Low-complexity Graph Sampling With Noise and Signal Reconstruction via Neumann Series

Graph sampling addresses the problem of selecting a node subset in a graph to collect samples, so that a K-bandlimited signal can be reconstructed with high fidelity. Assuming an independent and identically distributed (i.i.d.) noise model, minimizing the expected mean square error (MMSE) leads to t...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on signal processing Ročník 67; číslo 21; s. 5511 - 5526
Hlavní autoři: Wang, Fen, Cheung, Gene, Wang, Yongchao
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.11.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:1053-587X, 1941-0476
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Graph sampling addresses the problem of selecting a node subset in a graph to collect samples, so that a K-bandlimited signal can be reconstructed with high fidelity. Assuming an independent and identically distributed (i.i.d.) noise model, minimizing the expected mean square error (MMSE) leads to the known A-optimality criterion for graph sampling, which is expensive to compute and difficult to optimize. In this paper, we propose an augmented objective based on Neumann series that well approximates the A-optimal criterion and is amenable to greedy optimization. Specifically, we show that a shifted A-optimal criterion can be equivalently written as a function of an ideal low-pass (LP) graph filter, which in turn can be approximated efficiently via fast graph Fourier transform (FGFT). Minimizing the new objective, we select nodes greedily without large matrix inversions using a matrix inverse lemma. Further, for the dynamic subset sampling case where node availability varies across time, we propose an extended sampling strategy that replaces offline samples one-by-one in the selected set. For signal reconstruction, we propose an accompanied biased signal recovery strategy that reuses the approximated filter from sampling. Experiments show that our reconstruction is more robust to large noise than the least squares (LS) solution, and our sampling strategy far outperforms several existing schemes.
AbstractList Graph sampling addresses the problem of selecting a node subset in a graph to collect samples, so that a [Formula Omitted]-bandlimited signal can be reconstructed with high fidelity. Assuming an independent and identically distributed (i.i.d.) noise model, minimizing the expected mean square error (MMSE) leads to the known A-optimality criterion for graph sampling, which is expensive to compute and difficult to optimize. In this paper, we propose an augmented objective based on Neumann series that well approximates the A-optimal criterion and is amenable to greedy optimization. Specifically, we show that a shifted A-optimal criterion can be equivalently written as a function of an ideal low-pass (LP) graph filter, which in turn can be approximated efficiently via fast graph Fourier transform (FGFT). Minimizing the new objective, we select nodes greedily without large matrix inversions using a matrix inverse lemma. Further, for the dynamic subset sampling case where node availability varies across time, we propose an extended sampling strategy that replaces offline samples one-by-one in the selected set. For signal reconstruction, we propose an accompanied biased signal recovery strategy that reuses the approximated filter from sampling. Experiments show that our reconstruction is more robust to large noise than the least squares (LS) solution, and our sampling strategy far outperforms several existing schemes.
Graph sampling addresses the problem of selecting a node subset in a graph to collect samples, so that a K-bandlimited signal can be reconstructed with high fidelity. Assuming an independent and identically distributed (i.i.d.) noise model, minimizing the expected mean square error (MMSE) leads to the known A-optimality criterion for graph sampling, which is expensive to compute and difficult to optimize. In this paper, we propose an augmented objective based on Neumann series that well approximates the A-optimal criterion and is amenable to greedy optimization. Specifically, we show that a shifted A-optimal criterion can be equivalently written as a function of an ideal low-pass (LP) graph filter, which in turn can be approximated efficiently via fast graph Fourier transform (FGFT). Minimizing the new objective, we select nodes greedily without large matrix inversions using a matrix inverse lemma. Further, for the dynamic subset sampling case where node availability varies across time, we propose an extended sampling strategy that replaces offline samples one-by-one in the selected set. For signal reconstruction, we propose an accompanied biased signal recovery strategy that reuses the approximated filter from sampling. Experiments show that our reconstruction is more robust to large noise than the least squares (LS) solution, and our sampling strategy far outperforms several existing schemes.
Author Wang, Fen
Cheung, Gene
Wang, Yongchao
Author_xml – sequence: 1
  givenname: Fen
  orcidid: 0000-0002-9109-4086
  surname: Wang
  fullname: Wang, Fen
  email: fenwang@stu.xidian.edu.cn
  organization: State Key Laboratory of Integrated Services Network, Xidian University, Xi'an, China
– sequence: 2
  givenname: Gene
  orcidid: 0000-0002-5571-4137
  surname: Cheung
  fullname: Cheung, Gene
  email: genec@yorku.ca
  organization: Department of EECS, York University, 4700 Keele Street, Toronto, Canada
– sequence: 3
  givenname: Yongchao
  orcidid: 0000-0002-0640-4140
  surname: Wang
  fullname: Wang, Yongchao
  email: ychwang@mail.xidian.edu.cn
  organization: State Key Laboratory of Integrated Services Network, Xidian University, Xi'an, China
BookMark eNp9kM9LwzAUx4NMcJveBS8Bz50vSZs2Rxk6hTHFbuitZGm6ZWzJTFp1_70tEw8evLz3eHw_78d3gHrWWY3QJYERISBu5vnziAIRIypiIFScoD4RMYkgTnmvrSFhUZKlb2doEMIGgMSx4H20mLrPSLndfqu_TH3AEy_3a5zLtmHsCr-aeo1nzgSNpS1xblZWbvGLVs6G2jeqNs7iDyPxTDc7aS3OtTc6nKPTSm6DvvjJQ7S4v5uPH6Lp0-RxfDuNFBWk7qJkCVFLBlVSKc5VVWnBSxJXTJWijZxxAEooSWRSkYwsuRBMa1bSEhRjQ3R9nLv37r3RoS42rvHtiaGgVGQpcEqhVcFRpbwLweuq2Huzk_5QECg684rWvKIzr_gxr0X4H0SZWnbf1l6a7X_g1RE0WuvfPVlGUwaUfQP58n4a
CODEN ITPRED
CitedBy_id crossref_primary_10_1049_iet_com_2020_0670
crossref_primary_10_1109_JIOT_2024_3484996
crossref_primary_10_1109_TVT_2021_3109603
crossref_primary_10_1007_s11432_021_3370_4
crossref_primary_10_1109_TSP_2020_2981202
crossref_primary_10_1016_j_dsp_2020_102782
crossref_primary_10_1016_j_sigpro_2020_107847
crossref_primary_10_1109_TSP_2020_2988784
crossref_primary_10_1186_s13634_022_00836_9
crossref_primary_10_1016_j_sigpro_2023_109263
crossref_primary_10_1109_TSIPN_2023_3261504
crossref_primary_10_1109_TSP_2022_3199664
crossref_primary_10_1007_s11760_025_04782_5
crossref_primary_10_1109_MSP_2020_3016908
crossref_primary_10_1016_j_dsp_2024_104728
crossref_primary_10_1109_TSIPN_2025_3540714
crossref_primary_10_1109_TSP_2020_3002607
crossref_primary_10_1109_TSP_2021_3054995
crossref_primary_10_1109_TSP_2023_3305079
crossref_primary_10_1016_j_neunet_2022_01_014
crossref_primary_10_1109_TPAMI_2024_3524180
crossref_primary_10_1109_TSP_2023_3284364
Cites_doi 10.1137/1.9781611971446
10.1109/CDC.2010.5717225
10.1109/MSP.2014.2329213
10.1109/GLOCOM.2017.8254798
10.1109/TSP.2017.2773429
10.1109/TSP.2018.2835384
10.1016/j.acha.2010.04.005
10.1109/JPROC.2018.2799702
10.1109/ICASSP.2019.8682200
10.1016/B978-0-444-50617-7.50010-0
10.1109/TSP.2015.2460224
10.1109/TSP.2016.2546233
10.1109/TSP.2017.2755586
10.1137/1031049
10.1109/TSP.2018.2870386
10.1109/ICASSP.2016.7472874
10.1109/GlobalSIP.2018.8646609
10.1109/JSTSP.2017.2726979
10.1109/MGRS.2015.2441912
10.1371/journal.pcbi.1000498
10.1109/GlobalSIP.2014.7032257
10.1109/ICASSP.2018.8462232
10.1016/j.sigpro.2016.05.037
10.1109/TSP.2017.2718969
10.1109/TSP.2015.2469645
10.1109/MSP.2012.2235192
10.1109/JPROC.2018.2820126
10.1109/TSIPN.2017.2710619
10.1109/TSP.2016.2573767
10.1109/TSP.2019.2908129
10.1017/CBO9780511804441
10.1109/LSP.2018.2818062
10.1016/j.acha.2016.05.005
10.1109/ICASSP.2014.6854325
10.1145/2623330.2623760
10.1109/ICASSP.2015.7178600
10.1093/imaiai/iax021
10.1090/S0002-9947-08-04511-X
10.1109/TSP.2014.2299518
10.1109/TSP.2016.2573748
10.1109/ICASSP.2017.7953286
10.1109/ISIT.2017.8006574
10.1109/TSP.2015.2507546
10.1109/TSIPN.2017.2731161
10.1109/ICASSP.2018.8462381
10.1109/TSP.2017.2752689
10.1137/S1064827500366124
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TSP.2019.2940129
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1941-0476
EndPage 5526
ExternalDocumentID 10_1109_TSP_2019_2940129
8827302
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China; National Science Foundation of China
  grantid: 61771356
  funderid: 10.13039/501100001809
– fundername: Natural Sciences and Engineering Research Council of Canada
  grantid: RGPIN-2019-06271; RGPAS-2019-00110
  funderid: 10.13039/501100000038
– fundername: CSC's scholarship
GroupedDBID -~X
.DC
0R~
29I
4.4
5GY
6IK
85S
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACIWK
ACNCT
AENEX
AGQYO
AHBIQ
AJQPL
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
EBS
EJD
F5P
HZ~
IFIPE
IPLJI
JAVBF
LAI
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
RIG
ID FETCH-LOGICAL-c291t-c29a351cb30f5fc66cffe96d14f3cd94f36360021215a5f181b6993ee3d2d0c33
IEDL.DBID RIE
ISICitedReferencesCount 31
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000489757100005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1053-587X
IngestDate Mon Jun 30 10:10:51 EDT 2025
Tue Nov 18 22:26:36 EST 2025
Sat Nov 29 04:10:49 EST 2025
Wed Aug 27 08:33:13 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 21
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c291t-c29a351cb30f5fc66cffe96d14f3cd94f36360021215a5f181b6993ee3d2d0c33
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-5571-4137
0000-0002-9109-4086
0000-0002-0640-4140
PQID 2298706220
PQPubID 85478
PageCount 16
ParticipantIDs proquest_journals_2298706220
crossref_primary_10_1109_TSP_2019_2940129
ieee_primary_8827302
crossref_citationtrail_10_1109_TSP_2019_2940129
PublicationCentury 2000
PublicationDate 2019-11-01
PublicationDateYYYYMMDD 2019-11-01
PublicationDate_xml – month: 11
  year: 2019
  text: 2019-11-01
  day: 01
PublicationDecade 2010
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on signal processing
PublicationTitleAbbrev TSP
PublicationYear 2019
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
ref13
ref12
ref14
fujishige (ref54) 2005; 58
ref52
ref55
ref11
ref10
ref17
ref16
ref19
ref51
ortiz-jiménez (ref37) 2018
ref46
ref45
ref48
ref47
ref42
ref41
hashemi (ref44) 2018
ref43
ref8
ref7
ref9
ref4
ref3
ref6
ref5
ref40
ref34
ref36
ref31
ref30
ref33
ref32
ref2
ref1
ref39
ref38
perraudin (ref56) 2014
isufi (ref35) 2017
kay (ref49) 1993
ref24
ref23
ref26
ref25
ref20
ref22
ref21
horn (ref18) 1990
ref28
ref27
valsesia (ref15) 2018
ref29
pukelsheim (ref50) 1993; 50
bernstein (ref53) 2005
References_xml – year: 1990
  ident: ref18
  publication-title: Matrix Analysis
– ident: ref52
  doi: 10.1137/1.9781611971446
– year: 2018
  ident: ref15
  article-title: Sampling of graph signals via randomized local aggregations
  publication-title: IEEE Trans Signal Inf Process Over Netw
– ident: ref41
  doi: 10.1109/CDC.2010.5717225
– ident: ref7
  doi: 10.1109/MSP.2014.2329213
– ident: ref22
  doi: 10.1109/GLOCOM.2017.8254798
– ident: ref43
  doi: 10.1109/TSP.2017.2773429
– ident: ref34
  doi: 10.1109/TSP.2018.2835384
– ident: ref5
  doi: 10.1016/j.acha.2010.04.005
– year: 1993
  ident: ref49
  publication-title: Fundamentals of Statistical Signal Processing Estimation Theory
– ident: ref3
  doi: 10.1109/JPROC.2018.2799702
– ident: ref30
  doi: 10.1109/ICASSP.2019.8682200
– volume: 50
  year: 1993
  ident: ref50
  publication-title: Optimal Design of Experiments
– ident: ref51
  doi: 10.1016/B978-0-444-50617-7.50010-0
– ident: ref40
  doi: 10.1109/TSP.2015.2460224
– ident: ref12
  doi: 10.1109/TSP.2016.2546233
– ident: ref20
  doi: 10.1109/TSP.2017.2755586
– ident: ref23
  doi: 10.1137/1031049
– ident: ref8
  doi: 10.1109/TSP.2018.2870386
– year: 2005
  ident: ref53
  publication-title: Matrix Mathematics
– ident: ref46
  doi: 10.1109/ICASSP.2016.7472874
– ident: ref36
  doi: 10.1109/GlobalSIP.2018.8646609
– ident: ref9
  doi: 10.1109/JSTSP.2017.2726979
– ident: ref10
  doi: 10.1109/MGRS.2015.2441912
– ident: ref11
  doi: 10.1371/journal.pcbi.1000498
– ident: ref16
  doi: 10.1109/GlobalSIP.2014.7032257
– volume: 58
  year: 2005
  ident: ref54
  publication-title: Submodular Functions and Optimization
– ident: ref47
  doi: 10.1109/ICASSP.2018.8462232
– ident: ref14
  doi: 10.1016/j.sigpro.2016.05.037
– ident: ref6
  doi: 10.1109/TSP.2017.2718969
– ident: ref27
  doi: 10.1109/TSP.2015.2469645
– ident: ref2
  doi: 10.1109/MSP.2012.2235192
– year: 2017
  ident: ref35
  article-title: Observing and tracking bandlimited graph processes
– ident: ref1
  doi: 10.1109/JPROC.2018.2820126
– ident: ref19
  doi: 10.1109/TSIPN.2017.2710619
– year: 2014
  ident: ref56
  article-title: Gspbox: A toolbox for signal processing on graphs
– ident: ref42
  doi: 10.1109/TSP.2016.2573767
– ident: ref29
  doi: 10.1109/TSP.2019.2908129
– ident: ref17
  doi: 10.1017/CBO9780511804441
– ident: ref31
  doi: 10.1109/LSP.2018.2818062
– ident: ref32
  doi: 10.1016/j.acha.2016.05.005
– ident: ref24
  doi: 10.1109/ICASSP.2014.6854325
– ident: ref57
  doi: 10.1145/2623330.2623760
– ident: ref48
  doi: 10.1109/ICASSP.2015.7178600
– ident: ref33
  doi: 10.1093/imaiai/iax021
– ident: ref25
  doi: 10.1090/S0002-9947-08-04511-X
– ident: ref39
  doi: 10.1109/TSP.2014.2299518
– ident: ref26
  doi: 10.1109/TSP.2016.2573748
– ident: ref28
  doi: 10.1109/ICASSP.2017.7953286
– ident: ref21
  doi: 10.1109/ISIT.2017.8006574
– ident: ref13
  doi: 10.1109/TSP.2015.2507546
– ident: ref45
  doi: 10.1109/TSIPN.2017.2731161
– ident: ref38
  doi: 10.1109/ICASSP.2018.8462381
– ident: ref4
  doi: 10.1109/TSP.2017.2752689
– ident: ref55
  doi: 10.1137/S1064827500366124
– year: 2018
  ident: ref37
  article-title: Sparse sampling for inverse problems with tensors
– year: 2018
  ident: ref44
  article-title: Randomized greedy sensor selection: Leveraging weak submodularity
SSID ssj0014496
Score 2.4547048
Snippet Graph sampling addresses the problem of selecting a node subset in a graph to collect samples, so that a K-bandlimited signal can be reconstructed with high...
Graph sampling addresses the problem of selecting a node subset in a graph to collect samples, so that a [Formula Omitted]-bandlimited signal can be...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 5511
SubjectTerms Approximation
Complexity theory
Covariance matrices
Fourier transforms
Graph signal processing
Inversions
Laplace equations
Matrix decomposition
matrix inversion
Neumann series theorem
Noise
Optimality criteria
Optimization
Robustness (mathematics)
Sampling
Sampling methods
Signal reconstruction
Strategy
Title Low-complexity Graph Sampling With Noise and Signal Reconstruction via Neumann Series
URI https://ieeexplore.ieee.org/document/8827302
https://www.proquest.com/docview/2298706220
Volume 67
WOSCitedRecordID wos000489757100005&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: PRVIEE
  databaseName: IEEE Xplore
  customDbUrl:
  eissn: 1941-0476
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014496
  issn: 1053-587X
  databaseCode: RIE
  dateStart: 19910101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDI7GxAEOvAZiMFAOXJDo1jbpI0eEeBzQNGmb2K3qEndUQi1iY_DzsbNugEBIXKIcmqi10_iL7Xxm7CwGF0QcSQfPs-BIZRT2POEo6UkNsZdCmNpiE1G3G49GqldjF6u7MABgk8-gTV0byzelfiVXWQfRIC5I3HDXoihc3NVaRQyktLW4EC4IJ4ij0TIk6arOoN-jHC7V9pUkv8s3E2RrqvzYiK11udn-33vtsK0KRfLLhdp3WQ2KPbb5hVuwwYb35ZtjE8bhHZE2vyVmat5PKYO8mPCHfPbIu2U-BZ4WhvfzCU1Ih9FPSlk-z1PeBXLzF5zcaDDdZ8Ob68HVnVPVUHC0r7wZtakIPD0WbhZkOgx1loEKjSczoY3ClgjDiOfdC9IgQ3s_DhGyAAjjG1cLccDqRVnAIeP4kXEYZZH2xmj2TaxkbFJQaO8R1CAsarLOUqyJrgjGqc7FU2IPGq5KUBEJKSKpFNFk56sRzwtyjT-ebZDgV89VMm-y1lJzSfX3TRPfVxS-9X336PdRx2yD5l7cKWyxOsoVTti6ns_y6cupXVgfK1bJqA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dT9swED9VgAQ8jG_RwYYf9jKJ0CR2PvyI0BjTSlSpRfQtSu1LiYRStHbAn8-dm5ZNQ0h7sfwQ5-PO8f18d_4dwJcUfZRpojzaz6KntNXUC6SnVaAMpkGBceGKTSRZlg6HuteC0-VZGER0yWd4xl0Xy7cT85tdZR1CgzQhacFdjZQK_flprWXMQClXjYsAg_SiNBkugpK-7gz6Pc7i0mehVux5-csIuaoq_yzFzr5cbv3fm23DhwZHivO54neghfUubP7BLrgHN93Jk-dSxvGZsLb4ztzUol9wDnk9FrfV7E5kk2qKoqit6FdjviFvR19JZcVjVYgM2dFfC3ak4XQfbi6_DS6uvKaKgmdCHcy4LWQUmJH0y6g0cWzKEnVsA1VKYzW1TBnGTO9BVEQlWfxRTKAFUdrQ-kbKA1ipJzUegqCPTOOkTEwwIsNvU61SW6Ami0-whoBRGzoLseamoRjnShf3udtq-DonReSsiLxRRBu-Lkc8zOk13rl2jwW_vK6ReRuOF5rLm_9vmoeh5gBuGPof3x51AutXg-tu3v2R_TyCDX7O_IThMayQjPETrJnHWTX99dlNshfTa8zv
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=Low-complexity+Graph+Sampling+With+Noise+and+Signal+Reconstruction+via+Neumann+Series&rft.jtitle=IEEE+transactions+on+signal+processing&rft.au=Wang%2C+Fen&rft.au=Cheung%2C+Gene&rft.au=Wang%2C+Yongchao&rft.date=2019-11-01&rft.pub=IEEE&rft.issn=1053-587X&rft.volume=67&rft.issue=21&rft.spage=5511&rft.epage=5526&rft_id=info:doi/10.1109%2FTSP.2019.2940129&rft.externalDocID=8827302
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1053-587X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1053-587X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1053-587X&client=summon