp5kwdd2mb4rDGZDfjLg3TpQVpD5jsEZOdMNkDJquLPwlwYzo
Cites_doi 10.1109/TSP.2004.837408
10.1049/iet-spr.2010.0083
10.1109/LSP.2009.2024736
10.1109/LSP.2011.2159373
10.1016/j.sigpro.2011.02.013
10.1109/TSP.2011.2109956
10.1109/78.705421
10.1137/0717073
10.1109/TSP.2010.2048103
10.1109/78.275601
10.1016/j.laa.2012.10.032
10.2514/1.6276
10.1002/acs.2635
10.1109/TSP.2010.2046897
10.1016/j.dsp.2015.02.018
10.1109/TSP.2015.2405492
10.1109/TSP.2014.2301135
ContentType Journal Article
Copyright The Author(s) 2016
Copyright_xml – notice: The Author(s) 2016
DBID C6C
DOI 10.1186/s40064-016-3120-6
DatabaseName Springer Nature OA Free Journals
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Sciences (General)
EISSN 2193-1801
ExternalDocumentID 10_1186_s40064_016_3120_6
GroupedDBID -A0
0R~
4.4
40G
53G
5VS
7X2
7XC
8CJ
8FE
8FG
8FH
AAKKN
ABDBF
ABEEZ
ABJCF
ACACY
ACGFO
ACGFS
ACIWK
ACPRK
ACUHS
ACULB
ADBBV
ADINQ
ADRAZ
AEGXH
AENEX
AEUYN
AFGXO
AFKRA
AFRAH
AHBYD
AHSBF
AHYZX
AIAGR
ALMA_UNASSIGNED_HOLDINGS
AMKLP
AOIJS
ARAPS
ATCPS
BAWUL
BBNVY
BENPR
BGLVJ
BHPHI
BKSAR
C24
C6C
CCPQU
CZ9
D1I
D1J
D1K
DIK
EBS
EJD
GROUPED_DOAJ
GX1
HCIFZ
HH5
HYE
HZ~
K6-
K6V
K7-
KB.
KC.
KQ8
L6V
LK5
LK8
M0K
M48
M7P
M7R
M7S
M~E
OK1
P62
PATMY
PCBAR
PDBOC
PGMZT
PTHSS
PYCSY
RNS
RPM
RSV
SHS
SOJ
ID FETCH-LOGICAL-s198t-d8b7bec2084be657b8f51faa5cf83c16842e7d05be6ef21be9fac2a7b9f14c783
IEDL.DBID C24
ISICitedReferencesCount 6
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000391794900002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Fri Feb 21 02:35:35 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords RLS
Convex regularization
TLS
1-norm
Adaptive filter
Sparsity
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-s198t-d8b7bec2084be657b8f51faa5cf83c16842e7d05be6ef21be9fac2a7b9f14c783
OpenAccessLink https://link.springer.com/10.1186/s40064-016-3120-6
ParticipantIDs springer_journals_10_1186_s40064_016_3120_6
PublicationCentury 2000
PublicationDate 2016-08-31
PublicationDateYYYYMMDD 2016-08-31
PublicationDate_xml – month: 08
  year: 2016
  text: 2016-08-31
  day: 31
PublicationDecade 2010
PublicationPlace Cham
PublicationPlace_xml – name: Cham
PublicationTitle SpringerPlus
PublicationTitleAbbrev SpringerPlus
PublicationYear 2016
Publisher Springer International Publishing
Publisher_xml – name: Springer International Publishing
References Soijer (CR20) 2004; 27
Davila (CR8) 1994; 42
Arablouei, Werner, Dogancay (CR2) 2014; 62
Dunne, Williamson (CR11) 2004; 52
Golub, Van Loan (CR15) 1980; 17
CR6
Feng, Bao, Jiao (CR14) 1998; 46
Arablouei, Dogancay, Werner (CR3) 2015; 63
Choi, Lim, Sung (CR7) 2005; 3496
Eksioglu (CR12) 2011; 5
Angelosante, Bazerque, Giannakis (CR1) 2010; 58
Babadi, Kalouptsidis, Tarokh (CR5) 2010; 58
Dumitrescu (CR9) 2013; 438
CR10
Moon, Stirling (CR19) 2000
Tanc (CR21) 2015; 40
Arablouei (CR4) 2016
Gu, Jin, Mei (CR16) 2009; 16
Kalouptsidis, Mileounis, Babadi, Tarokh (CR17) 2011; 91
Eksioglu, Tanc (CR13) 2011; 18
Lim, Pang (CR18) 2016; 30
Zhu, Leus, Giannakis (CR22) 2011; 59
References_xml – volume: 52
  start-page: 3345
  year: 2004
  end-page: 3356
  ident: CR11
  article-title: Analysis of gradient algorithms for TLS-based adaptive IIR filters
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2004.837408
– volume: 5
  start-page: 480
  year: 2011
  end-page: 487
  ident: CR12
  article-title: Sparsity regularized RLS adaptive filtering
  publication-title: IET Signal Process
  doi: 10.1049/iet-spr.2010.0083
– year: 2000
  ident: CR19
  publication-title: Mathematical methods and algorithm for signal processing
– volume: 16
  start-page: 774
  year: 2009
  end-page: 777
  ident: CR16
  article-title: Norm constraint LMS algorithm for sparse system identification
  publication-title: IEEE Signal Process Lett
  doi: 10.1109/LSP.2009.2024736
– volume: 18
  start-page: 470
  year: 2011
  end-page: 473
  ident: CR13
  article-title: RLS algorithm with convex regularization
  publication-title: IEEE Signal Process Lett
  doi: 10.1109/LSP.2011.2159373
– volume: 91
  start-page: 1910
  year: 2011
  end-page: 1919
  ident: CR17
  article-title: Adaptive algorithms for sparse system identification
  publication-title: Signal Process
  doi: 10.1016/j.sigpro.2011.02.013
– volume: 59
  start-page: 2002
  year: 2011
  end-page: 2016
  ident: CR22
  article-title: Sparsity-cognizant total least-squares for perturbed compressive sampling
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2011.2109956
– volume: 46
  start-page: 2122
  year: 1998
  end-page: 2130
  ident: CR14
  article-title: Total least mean squares algorithm
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/78.705421
– volume: 17
  start-page: 883
  year: 1980
  end-page: 893
  ident: CR15
  article-title: An analysis of the total least squares problem
  publication-title: SIAM J Numer Anal
  doi: 10.1137/0717073
– volume: 58
  start-page: 4013
  year: 2010
  end-page: 4025
  ident: CR5
  article-title: SPARLS: the sparse RLS algorithm
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2010.2048103
– volume: 42
  start-page: 268
  year: 1994
  end-page: 280
  ident: CR8
  article-title: An efficient recursive total least squares algorithm for FIR adaptive filtering
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/78.275601
– ident: CR10
– volume: 438
  start-page: 2661
  year: 2013
  end-page: 2674
  ident: CR9
  article-title: Sparse total least squares: analysis and greedy algorithms
  publication-title: Linear Algebra Appl
  doi: 10.1016/j.laa.2012.10.032
– volume: 27
  start-page: 501
  year: 2004
  end-page: 503
  ident: CR20
  article-title: Sequential computation of total least-squares parameter estimates
  publication-title: J Guidance
  doi: 10.2514/1.6276
– volume: 30
  start-page: 664
  year: 2016
  end-page: 673
  ident: CR18
  article-title: Mixed norm regularized recursive total least squares for group sparse system identification
  publication-title: Int J Adapt Control Signal Process
  doi: 10.1002/acs.2635
– volume: 58
  start-page: 3436
  year: 2010
  end-page: 3447
  ident: CR1
  article-title: Online adaptive estimation of sparse signals: where RLS meets the l1-norm
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2010.2046897
– ident: CR6
– volume: 3496
  start-page: 558
  year: 2005
  end-page: 565
  ident: CR7
  article-title: An efficient recursive total least squares algorithm for training multilayer feedforward neural networks
  publication-title: LNCS
– volume: 40
  start-page: 176
  year: 2015
  end-page: 180
  ident: CR21
  article-title: Sparsity regularized recursive total least-squares
  publication-title: Digital Signal Process
  doi: 10.1016/j.dsp.2015.02.018
– volume: 63
  start-page: 1941
  year: 2015
  end-page: 1949
  ident: CR3
  article-title: Recursive total least-squares algorithm based on inverse power method and dichotomous coordinate-descent iterations
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2015.2405492
– year: 2016
  ident: CR4
  article-title: Fast reconstruction algorithm for perturbed compressive sensing based on total least-squares and proximal splitting
  publication-title: Signal Process
– volume: 62
  start-page: 1256
  year: 2014
  end-page: 1264
  ident: CR2
  article-title: Analysis of the gradient-decent total least-squares algorithm
  publication-title: IEEE Trans Signal Process
  doi: 10.1109/TSP.2014.2301135
SSID ssj0000671470
Score 2.0722866
Snippet In this paper an ℓ 1 -regularized recursive total least squares (RTLS) algorithm is considered for the sparse system identification. Although recursive least...
SourceID springer
SourceType Publisher
SubjectTerms Engineering
Humanities and Social Sciences
multidisciplinary
Science
Science (multidisciplinary)
Title ℓ1-regularized recursive total least squares based sparse system identification for the error-in-variables
URI https://link.springer.com/article/10.1186/s40064-016-3120-6
Volume 5
WOSCitedRecordID wos000391794900002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  databaseCode: M~E
  dateStart: 20120101
  customDbUrl:
  isFulltext: true
  eissn: 2193-1801
  dateEnd: 99991231
  titleUrlDefault: https://road.issn.org
  omitProxy: false
  ssIdentifier: ssj0000671470
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  databaseCode: P5Z
  dateStart: 20120301
  customDbUrl:
  isFulltext: true
  eissn: 2193-1801
  dateEnd: 20180228
  titleUrlDefault: https://search.proquest.com/hightechjournals
  omitProxy: false
  ssIdentifier: ssj0000671470
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Agricultural Science Database
  databaseCode: M0K
  dateStart: 20120301
  customDbUrl:
  isFulltext: true
  eissn: 2193-1801
  dateEnd: 20180228
  titleUrlDefault: https://search.proquest.com/agriculturejournals
  omitProxy: false
  ssIdentifier: ssj0000671470
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Biological Science Database
  databaseCode: M7P
  dateStart: 20120301
  customDbUrl:
  isFulltext: true
  eissn: 2193-1801
  dateEnd: 20180228
  titleUrlDefault: http://search.proquest.com/biologicalscijournals
  omitProxy: false
  ssIdentifier: ssj0000671470
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database (ProQuest)
  databaseCode: K7-
  dateStart: 20120301
  customDbUrl:
  isFulltext: true
  eissn: 2193-1801
  dateEnd: 20180228
  titleUrlDefault: http://search.proquest.com/compscijour
  omitProxy: false
  ssIdentifier: ssj0000671470
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Earth, Atmospheric & Aquatic Science Database
  databaseCode: PCBAR
  dateStart: 20120301
  customDbUrl:
  isFulltext: true
  eissn: 2193-1801
  dateEnd: 20180228
  titleUrlDefault: https://search.proquest.com/eaasdb
  omitProxy: false
  ssIdentifier: ssj0000671470
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Engineering Database
  databaseCode: M7S
  dateStart: 20120301
  customDbUrl:
  isFulltext: true
  eissn: 2193-1801
  dateEnd: 20180228
  titleUrlDefault: http://search.proquest.com
  omitProxy: false
  ssIdentifier: ssj0000671470
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Environmental Science Database
  databaseCode: PATMY
  dateStart: 20120301
  customDbUrl:
  isFulltext: true
  eissn: 2193-1801
  dateEnd: 20180228
  titleUrlDefault: http://search.proquest.com/environmentalscience
  omitProxy: false
  ssIdentifier: ssj0000671470
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Materials Science Database
  databaseCode: KB.
  dateStart: 20120301
  customDbUrl:
  isFulltext: true
  eissn: 2193-1801
  dateEnd: 20180228
  titleUrlDefault: http://search.proquest.com/materialsscijournals
  omitProxy: false
  ssIdentifier: ssj0000671470
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  databaseCode: BENPR
  dateStart: 20120301
  customDbUrl:
  isFulltext: true
  eissn: 2193-1801
  dateEnd: 20180228
  titleUrlDefault: https://www.proquest.com/central
  omitProxy: false
  ssIdentifier: ssj0000671470
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: SpringerOpen
  databaseCode: C24
  dateStart: 20121201
  customDbUrl:
  isFulltext: true
  eissn: 2193-1801
  dateEnd: 20171231
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  omitProxy: false
  ssIdentifier: ssj0000671470
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV07T8MwELagZYABaAHxrDwwgJBFnTiJM0LViqmqEEjdIscPKRJKhZ12YOYf8A_5JdiuIyHBArOTU3SXe_m-uwPgUmIexywmiCgikHMBiLFcoFyKjMshj5liftlENp3S-TyfhT5u06Ld25Kkt9RerWl6a4hznzb1Ta3dcDnPJugmmOYOxzcKLQ7B_GKStRXMX9_8UfX0zmSy96_P2Ae7IXaEd2th98CGrPtg59tEwT7oBV018CoMlL4-AC-f7x8Yab91XldvUkDtbtkdcB02Cxt9wxe3wQea16XrRoLOswloTY02Eq5HPcNKBFiRlyS0oS60oSOUWi80qmq0spRdF5Y5BM-T8dPoAYUtC8jgnDZI0DKzgoyGlJQyTbKSqgQrxhKuaMyxq9PJTAwTeyhVhEuZK8YjlpW5woRnND4CnXpRy2MAIyK4kqK054JE3NLAIoktoZTFmFN-Am5anhZBVUzhsxCaFmvGFg5x5hhbpKd_evoMbEdOKP669xx0Gr2UF2CLr5rK6AHo3o-ns8eB_1W-AM7Xv8I
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEA5aBfWgtiq-zcGDIsFmN7ubPUqxVKzFQ4XelmweUChbTNoePPsP_If-EpM0C4Je9JzdYZnZeWW-mQHgUmIexywmiCgikHMBiLFcoFyKjMs2j5liftlENhjQ0Sh_Dn3cpka71yVJb6m9WtP01hDnPm3qm1q74XKeVbDmJq84HF8ntDgE84tJVlcwf33zR9XTO5Puzr8-Yxdsh9gR3i2F3QQrsmqBrW8TBVugGXTVwKswUPp6D0w-3z8w0n7rvB6_SQG1u2V3wHU4m9roG07cBh9oXueuGwk6zyagNTXaSLgc9QzHIsCKvCShDXWhDR2h1Hqq0bhCC0vZdWGZffDSvR92eihsWUAG53SGBC0zK8ioTUkp0yQrqUqwYizhisYcuzqdzEQ7sYdSRbiUuWI8YlmZK0x4RuMD0KimlTwEMCKCKylKey5IxC0NLJLYEkpZjDnlR-Cm5mkRVMUUPguhabFkbOEQZ46xRXr8p6cvwEZv-NQv-g-DxxOwGTkB-avfU9CY6bk8A-t8MRsbfe5_ly_PzsEN
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpR1NS8MwNOgU0YO6qfhtDh4UCVvatE2PMh2KMnZQ2K2k-YDC6DTpdvDsP_Af-ktM2gwEvYjntI_wvl_eFwDnEvMwZCFBRBGBnAlAjKUCpVIkXPZ4yBSrl00kwyEdj9OR33NqFtXui5Rk09PgpjSVVfdFqEbEadw1xJlSGwbHVoe4-GcZrLiElGPxvm938KoYk2SRzfz1zx8Z0NqwDLb-faVtsOl9SnjdMEEbLMmyAza-TRrsgLaXYQMv_KDpyx0w-Xz_wEjX2-h18SYF1O713RW0w2pqvXI4cZt9oHmduS4l6CyegFYFaSNhMwIaFsKXG9UUhtYFhtalhFLrqUZFieYWsuvOMrvgeXD71L9DfvsCMjilFRI0TyyBgx4luYyjJKcqwoqxiCsacuzydzIRvcgeShXgXKaK8YAleaow4QkN90CrnJZyH8CACK6kyO25IAG3MLCIQgsoZiHmlB-AqwV-My9CJqujExpnDWIzV4nmEJvFh3_6-gysjW4G2eP98OEIrAeOPvWL8DFoVXomT8Aqn1eF0ac153wBNpfJ8Q
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E2%84%931-regularized+recursive+total+least+squares+based+sparse+system+identification+for+the+error-in-variables&rft.jtitle=SpringerPlus&rft.au=Lim%2C+Jun-seok&rft.au=Pang%2C+Hee-Suk&rft.date=2016-08-31&rft.pub=Springer+International+Publishing&rft.eissn=2193-1801&rft.volume=5&rft.issue=1&rft_id=info:doi/10.1186%2Fs40064-016-3120-6&rft.externalDocID=10_1186_s40064_016_3120_6