Regularized LTI system identification in the presence of outliers: A variational EM approach

Regularized system identification of linear time invariant systems in the presence of outliers is investigated. The finite impulse response (fir) model and the Gaussian scale mixture are chosen to be the system model and the noise model, respectively. Two special cases of the noise model are conside...

Full description

Saved in:
Bibliographic Details
Published in:Automatica (Oxford) Vol. 121; p. 109152
Main Authors: Lindfors, Martin, Chen, Tianshi
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.11.2020
Subjects:
ISSN:0005-1098, 1873-2836, 1873-2836
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Regularized system identification of linear time invariant systems in the presence of outliers is investigated. The finite impulse response (fir) model and the Gaussian scale mixture are chosen to be the system model and the noise model, respectively. Two special cases of the noise model are considered: the well-known Student’s t distribution and a proposed G-confluent distribution. Both the fir model parameter and the latent variables in the noise model are treated as parameters of our statistical model and moreover, the scale of the noise variance is treated as a hyper-parameter besides the hyper-parameters used to parameterize the priors of the impulse response and the latent variables. Then a variational expectation–maximization algorithm is proposed for inference of the parameters and hyper-parameters of the statistical model, and the algorithm is guaranteed to converge to a stationary point. Monte Carlo numerical simulations show that when the relative size of outliers is small, the proposed approach performs comparably to a state-of-the-art method and when the relative size of outliers and/or the occurrence probability of outliers is large, the proposed approach outperforms the state-of-the-art method.
AbstractList Regularized system identification of linear time invariant systems in the presence of outliers is investigated. The finite impulse response (FIR) model and the Gaussian scale mixture are chosen to be the system model and the noise model, respectively. Two special cases of the noise model are considered: the well-known Students t distribution and a proposed G-confluent distribution. Both the FIR model parameter and the latent variables in the noise model are treated as parameters of our statistical model and moreover, the scale of the noise variance is treated as a hyper-parameter besides the hyper-parameters used to parameterize the priors of the impulse response and the latent variables. Then a variational expectation-maximization algorithm is proposed for inference of the parameters and hyper-parameters of the statistical model, and the algorithm is guaranteed to converge to a stationary point. Monte Carlo numerical simulations show that when the relative size of outliers is small, the proposed approach performs comparably to a state-of-the-art method and when the relative size of outliers and/or the occurrence probability of outliers is large, the proposed approach outperforms the state-of-the-art method. (C) 2020 Elsevier Ltd. All rights reserved.
Regularized system identification of linear time invariant systems in the presence of outliers is investigated. The finite impulse response (fir) model and the Gaussian scale mixture are chosen to be the system model and the noise model, respectively. Two special cases of the noise model are considered: the well-known Student’s t distribution and a proposed G-confluent distribution. Both the fir model parameter and the latent variables in the noise model are treated as parameters of our statistical model and moreover, the scale of the noise variance is treated as a hyper-parameter besides the hyper-parameters used to parameterize the priors of the impulse response and the latent variables. Then a variational expectation–maximization algorithm is proposed for inference of the parameters and hyper-parameters of the statistical model, and the algorithm is guaranteed to converge to a stationary point. Monte Carlo numerical simulations show that when the relative size of outliers is small, the proposed approach performs comparably to a state-of-the-art method and when the relative size of outliers and/or the occurrence probability of outliers is large, the proposed approach outperforms the state-of-the-art method.
ArticleNumber 109152
Author Lindfors, Martin
Chen, Tianshi
Author_xml – sequence: 1
  givenname: Martin
  surname: Lindfors
  fullname: Lindfors, Martin
  email: martin.lindfors@liu.se
  organization: Division of Automatic Control, Department of Electrical Engineering, Linköping University, Linköping, 58183, Sweden
– sequence: 2
  givenname: Tianshi
  surname: Chen
  fullname: Chen, Tianshi
  email: tschen@cuhk.edu.cn
  organization: School of Data Science and Shenzhen Research Institute of Big Data, The Chinese University of Hong Kong, Shenzhen, 518172, China
BackLink https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-170620$$DView record from Swedish Publication Index (Linköpings universitet)
BookMark eNqNkN1KAzEQRoNUsK2-Q15ga36629QLodaqhYog1SshpJtJm7LdLEm2Up_ebSsK3ujVkMn3HZjTQa3SlYAQpqRHCc0u1z1VR7dR0eaqxwjbr4c0ZSeoTcWAJ0zwrIXahJA0aX7EGeqEsG6efSpYG709w7IulLcfoPFsPsVhFyJssNVQRmsaaLSuxLbEcQW48hCgzAE7g10dCws-XOER3jaAQ1AVePKIVVV5p_LVOTo1qghw8TW76OVuMh8_JLOn--l4NEtynmYxYcaYdME5BW1gwEUfFDFcLYbc0OFCk1QxnRnOAKjuCwKZEik3QASnRhOS8S5KjtzwDlW9kJW3G-V30ikrb-3rSDq_lIWtJR2QjJEmL4753LsQPJjvBiVyb1Wu5Y9Vubcqj1ab6vWvam7j4fTolS3-A7g5AqARsm0EypDbvVNtPeRRamf_hnwChMmeeg
CitedBy_id crossref_primary_10_1016_j_oceaneng_2025_122303
crossref_primary_10_1109_JAS_2024_125109
crossref_primary_10_1016_j_automatica_2022_110489
crossref_primary_10_1016_j_automatica_2022_110687
crossref_primary_10_1109_TSMC_2022_3151761
crossref_primary_10_1109_TSMC_2024_3362067
crossref_primary_10_1109_TAC_2023_3338462
crossref_primary_10_1109_TAC_2022_3195151
crossref_primary_10_1002_acs_3497
crossref_primary_10_1016_j_automatica_2021_109682
Cites_doi 10.1016/j.automatica.2018.04.015
10.3182/20140824-6-ZA-1003.01587
10.1137/0111030
10.1109/MSP.2008.929620
10.1016/j.automatica.2009.10.031
10.1109/TSP.2010.2080271
10.1016/j.automatica.2018.04.035
10.1016/j.automatica.2012.05.026
10.1016/j.automatica.2017.12.039
10.1109/TAC.2016.2582642
10.1109/TAC.2014.2351851
10.1080/03610927708827533
10.1016/j.automatica.2014.01.001
10.1016/j.automatica.2015.05.012
10.1080/01621459.1976.10480376
10.1016/j.automatica.2013.03.030
10.1016/j.neucom.2005.02.016
10.1016/j.automatica.2016.01.036
ContentType Journal Article
Copyright 2020 Elsevier Ltd
Copyright_xml – notice: 2020 Elsevier Ltd
DBID AAYXX
CITATION
ADTPV
AOWAS
DG8
DOI 10.1016/j.automatica.2020.109152
DatabaseName CrossRef
SwePub
SwePub Articles
SWEPUB Linköpings universitet
DatabaseTitle CrossRef
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1873-2836
ExternalDocumentID oai_DiVA_org_liu_170620
10_1016_j_automatica_2020_109152
S0005109820303502
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
1B1
1~.
1~5
23N
3R3
4.4
457
4G.
5GY
5VS
6TJ
7-5
71M
8P~
9JN
9JO
AAAKF
AAAKG
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AARIN
AAXUO
ABDEX
ABFNM
ABFRF
ABJNI
ABMAC
ABUCO
ABXDB
ABYKQ
ACBEA
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ADBBV
ADEZE
ADIYS
ADMUD
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFFNX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHPGS
AI.
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
APLSM
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
HAMUX
HLZ
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
K-O
KOM
LG9
LY7
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
RXW
SBC
SDF
SDG
SDP
SES
SET
SEW
SPC
SPCBC
SSB
SSD
SST
SSZ
T5K
T9H
TAE
TN5
VH1
WH7
WUQ
X6Y
XFK
XPP
ZMT
~G-
77I
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABUFD
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ADTPV
AOWAS
DG8
ID FETCH-LOGICAL-c356t-2fff5b331edfe7384ea0f3ab93f19bd05a2d6f32ee1d480e6a853fe0831fd0063
ISICitedReferencesCount 13
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000571446000010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0005-1098
1873-2836
IngestDate Tue Nov 04 16:41:34 EST 2025
Tue Nov 18 22:39:59 EST 2025
Sat Nov 29 07:01:21 EST 2025
Fri Feb 23 02:50:04 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Outliers
Variational expectation–maximization
Kernel-based regularization methods
System identification
WASP_publications
Variational expectation-maximization
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c356t-2fff5b331edfe7384ea0f3ab93f19bd05a2d6f32ee1d480e6a853fe0831fd0063
ParticipantIDs swepub_primary_oai_DiVA_org_liu_170620
crossref_primary_10_1016_j_automatica_2020_109152
crossref_citationtrail_10_1016_j_automatica_2020_109152
elsevier_sciencedirect_doi_10_1016_j_automatica_2020_109152
PublicationCentury 2000
PublicationDate 2020-11-01
PublicationDateYYYYMMDD 2020-11-01
PublicationDate_xml – month: 11
  year: 2020
  text: 2020-11-01
  day: 01
PublicationDecade 2020
PublicationTitle Automatica (Oxford)
PublicationYear 2020
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References (pp. 3646–3655).
Hawkins (b16) 1980
Bottegal, Aravkin, Hjalmarsson, Pillonetto (b8) 2016; 67
Bottegal, Aravkin, Hjalmarsson, Pillonetto (b7) 2014; 47
Beal, Ghahramani (b2) 2003; 7
Pillonetto, De Nicolao (b24) 2010; 46
Bishop (b5) 2006
Tzikas, Likas, Galatsanos (b27) 2008; 25
Green (b15) 1976; 71
Pillonetto, Chiuso (b23) 2015; 58
Holland, Welsch (b17) 1977; 6
Bickel, Doksum (b4) 2001
Chen (b10) 2018; 90
Wu (b29) 1983
Neal, Hinton (b22) 1998
Wang, Yixin, Kucukelbir, Alp, & Blei, David M. (2017). Robust probabilistic modeling with Bayesian data reweighting. In
Abramowitz, Stegun (b1) 1964
Pillonetto, Dinuzzo, Chen, De Nicolao, Ljung (b25) 2014; 50
Bertsekas (b3) 1999
Marquardt (b20) 1963; 11
Ljung (b19) 1999
Björck (b6) 1996
Chen, Ljung (b12) 2013; 49
Tipping, Lawrence (b26) 2005; 69
Mu, Chen, Ljung (b21) 2018; 94
Chen, Andersen, Ljung, Chiuso, Pillonetto (b11) 2013; 59
Huber (b18) 2011
Christmas, Everson (b14) 2011; 59
Carli, Chen, Ljung (b9) 2017; 62
Chen, Ohlsson, Ljung (b13) 2012; 48
Zorzi, Chiuso (b30) 2018; 94
Tzikas (10.1016/j.automatica.2020.109152_b27) 2008; 25
Pillonetto (10.1016/j.automatica.2020.109152_b23) 2015; 58
Pillonetto (10.1016/j.automatica.2020.109152_b25) 2014; 50
Pillonetto (10.1016/j.automatica.2020.109152_b24) 2010; 46
Abramowitz (10.1016/j.automatica.2020.109152_b1) 1964
Bickel (10.1016/j.automatica.2020.109152_b4) 2001
Marquardt (10.1016/j.automatica.2020.109152_b20) 1963; 11
Chen (10.1016/j.automatica.2020.109152_b11) 2013; 59
Chen (10.1016/j.automatica.2020.109152_b10) 2018; 90
Beal (10.1016/j.automatica.2020.109152_b2) 2003; 7
Holland (10.1016/j.automatica.2020.109152_b17) 1977; 6
Mu (10.1016/j.automatica.2020.109152_b21) 2018; 94
10.1016/j.automatica.2020.109152_b28
Chen (10.1016/j.automatica.2020.109152_b12) 2013; 49
Bottegal (10.1016/j.automatica.2020.109152_b7) 2014; 47
Hawkins (10.1016/j.automatica.2020.109152_b16) 1980
Huber (10.1016/j.automatica.2020.109152_b18) 2011
Chen (10.1016/j.automatica.2020.109152_b13) 2012; 48
Björck (10.1016/j.automatica.2020.109152_b6) 1996
Neal (10.1016/j.automatica.2020.109152_b22) 1998
Zorzi (10.1016/j.automatica.2020.109152_b30) 2018; 94
Bottegal (10.1016/j.automatica.2020.109152_b8) 2016; 67
Christmas (10.1016/j.automatica.2020.109152_b14) 2011; 59
Carli (10.1016/j.automatica.2020.109152_b9) 2017; 62
Ljung (10.1016/j.automatica.2020.109152_b19) 1999
Bishop (10.1016/j.automatica.2020.109152_b5) 2006
Wu (10.1016/j.automatica.2020.109152_b29) 1983
Green (10.1016/j.automatica.2020.109152_b15) 1976; 71
Bertsekas (10.1016/j.automatica.2020.109152_b3) 1999
Tipping (10.1016/j.automatica.2020.109152_b26) 2005; 69
References_xml – year: 2001
  ident: b4
  article-title: Mathematical statistics: basic ideas and selected topics (vol I)
– year: 1996
  ident: b6
  article-title: Numerical methods for least squares problems
– volume: 46
  start-page: 81
  year: 2010
  end-page: 93
  ident: b24
  article-title: A new kernel-based approach for linear system identification
  publication-title: Automatica
– year: 1980
  ident: b16
  article-title: Identification of outliers (vol. 11)
– year: 2006
  ident: b5
  article-title: Pattern recognition and machine learning
– year: 1999
  ident: b3
  article-title: Nonlinear programming
– volume: 90
  start-page: 109
  year: 2018
  end-page: 122
  ident: b10
  article-title: On kernel design for regularized system identification
  publication-title: Automatica
– reference: (pp. 3646–3655).
– volume: 25
  start-page: 131
  year: 2008
  end-page: 146
  ident: b27
  article-title: The variational approximation for Bayesian inference
  publication-title: IEEE Signal Processing Magazine
– volume: 6
  start-page: 813
  year: 1977
  end-page: 827
  ident: b17
  article-title: Robust regression using iteratively reweighted least-squares
  publication-title: Communications in Statistics-theory and Methods
– volume: 94
  start-page: 125
  year: 2018
  end-page: 137
  ident: b30
  article-title: The harmonic analysis of kernel functions
  publication-title: Automatica
– volume: 50
  start-page: 657
  year: 2014
  end-page: 682
  ident: b25
  article-title: Kernel methods in system identification, machine learning and function estimation: A survey
  publication-title: Automatica
– volume: 67
  start-page: 114
  year: 2016
  end-page: 126
  ident: b8
  article-title: Robust EM kernel-based methods for linear system identification
  publication-title: Automatica
– volume: 58
  start-page: 106
  year: 2015
  end-page: 117
  ident: b23
  article-title: Tuning complexity in regularized kernel-based regression and linear system identification: The robustness of the marginal likelihood estimator
  publication-title: Automatica
– start-page: 1248
  year: 2011
  end-page: 1251
  ident: b18
  article-title: Robust statistics
  publication-title: International Encyclopedia of Statistical Science
– volume: 47
  start-page: 1073
  year: 2014
  end-page: 1078
  ident: b7
  article-title: Outlier robust system identification: a Bayesian kernel-based approach
  publication-title: IFAC Proceedings Volumes
– reference: Wang, Yixin, Kucukelbir, Alp, & Blei, David M. (2017). Robust probabilistic modeling with Bayesian data reweighting. In
– volume: 62
  start-page: 1471
  year: 2017
  end-page: 1477
  ident: b9
  article-title: Maximum entropy kernels for system identification
  publication-title: IEEE Transactions on Automatic Control
– volume: 71
  start-page: 502
  year: 1976
  end-page: 505
  ident: b15
  article-title: Outlier-prone and outlier-resistant distributions
  publication-title: Journal of the American Statistical Association
– year: 1964
  ident: b1
  article-title: Handbook of mathematical functions: with formulas, graphs, and mathematical tables (vol. 55)
– volume: 94
  start-page: 381
  year: 2018
  end-page: 395
  ident: b21
  article-title: On asymptotic properties of hyperparameter estimators for kernel-based regularization methods
  publication-title: Automatica
– start-page: 95
  year: 1983
  end-page: 103
  ident: b29
  article-title: On the convergence properties of the EM algorithm
  publication-title: The Annals of statistics
– volume: 48
  start-page: 1525
  year: 2012
  end-page: 1535
  ident: b13
  article-title: On the estimation of transfer functions, regularizations and Gaussian processes – revisited
  publication-title: Automatica
– volume: 59
  start-page: 2933
  year: 2013
  end-page: 2945
  ident: b11
  article-title: System identification via sparse multiple kernel-based regularization using sequential convex optimization techniques
  publication-title: IEEE Transactions on Automatic Control
– volume: 69
  start-page: 123
  year: 2005
  end-page: 141
  ident: b26
  article-title: Variational inference for Student-
  publication-title: Neurocomputing
– volume: 11
  start-page: 431
  year: 1963
  end-page: 441
  ident: b20
  article-title: An algorithm for least-squares estimation of nonlinear parameters
  publication-title: Journal of the Society for Industrial and Applied Mathematics
– volume: 49
  start-page: 2213
  year: 2013
  end-page: 2220
  ident: b12
  article-title: Implementation of algorithms for tuning parameters in regularized least squares problems in system identification
  publication-title: Automatica
– year: 1999
  ident: b19
  article-title: System identification - theory for the user
  publication-title: Wiley encyclopedia of electrical and electronics engineering
– volume: 7
  start-page: 453
  year: 2003
  end-page: 464
  ident: b2
  article-title: The variational Bayesian EM algorithm for incomplete data: with application to scoring graphical model structures
  publication-title: Bayesian Statistics
– volume: 59
  start-page: 48
  year: 2011
  end-page: 57
  ident: b14
  article-title: Robust autoregression: Student-
  publication-title: IEEE Transactions on Signal Processing
– start-page: 355
  year: 1998
  end-page: 368
  ident: b22
  article-title: A view of the EM algorithm that justifies incremental, sparse, and other variants
  publication-title: Learning in Graphical Models
– volume: 94
  start-page: 125
  year: 2018
  ident: 10.1016/j.automatica.2020.109152_b30
  article-title: The harmonic analysis of kernel functions
  publication-title: Automatica
  doi: 10.1016/j.automatica.2018.04.015
– volume: 47
  start-page: 1073
  issue: 3
  year: 2014
  ident: 10.1016/j.automatica.2020.109152_b7
  article-title: Outlier robust system identification: a Bayesian kernel-based approach
  publication-title: IFAC Proceedings Volumes
  doi: 10.3182/20140824-6-ZA-1003.01587
– volume: 11
  start-page: 431
  issue: 2
  year: 1963
  ident: 10.1016/j.automatica.2020.109152_b20
  article-title: An algorithm for least-squares estimation of nonlinear parameters
  publication-title: Journal of the Society for Industrial and Applied Mathematics
  doi: 10.1137/0111030
– volume: 25
  start-page: 131
  issue: 6
  year: 2008
  ident: 10.1016/j.automatica.2020.109152_b27
  article-title: The variational approximation for Bayesian inference
  publication-title: IEEE Signal Processing Magazine
  doi: 10.1109/MSP.2008.929620
– volume: 46
  start-page: 81
  issue: 1
  year: 2010
  ident: 10.1016/j.automatica.2020.109152_b24
  article-title: A new kernel-based approach for linear system identification
  publication-title: Automatica
  doi: 10.1016/j.automatica.2009.10.031
– start-page: 95
  year: 1983
  ident: 10.1016/j.automatica.2020.109152_b29
  article-title: On the convergence properties of the EM algorithm
  publication-title: The Annals of statistics
– volume: 59
  start-page: 48
  issue: 1
  year: 2011
  ident: 10.1016/j.automatica.2020.109152_b14
  article-title: Robust autoregression: Student-t innovations using variational Bayes
  publication-title: IEEE Transactions on Signal Processing
  doi: 10.1109/TSP.2010.2080271
– year: 1999
  ident: 10.1016/j.automatica.2020.109152_b19
  article-title: System identification - theory for the user
– volume: 94
  start-page: 381
  year: 2018
  ident: 10.1016/j.automatica.2020.109152_b21
  article-title: On asymptotic properties of hyperparameter estimators for kernel-based regularization methods
  publication-title: Automatica
  doi: 10.1016/j.automatica.2018.04.035
– year: 1999
  ident: 10.1016/j.automatica.2020.109152_b3
– year: 1996
  ident: 10.1016/j.automatica.2020.109152_b6
– ident: 10.1016/j.automatica.2020.109152_b28
– volume: 48
  start-page: 1525
  issue: 8
  year: 2012
  ident: 10.1016/j.automatica.2020.109152_b13
  article-title: On the estimation of transfer functions, regularizations and Gaussian processes – revisited
  publication-title: Automatica
  doi: 10.1016/j.automatica.2012.05.026
– year: 1980
  ident: 10.1016/j.automatica.2020.109152_b16
– volume: 90
  start-page: 109
  year: 2018
  ident: 10.1016/j.automatica.2020.109152_b10
  article-title: On kernel design for regularized system identification
  publication-title: Automatica
  doi: 10.1016/j.automatica.2017.12.039
– volume: 62
  start-page: 1471
  issue: 3
  year: 2017
  ident: 10.1016/j.automatica.2020.109152_b9
  article-title: Maximum entropy kernels for system identification
  publication-title: IEEE Transactions on Automatic Control
  doi: 10.1109/TAC.2016.2582642
– volume: 59
  start-page: 2933
  issue: 11
  year: 2013
  ident: 10.1016/j.automatica.2020.109152_b11
  article-title: System identification via sparse multiple kernel-based regularization using sequential convex optimization techniques
  publication-title: IEEE Transactions on Automatic Control
  doi: 10.1109/TAC.2014.2351851
– volume: 6
  start-page: 813
  issue: 9
  year: 1977
  ident: 10.1016/j.automatica.2020.109152_b17
  article-title: Robust regression using iteratively reweighted least-squares
  publication-title: Communications in Statistics-theory and Methods
  doi: 10.1080/03610927708827533
– volume: 50
  start-page: 657
  issue: 3
  year: 2014
  ident: 10.1016/j.automatica.2020.109152_b25
  article-title: Kernel methods in system identification, machine learning and function estimation: A survey
  publication-title: Automatica
  doi: 10.1016/j.automatica.2014.01.001
– year: 2006
  ident: 10.1016/j.automatica.2020.109152_b5
– start-page: 1248
  year: 2011
  ident: 10.1016/j.automatica.2020.109152_b18
  article-title: Robust statistics
– volume: 58
  start-page: 106
  year: 2015
  ident: 10.1016/j.automatica.2020.109152_b23
  article-title: Tuning complexity in regularized kernel-based regression and linear system identification: The robustness of the marginal likelihood estimator
  publication-title: Automatica
  doi: 10.1016/j.automatica.2015.05.012
– volume: 71
  start-page: 502
  issue: 354
  year: 1976
  ident: 10.1016/j.automatica.2020.109152_b15
  article-title: Outlier-prone and outlier-resistant distributions
  publication-title: Journal of the American Statistical Association
  doi: 10.1080/01621459.1976.10480376
– start-page: 355
  year: 1998
  ident: 10.1016/j.automatica.2020.109152_b22
  article-title: A view of the EM algorithm that justifies incremental, sparse, and other variants
– volume: 7
  start-page: 453
  year: 2003
  ident: 10.1016/j.automatica.2020.109152_b2
  article-title: The variational Bayesian EM algorithm for incomplete data: with application to scoring graphical model structures
  publication-title: Bayesian Statistics
– volume: 49
  start-page: 2213
  issue: 7
  year: 2013
  ident: 10.1016/j.automatica.2020.109152_b12
  article-title: Implementation of algorithms for tuning parameters in regularized least squares problems in system identification
  publication-title: Automatica
  doi: 10.1016/j.automatica.2013.03.030
– volume: 69
  start-page: 123
  issue: 1
  year: 2005
  ident: 10.1016/j.automatica.2020.109152_b26
  article-title: Variational inference for Student-t models: Robust Bayesian interpolation and generalised component analysis
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2005.02.016
– year: 1964
  ident: 10.1016/j.automatica.2020.109152_b1
– year: 2001
  ident: 10.1016/j.automatica.2020.109152_b4
– volume: 67
  start-page: 114
  year: 2016
  ident: 10.1016/j.automatica.2020.109152_b8
  article-title: Robust EM kernel-based methods for linear system identification
  publication-title: Automatica
  doi: 10.1016/j.automatica.2016.01.036
SSID ssj0004182
Score 2.4214814
Snippet Regularized system identification of linear time invariant systems in the presence of outliers is investigated. The finite impulse response (fir) model and the...
Regularized system identification of linear time invariant systems in the presence of outliers is investigated. The finite impulse response (FIR) model and the...
SourceID swepub
crossref
elsevier
SourceType Open Access Repository
Enrichment Source
Index Database
Publisher
StartPage 109152
SubjectTerms Kernel-based regularization methods
Outliers
System identification
Variational expectation–maximization
Title Regularized LTI system identification in the presence of outliers: A variational EM approach
URI https://dx.doi.org/10.1016/j.automatica.2020.109152
https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-170620
Volume 121
WOSCitedRecordID wos000571446000010&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-2836
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004182
  issn: 0005-1098
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELag5QAHVF6iQJEPiAsKSuIkduAU0a0oaiuElmoPSJbjR0lVZVf7qFb8esaPZINopeXAJVpZa6_lz5n9ZjTzDUJvMpnVaUIkuKmURpnQOqplnkQpIUCXmVapawd0fkLPzthkUn4NbdkXrp0AbVu2Xpez_wo1jAHYtnT2H-DuF4UB-AygwxNgh-dWwH9z3eXnzS-gkifj46DV_K5RIS9IDNMbZ676SLrAgc0Nco2xXbH6NSzRBQpHp732-JDMVqvl1Cm-CidauvZ58n1kwbr7MLQIJUGdxrfLJfDGbgx3c_GzGUYewM1M-shDZ02tiqnvIt1bU1_w_Jdl9kGCS5uXE7b23q5p5awSr2F7g-71YXNe8en8gl81K26FftL4LtpNaV6CDd6tjkeTL5si2IR5afiwKetpM0oi4E9FSOHyiX037-BWXjIUkHWkY7yHHgZvAVce5Ufojm4fowcDDckn6McAbwx4Y483_hNv3LQY8MYd3nhqcIf3B1zhAdp4dIo7tJ-i70ej8afPUWiZEUmSF8soNcbkNSGJVkZTwjItYkNEXRKTlLWKc5GqwpBU60RlLNaFALpmtG03Z5Slq8_QTjtt9XOEpS7qOFOaCqEzxWSt4c8RXmtWCy0pyfYR7Q6My6Anb9uaXPEucfCSb46a26Pm_qj3UdLPnHlNlS3mfOww4YEbes7H4YJtMfuth7H_vVtu14ttv_gS3d-8Eq_QznK-0gfonrxeNov563A3fwOb-Zbn
linkProvider Elsevier
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=Regularized+LTI+system+identification+in+the+presence+of+outliers%3A+A+variational+EM+approach&rft.jtitle=Automatica+%28Oxford%29&rft.au=Lindfors%2C+Martin&rft.au=Chen%2C+Tianshi&rft.date=2020-11-01&rft.issn=0005-1098&rft.volume=121&rft_id=info:doi/10.1016%2Fj.automatica.2020.109152&rft.externalDocID=oai_DiVA_org_liu_170620
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0005-1098&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0005-1098&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0005-1098&client=summon