Semi-supervised Stacked Label Consistent Autoencoder for Reconstruction and Analysis of Biomedical Signals

Objective: An autoencoder-based framework that simultaneously reconstruct and classify biomedical signals is proposed. Previous work has treated reconstruction and classification as separate problems. This is the first study that proposes a combined framework to address the issue in a holistic fashi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on biomedical engineering Jg. 64; H. 9; S. 2196 - 2205
Hauptverfasser: Gogna, Anupriya, Majumdar, Angshul, Ward, Rabab
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.09.2017
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:0018-9294, 1558-2531
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Objective: An autoencoder-based framework that simultaneously reconstruct and classify biomedical signals is proposed. Previous work has treated reconstruction and classification as separate problems. This is the first study that proposes a combined framework to address the issue in a holistic fashion. Methods: For telemonitoring purposes, reconstruction techniques of biomedical signals are largely based on compressed sensing (CS); these are "designed" techniques where the reconstruction formulation is based on some "assumption" regarding the signal. In this study, we propose a new paradigm for reconstruction-the reconstruction is "learned," using an autoencoder; it does not require any assumption regarding the signal as long as there is sufficiently large training data. But since the final goal is to analyze/classify the signal, the system can also learn a linear classification map that is added inside the autoencoder. The ensuing optimization problem is solved using the Split Bregman technique. Results: Experiments were carried out on reconstructing and classifying electrocardiogram (ECG) (arrhythmia classification) and EEG (seizure classification) signals. Conclusion: Our proposed tool is capable of operating in a semi-supervised fashion. We show that our proposed method is better in reconstruction and more than an order magnitude faster than CS based methods; it is capable of real-time operation. Our method also yields better results than recently proposed classification methods. Significance: This is the first study offering an alternative to CS-based reconstruction. It also shows that the representation learning approach can yield better results than traditional methods that use hand-crafted features for signal analysis.
AbstractList Objective: An autoencoder-based framework that simultaneously reconstruct and classify biomedical signals is proposed. Previous work has treated reconstruction and classification as separate problems. This is the first study that proposes a combined framework to address the issue in a holistic fashion. Methods: For telemonitoring purposes, reconstruction techniques of biomedical signals are largely based on compressed sensing (CS); these are “designed” techniques where the reconstruction formulation is based on some “assumption” regarding the signal. In this study, we propose a new paradigm for reconstruction-the reconstruction is “learned,” using an autoencoder; it does not require any assumption regarding the signal as long as there is sufficiently large training data. But since the final goal is to analyze/classify the signal, the system can also learn a linear classification map that is added inside the autoencoder. The ensuing optimization problem is solved using the Split Bregman technique. Results: Experiments were carried out on reconstructing and classifying electrocardiogram (ECG) (arrhythmia classification) and EEG (seizure classification) signals. Conclusion: Our proposed tool is capable of operating in a semi-supervised fashion. We show that our proposed method is better in reconstruction and more than an order magnitude faster than CS based methods; it is capable of real-time operation. Our method also yields better results than recently proposed classification methods. Significance: This is the first study offering an alternative to CS-based reconstruction. It also shows that the representation learning approach can yield better results than traditional methods that use hand-crafted features for signal analysis.
An autoencoder-based framework that simultaneously reconstruct and classify biomedical signals is proposed. Previous work has treated reconstruction and classification as separate problems. This is the first study that proposes a combined framework to address the issue in a holistic fashion. For telemonitoring purposes, reconstruction techniques of biomedical signals are largely based on compressed sensing (CS); these are "designed" techniques where the reconstruction formulation is based on some "assumption" regarding the signal. In this study, we propose a new paradigm for reconstruction-the reconstruction is "learned," using an autoencoder; it does not require any assumption regarding the signal as long as there is sufficiently large training data. But since the final goal is to analyze/classify the signal, the system can also learn a linear classification map that is added inside the autoencoder. The ensuing optimization problem is solved using the Split Bregman technique. Experiments were carried out on reconstructing and classifying electrocardiogram (ECG) (arrhythmia classification) and EEG (seizure classification) signals. Our proposed tool is capable of operating in a semi-supervised fashion. We show that our proposed method is better in reconstruction and more than an order magnitude faster than CS based methods; it is capable of real-time operation. Our method also yields better results than recently proposed classification methods. This is the first study offering an alternative to CS-based reconstruction. It also shows that the representation learning approach can yield better results than traditional methods that use hand-crafted features for signal analysis.
OBJECTIVEAn autoencoder-based framework that simultaneously reconstruct and classify biomedical signals is proposed. Previous work has treated reconstruction and classification as separate problems. This is the first study that proposes a combined framework to address the issue in a holistic fashion.METHODSFor telemonitoring purposes, reconstruction techniques of biomedical signals are largely based on compressed sensing (CS); these are "designed" techniques where the reconstruction formulation is based on some "assumption" regarding the signal. In this study, we propose a new paradigm for reconstruction-the reconstruction is "learned," using an autoencoder; it does not require any assumption regarding the signal as long as there is sufficiently large training data. But since the final goal is to analyze/classify the signal, the system can also learn a linear classification map that is added inside the autoencoder. The ensuing optimization problem is solved using the Split Bregman technique.RESULTSExperiments were carried out on reconstructing and classifying electrocardiogram (ECG) (arrhythmia classification) and EEG (seizure classification) signals.CONCLUSIONOur proposed tool is capable of operating in a semi-supervised fashion. We show that our proposed method is better in reconstruction and more than an order magnitude faster than CS based methods; it is capable of real-time operation. Our method also yields better results than recently proposed classification methods.SIGNIFICANCEThis is the first study offering an alternative to CS-based reconstruction. It also shows that the representation learning approach can yield better results than traditional methods that use hand-crafted features for signal analysis.
Author Majumdar, Angshul
Ward, Rabab
Gogna, Anupriya
Author_xml – sequence: 1
  givenname: Anupriya
  surname: Gogna
  fullname: Gogna, Anupriya
  organization: Indraprasatha Institute of Information Technology
– sequence: 2
  givenname: Angshul
  surname: Majumdar
  fullname: Majumdar, Angshul
  email: angshul@iiitd.ac.in
  organization: Indraprasatha Institute of Information Technology, Delhi, India
– sequence: 3
  givenname: Rabab
  surname: Ward
  fullname: Ward, Rabab
  organization: University of British Columbia
BackLink https://www.ncbi.nlm.nih.gov/pubmed/27893378$$D View this record in MEDLINE/PubMed
BookMark eNp9kU1vEzEQhi1URNPCD0BIyBKXXjb4a_1xTKNSkIKQSDlbXu8sctisg-1F6r_HUVIOPXB6NZrnHc3Me4UupjgBQm8pWVJKzMeH2693S0aoXDLJqWTkBVrQttUNazm9QAtCqG4MM-ISXeW8q6XQQr5Cl0xpw7nSC7Tbwj40eT5A-hMy9HhbnP9VdeM6GPE6TjnkAlPBq7lEmHzsIeEhJvwdfG2WNPsS4oTd1OPV5MbHyuM44NsQ99AH70a8DT9rI79GL4cq8Oas1-jHp7uH9edm8-3-y3q1aTwXpjRcUS5bwb3gpHWGCNJJZXpiXK9h8APIYWg500r1XS99Nwyd7oRgnQTFBVB-jW5Ocw8p_p4hF7sP2cM4ugninC3VQkhimGIV_fAM3cU5HZe1jCrBGTFCVur9mZq7epM9pLB36dE-fbEC6gT4FHNOMFgfiju-pSQXRkuJPeZlj3nZY172nFd10mfOp-H_87w7eQIA_OOVapnmkv8Fqe6gYA
CODEN IEBEAX
CitedBy_id crossref_primary_10_1109_TBCAS_2023_3234280
crossref_primary_10_1016_j_bspc_2023_104992
crossref_primary_10_1109_ACCESS_2020_3000638
crossref_primary_10_1016_j_image_2020_116111
crossref_primary_10_1109_TASE_2022_3218132
crossref_primary_10_1109_TCDS_2021_3079712
crossref_primary_10_1016_j_bspc_2021_103065
crossref_primary_10_1088_1361_6501_abfbab
crossref_primary_10_1109_THMS_2023_3244938
crossref_primary_10_1109_TBME_2021_3137184
crossref_primary_10_1016_j_bspc_2020_102054
crossref_primary_10_1088_1741_2552_adc48e
crossref_primary_10_1109_ACCESS_2024_3406736
crossref_primary_10_1109_TSG_2018_2815763
crossref_primary_10_1016_j_neunet_2023_01_034
crossref_primary_10_1016_j_chemosphere_2024_143835
crossref_primary_10_1109_ACCESS_2017_2771536
crossref_primary_10_1016_j_knosys_2025_113173
crossref_primary_10_1016_j_knosys_2024_112322
crossref_primary_10_1109_JAS_2022_105425
crossref_primary_10_3390_jmse13050956
crossref_primary_10_1145_3448302
crossref_primary_10_1016_j_measurement_2023_113944
crossref_primary_10_1016_j_compbiomed_2020_103797
crossref_primary_10_3389_fnins_2023_1135850
crossref_primary_10_1109_TBCAS_2019_2930215
crossref_primary_10_1111_exsy_12494
crossref_primary_10_1109_ACCESS_2018_2859267
crossref_primary_10_1145_3241056
crossref_primary_10_1109_JSEN_2020_3025384
crossref_primary_10_3390_s24113601
crossref_primary_10_1109_TNSE_2022_3222362
crossref_primary_10_1007_s11063_021_10467_0
crossref_primary_10_1016_j_neunet_2018_07_016
crossref_primary_10_1109_ACCESS_2018_2881492
crossref_primary_10_1016_j_nanoen_2024_109796
crossref_primary_10_1016_j_mri_2018_06_003
crossref_primary_10_1109_ACCESS_2020_3038314
crossref_primary_10_1109_ACCESS_2019_2919143
crossref_primary_10_1109_TMM_2020_2999183
crossref_primary_10_1016_j_eswa_2021_115729
crossref_primary_10_1016_j_comcom_2022_07_027
crossref_primary_10_1016_j_bspc_2021_103281
crossref_primary_10_1109_JBHI_2020_3006145
crossref_primary_10_1007_s10489_019_01581_7
crossref_primary_10_1007_s11042_023_15052_2
crossref_primary_10_1109_ACCESS_2025_3553056
crossref_primary_10_1016_j_bspc_2020_102225
crossref_primary_10_1109_ACCESS_2019_2912036
crossref_primary_10_1186_s12938_019_0630_9
crossref_primary_10_1371_journal_pone_0218930
crossref_primary_10_1109_JIOT_2020_3021724
crossref_primary_10_1109_JBHI_2018_2871678
crossref_primary_10_1364_AO_57_002545
crossref_primary_10_1109_THMS_2019_2904615
crossref_primary_10_3390_electronics8060667
crossref_primary_10_1109_TBCAS_2021_3090995
crossref_primary_10_1109_TSMC_2019_2946398
crossref_primary_10_1016_j_bdr_2021_100305
crossref_primary_10_1109_TBME_2019_2926104
crossref_primary_10_1177_14604582231213846
crossref_primary_10_1016_j_neucom_2024_128644
crossref_primary_10_1186_s12911_019_0967_9
crossref_primary_10_3390_brainsci11050668
crossref_primary_10_1109_TCBB_2020_3006699
crossref_primary_10_1109_TIM_2018_2872387
crossref_primary_10_1007_s00034_022_02071_x
crossref_primary_10_3390_app12168368
crossref_primary_10_1002_rcs_1947
crossref_primary_10_1016_j_dsp_2025_105608
crossref_primary_10_1007_s42979_024_03508_7
crossref_primary_10_1109_JIOT_2024_3402254
crossref_primary_10_1016_j_neucom_2022_12_017
crossref_primary_10_1016_j_patcog_2021_108386
crossref_primary_10_1109_ACCESS_2019_2930882
crossref_primary_10_3389_fnins_2022_824471
crossref_primary_10_1088_1741_2552_ad48ba
crossref_primary_10_1109_ACCESS_2020_3025324
crossref_primary_10_3389_fnbot_2019_00037
crossref_primary_10_1016_j_dsp_2025_105053
crossref_primary_10_1016_j_inffus_2024_102536
crossref_primary_10_1109_TNNLS_2020_3042500
crossref_primary_10_1155_2020_8849011
crossref_primary_10_3389_fphys_2021_727210
crossref_primary_10_3390_app12168256
Cites_doi 10.3390/s140202036
10.1109/TBCAS.2015.2444276
10.1109/JSSC.2003.811979
10.1561/2200000006
10.1109/18.382009
10.1109/TITB.2009.2034649
10.1016/j.eswa.2012.12.063
10.1016/j.bspc.2013.01.005
10.1109/TBME.2010.2048568
10.1109/JBHI.2013.2255132
10.1109/TIT.2011.2173241
10.1109/TBME.2012.2217959
10.3390/s140101474
10.1109/TSP.2012.2208955
10.1109/SSP.2007.4301243
10.1109/JBHI.2014.2312374
10.1016/j.bspc.2015.03.002
10.1109/TIT.2007.909108
10.1109/JBHI.2014.2358640
10.1109/JSSC.2007.897157
10.1109/JSSC.2011.2179451
10.1109/TNSRE.2013.2290870
10.1016/j.bspc.2014.11.006
10.1109/TIFS.2015.2398817
10.1109/TNSRE.2014.2319334
10.1002/cpa.20042
10.1016/j.cmpb.2013.11.014
10.1109/TBME.2010.2068048
10.1016/j.bspc.2013.08.006
10.1109/TPAMI.2013.88
10.1145/1390156.1390224
10.1109/TBME.2012.2226175
10.1109/JBHI.2014.2325017
10.1126/science.1127647
10.1109/ICASSP.2013.6639345
10.1109/TBME.2014.2360101
10.1109/TITB.2011.2181403
10.1007/BF02551274
10.1016/j.bspc.2014.09.003
10.1186/1475-925X-8-31
10.1016/0893-6080(91)90009-T
10.1016/j.bspc.2014.04.004
10.1016/j.acha.2008.07.002
10.1109/TITB.2009.2038481
10.1109/TITB.2011.2159805
10.1016/j.bspc.2013.09.005
10.1016/j.eswa.2010.02.045
10.1109/TBCAS.2013.2263459
10.1109/TNSRE.2015.2441835
10.1109/TSP.2013.2241055
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2017
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2017
DBID 97E
RIA
RIE
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
KR7
L7M
L~C
L~D
P64
7X8
DOI 10.1109/TBME.2016.2631620
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
Aluminium Industry Abstracts
Biotechnology Research Abstracts
Ceramic Abstracts
Computer and Information Systems Abstracts
Corrosion Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
Materials Business File
Mechanical & Transportation Engineering Abstracts
Solid State and Superconductivity Abstracts
METADEX
Technology Research Database
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
Aerospace Database
Materials Research Database
ProQuest Computer Science Collection
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Biotechnology and BioEngineering Abstracts
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Materials Research Database
Civil Engineering Abstracts
Aluminium Industry Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Ceramic Abstracts
Materials Business File
METADEX
Biotechnology and BioEngineering Abstracts
Computer and Information Systems Abstracts Professional
Aerospace Database
Engineered Materials Abstracts
Biotechnology Research Abstracts
Solid State and Superconductivity Abstracts
Engineering Research Database
Corrosion Abstracts
Advanced Technologies Database with Aerospace
ANTE: Abstracts in New Technology & Engineering
MEDLINE - Academic
DatabaseTitleList Materials Research Database
MEDLINE
MEDLINE - Academic

Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Engineering
EISSN 1558-2531
EndPage 2205
ExternalDocumentID 27893378
10_1109_TBME_2016_2631620
7752836
Genre orig-research
Research Support, Non-U.S. Gov't
Journal Article
GrantInformation_xml – fundername: Qatar Foundation
– fundername: NPRP
  grantid: 7-684-1-127
– fundername: Qatar National Research Fund
  funderid: 10.13039/100008982
GroupedDBID ---
-~X
.55
.DC
.GJ
0R~
29I
4.4
53G
5GY
5RE
5VS
6IF
6IK
6IL
6IN
85S
97E
AAJGR
AARMG
AASAJ
AAWTH
AAYJJ
ABAZT
ABJNI
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACKIV
ACNCT
ACPRK
ADZIZ
AENEX
AETIX
AFFNX
AFRAH
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CHZPO
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
IAAWW
IBMZZ
ICLAB
IDIHD
IEGSK
IFIPE
IFJZH
IPLJI
JAVBF
LAI
MS~
O9-
OCL
P2P
RIA
RIE
RIL
RNS
TAE
TN5
VH1
VJK
X7M
ZGI
ZXP
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
PKN
RIG
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
KR7
L7M
L~C
L~D
P64
7X8
ID FETCH-LOGICAL-c349t-37136543c4305a9040b679d09ad8efcfe6ff532877dbd6cbffb8b442b6e734e13
IEDL.DBID RIE
ISICitedReferencesCount 107
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000408111500018&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0018-9294
IngestDate Thu Oct 02 11:04:54 EDT 2025
Mon Jun 30 08:15:05 EDT 2025
Wed Feb 19 02:41:17 EST 2025
Sat Nov 29 05:34:20 EST 2025
Tue Nov 18 21:53:44 EST 2025
Wed Aug 27 02:53:44 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 9
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c349t-37136543c4305a9040b679d09ad8efcfe6ff532877dbd6cbffb8b442b6e734e13
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
PMID 27893378
PQID 2174320946
PQPubID 85474
PageCount 10
ParticipantIDs proquest_journals_2174320946
crossref_citationtrail_10_1109_TBME_2016_2631620
proquest_miscellaneous_1844609272
ieee_primary_7752836
pubmed_primary_27893378
crossref_primary_10_1109_TBME_2016_2631620
PublicationCentury 2000
PublicationDate 2017-09-01
PublicationDateYYYYMMDD 2017-09-01
PublicationDate_xml – month: 09
  year: 2017
  text: 2017-09-01
  day: 01
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle IEEE transactions on biomedical engineering
PublicationTitleAbbrev TBME
PublicationTitleAlternate IEEE Trans Biomed Eng
PublicationYear 2017
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 (ref59) 2016
ref57
ref56
ref12
ref15
ref53
majumdar (ref17) 2014; 14
ref52
ref55
ref11
ref54
ref10
bengio (ref36) 0
ref19
ref18
makhani (ref39) 0
cho (ref28) 0
hinton (ref26) 2006; 13
ref51
ref50
ref46
ref45
ref48
ref47
ref42
ref44
ref43
fauvel (ref13) 2014; 14
ref8
ref7
majumdar (ref41) 0
ref9
ref4
ref3
vincent (ref27) 2010; 11
ref6
ref5
ref35
ref34
ref37
ref30
ref33
ref32
(ref64) 2016
ref2
chiang (ref14) 2013; 14
ref1
lin (ref31) 2010; 57
hosseini kamal (ref16) 0
chen (ref38) 0
ref24
ref23
ref25
(ref49) 1957; 144
ref20
ref63
ref22
ref21
ye (ref58) 0
ref29
rifai (ref40) 0
ref60
ref62
ref61
References_xml – volume: 14
  start-page: 2036
  year: 2013
  ident: ref14
  article-title: Energy-efficient data reduction techniques for wireless seizure detection systems
  publication-title: SENSORS
  doi: 10.3390/s140202036
– ident: ref7
  doi: 10.1109/TBCAS.2015.2444276
– ident: ref10
  doi: 10.1109/JSSC.2003.811979
– ident: ref37
  doi: 10.1561/2200000006
– volume: 14
  start-page: 15729
  year: 2014
  ident: ref17
  article-title: Low-rank matrix recovery approach for energy efficient EEG acquisition for wireless body area network
  publication-title: Sensors Special Issue State-of-the-Art Sensor Technol Canada
– ident: ref46
  doi: 10.1109/18.382009
– start-page: 4305
  year: 0
  ident: ref16
  article-title: Compressive multichannel cortical signal recording
  publication-title: Proc IEEE ICASSP
– ident: ref22
  doi: 10.1109/TITB.2009.2034649
– ident: ref55
  doi: 10.1016/j.eswa.2012.12.063
– ident: ref56
  doi: 10.1016/j.bspc.2013.01.005
– volume: 57
  start-page: 1798
  year: 2010
  ident: ref31
  article-title: EEG-based emotion recognition in music listening
  publication-title: IEEE Trans Biomed Eng
  doi: 10.1109/TBME.2010.2048568
– ident: ref30
  doi: 10.1109/JBHI.2013.2255132
– ident: ref43
  doi: 10.1109/TIT.2011.2173241
– start-page: 1476
  year: 0
  ident: ref38
  article-title: Marginalized denoising autoencoders for nonlinear representation
  publication-title: Proc of ICML 2014
– ident: ref6
  doi: 10.1109/TBME.2012.2217959
– volume: 14
  start-page: 1474
  year: 2014
  ident: ref13
  article-title: An Energy efficient compressed sensing framework for the compression of electroencephalogram signals
  publication-title: SENSORS
  doi: 10.3390/s140101474
– ident: ref53
  doi: 10.1109/TSP.2012.2208955
– volume: 144
  start-page: 679
  year: 1957
  ident: ref49
  article-title: On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition
  publication-title: Doklady Akad Nauk SSSR
– ident: ref12
  doi: 10.1109/SSP.2007.4301243
– ident: ref2
  doi: 10.1109/JBHI.2014.2312374
– start-page: 833
  year: 0
  ident: ref40
  article-title: Contractive auto-encoders: Explicit invariance during feature extraction
  publication-title: Proc ICML 2011
– start-page: 153
  year: 0
  ident: ref36
  article-title: Greedy layer-wise training of deep networks
  publication-title: Proc NIPS
– year: 2016
  ident: ref59
– start-page: 1918
  year: 0
  ident: ref58
  article-title: Arrhythmia detection and classification using morphological and dynamic features of ECG signals
  publication-title: Proc IEEE EMBS
– ident: ref20
  doi: 10.1016/j.bspc.2015.03.002
– ident: ref42
  doi: 10.1109/TIT.2007.909108
– ident: ref29
  doi: 10.1109/JBHI.2014.2358640
– ident: ref9
  doi: 10.1109/JSSC.2007.897157
– start-page: 432
  year: 0
  ident: ref28
  article-title: Simple sparsification improves sparse denoising autoencoders in denoising highly noisy images
  publication-title: Proc of ICML'2013
– year: 0
  ident: ref39
  article-title: K-sparse autoencoder
  publication-title: Proceedings of the ICLR 2014
– year: 2016
  ident: ref64
– ident: ref8
  doi: 10.1109/JSSC.2011.2179451
– ident: ref33
  doi: 10.1109/TNSRE.2013.2290870
– ident: ref21
  doi: 10.1016/j.bspc.2014.11.006
– ident: ref34
  doi: 10.1109/TIFS.2015.2398817
– ident: ref3
  doi: 10.1109/TNSRE.2014.2319334
– ident: ref45
  doi: 10.1002/cpa.20042
– ident: ref61
  doi: 10.1016/j.cmpb.2013.11.014
– ident: ref54
  doi: 10.1109/TBME.2010.2068048
– ident: ref62
  doi: 10.1016/j.bspc.2013.08.006
– ident: ref52
  doi: 10.1109/TPAMI.2013.88
– ident: ref51
  doi: 10.1145/1390156.1390224
– ident: ref1
  doi: 10.1109/TBME.2012.2226175
– ident: ref5
  doi: 10.1109/JBHI.2014.2325017
– volume: 13
  start-page: 504
  year: 2006
  ident: ref26
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
  doi: 10.1126/science.1127647
– ident: ref35
  doi: 10.1109/ICASSP.2013.6639345
– ident: ref60
  doi: 10.1109/TBME.2014.2360101
– ident: ref24
  doi: 10.1109/TITB.2011.2181403
– volume: 11
  start-page: 3371
  year: 2010
  ident: ref27
  article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
  publication-title: J Mach Learn Res
– ident: ref47
  doi: 10.1007/BF02551274
– ident: ref50
  doi: 10.1109/18.382009
– ident: ref19
  doi: 10.1016/j.bspc.2014.09.003
– ident: ref57
  doi: 10.1186/1475-925X-8-31
– ident: ref48
  doi: 10.1016/0893-6080(91)90009-T
– ident: ref18
  doi: 10.1016/j.bspc.2014.04.004
– ident: ref44
  doi: 10.1016/j.acha.2008.07.002
– ident: ref23
  doi: 10.1109/TITB.2009.2038481
– year: 0
  ident: ref41
  article-title: Face recognition via class sparsity based supervised encoding
  publication-title: IEEE Trans Pattern Anal Mach Intell
– ident: ref25
  doi: 10.1109/TITB.2011.2159805
– ident: ref15
  doi: 10.1016/j.bspc.2013.09.005
– ident: ref63
  doi: 10.1016/j.eswa.2010.02.045
– ident: ref4
  doi: 10.1109/TBCAS.2013.2263459
– ident: ref32
  doi: 10.1109/TNSRE.2015.2441835
– ident: ref11
  doi: 10.1109/TSP.2013.2241055
SSID ssj0014846
Score 2.567681
Snippet Objective: An autoencoder-based framework that simultaneously reconstruct and classify biomedical signals is proposed. Previous work has treated reconstruction...
An autoencoder-based framework that simultaneously reconstruct and classify biomedical signals is proposed. Previous work has treated reconstruction and...
OBJECTIVEAn autoencoder-based framework that simultaneously reconstruct and classify biomedical signals is proposed. Previous work has treated reconstruction...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 2196
SubjectTerms Algorithms
Arrhythmia
Body area network (BAN)
Classification
Compressed sensing
Correlation
Data processing
deep learning
EEG
EKG
Electrocardiography - methods
Electroencephalography
Image reconstruction
Information Storage and Retrieval - methods
Monitoring
Pattern Recognition, Automated - methods
Real time operation
Reconstruction
Signal analysis
Signal classification
Signal Processing, Computer-Assisted
Supervised Machine Learning
Title Semi-supervised Stacked Label Consistent Autoencoder for Reconstruction and Analysis of Biomedical Signals
URI https://ieeexplore.ieee.org/document/7752836
https://www.ncbi.nlm.nih.gov/pubmed/27893378
https://www.proquest.com/docview/2174320946
https://www.proquest.com/docview/1844609272
Volume 64
WOSCitedRecordID wos000408111500018&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 Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-2531
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014846
  issn: 0018-9294
  databaseCode: RIE
  dateStart: 19640101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bT9VAEJ4AMUYeUEHlIJI18clYaLt79vIIBuIDEBMwOW_N3kqOwZbQc_z9zmx7Cg9o4luT7S2dmd35OjvfB_Bp6rROgiYIvWwmrCgzV2ufBau185LUzZNqybm6vNSzmfm-Bl_GXpgYY9p8Fg_pMNXyQ-uX9KvsSCmiIpHrsK6U7Hu1xoqB0H1TTl5gAJdGDBXMIjdH1ycXp7SJSx6WkheyJPU3agDlnMTVHi1HSV_l76lmWnLOXv7fy76CrSG1ZMe9L7yGtdhsw-YjwsFteH4xlNJ34OdV_DXPuuUdTRZdDAzTTozowM6ti7csCXmiBzQLdrxctER3GeI9wxSXEWJ94J1ltglsRW3C2pqdpIZ-sj27mt8QPfMb-HF2ev31WzYIL2SeC7PASYc2vwnuiQ_MGoxzJ5UJubFBx9rXUdb1lCPWUsEF6V1dO-2EKJ2MiotY8Lew0bRN3AUWcm-nwuMkahxiI2M9piCBMjsrC5fzCeSr71_5gZWcxDFuq4ROclOR9SqyXjVYbwKfx0vuekqOf528Q6YZTxysMoH9lZGrIWi7KqGzEvEuDn8chzHcqIZim9guuwoBsZC5KVU5gXe9c4z3XvnU3tPPfA8vSsoJ0ga1fdhAO8UP8Mz_Xsy7-wP06Zk-SD79B5A08Dg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VgngceLQ8thQwEifUtIntdexji1oVsbtC6iL1ZvkVtKgkVbPL78fjZNMeaCVukZyXMjP2fBnP9wF8Glspk6BJhF4m44bTzFbSZd5IaZ1AdfOkWjIpZzN5fq6-b8De0AsTQkibz8I-HqZavm_cCn-VHZQlUpGIe3AflbPGXbfWUDPgsmvLyYsYwlTxvoZZ5OpgfjQ9xm1cYp8KVgiK-m_YAsoYyqvdWJCSwsrtyWZadE6e_d_rPoenfXJJDjtveAEbod6CJzcoB7fg4bQvpm_Dr7Pwe5G1q0ucLtrgSUw8Y0x7MjE2XJAk5Rl9oF6Sw9WyQcJLH65ITHIJYtZr5lliak_W5CakqchRaulH65OzxU8kaH4JP06O519Os156IXOMq2WcdnD7G2cOGcGMipFuRal8royXoXJVEFU1ZhFtld564WxVWWk5p1aEkvFQsFewWTd1eAPE586MuYvTqLIRHSnjYhLiMbczorA5G0G-_v7a9bzkKI9xoRM-yZVG62m0nu6tN4LPwyWXHSnHXSdvo2mGE3urjGB3bWTdh22rEz6jEfHG4Y_DcAw4rKKYOjSrVkdIzEWuaElH8LpzjuHea5_a-fczP8Cj0_l0oidfZ9_ewmOKGULarrYLm9Fm4R08cH-Wi_bqffLsv5RJ8ps
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=Semi-supervised+Stacked+Label+Consistent+Autoencoder+for+Reconstruction+and+Analysis+of+Biomedical+Signals&rft.jtitle=IEEE+transactions+on+biomedical+engineering&rft.au=Gogna%2C+Anupriya&rft.au=Majumdar%2C+Angshul&rft.au=Ward%2C+Rabab&rft.date=2017-09-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0018-9294&rft.eissn=1558-2531&rft.volume=64&rft.issue=9&rft.spage=2196&rft_id=info:doi/10.1109%2FTBME.2016.2631620&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9294&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9294&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9294&client=summon