Attention-Based Convolutional Denoising Autoencoder for Two-Lead ECG Denoising and Arrhythmia Classification

This article presents a fast and accurate electrocardiogram (ECG) denoising and classification method for low-quality ECG signals. To achieve this, a novel attention-based convolutional denoising autoencoder (ACDAE) model is proposed that utilizes a skip-layer and attention module for reliable recon...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on instrumentation and measurement Jg. 71; S. 1 - 10
Hauptverfasser:	Singh, Prateek, Sharma, Ambalika
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York IEEE 2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Arrhythmia Arrhythmias atrial fibrillation (AF) Cardiac stress tests Classification Codes Convolution convolutional neural network (CNN) denoising autoencoder (DAE) electrocardiogram (ECG) Electrocardiography Feature extraction Modules Noise reduction Random noise Recording Signal quality Signal to noise ratio
ISSN:	0018-9456, 1557-9662
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	This article presents a fast and accurate electrocardiogram (ECG) denoising and classification method for low-quality ECG signals. To achieve this, a novel attention-based convolutional denoising autoencoder (ACDAE) model is proposed that utilizes a skip-layer and attention module for reliable reconstruction of ECG signals from extreme noise conditions. Skip-layer connections are used to reduce information loss while reconstructing the original signal, and a lightweight, efficient channel attention (ECA) module is used to update relevant features retrieved via cross-channel interaction efficiently. The model is trained and tested using four widely available databases. For evaluation, the signals are mixed with simulated additive white Gaussian noise (AWGN) ranging from −20 to 20 dB and the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) noise stress test database (NSTDB) noise ranging from −6 to 24 dB. The model outperformed the most cited published works, achieving an average signal-to-noise ratio (SNR) improvement of 19.07 ± 1.67 and a percentage-root-mean-square difference (PRD) of 11.0 % at 0-dB SNR. The model classification performance on 60 000 beats is 98.76% ± 0.44% precision, 98.48% ± 0.58% recall, and 98.88% ± 0.42% accuracy, respectively, using a stratified fivefold cross-validation strategy.
AbstractList	This article presents a fast and accurate electrocardiogram (ECG) denoising and classification method for low-quality ECG signals. To achieve this, a novel attention-based convolutional denoising autoencoder (ACDAE) model is proposed that utilizes a skip-layer and attention module for reliable reconstruction of ECG signals from extreme noise conditions. Skip-layer connections are used to reduce information loss while reconstructing the original signal, and a lightweight, efficient channel attention (ECA) module is used to update relevant features retrieved via cross-channel interaction efficiently. The model is trained and tested using four widely available databases. For evaluation, the signals are mixed with simulated additive white Gaussian noise (AWGN) ranging from −20 to 20 dB and the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) noise stress test database (NSTDB) noise ranging from −6 to 24 dB. The model outperformed the most cited published works, achieving an average signal-to-noise ratio (SNR) improvement of 19.07 ± 1.67 and a percentage-root-mean-square difference (PRD) of 11.0 % at 0-dB SNR. The model classification performance on 60 000 beats is 98.76% ± 0.44% precision, 98.48% ± 0.58% recall, and 98.88% ± 0.42% accuracy, respectively, using a stratified fivefold cross-validation strategy.
Author	Singh, Prateek Sharma, Ambalika
Author_xml	– sequence: 1 givenname: Prateek orcidid: 0000-0002-8398-9867 surname: Singh fullname: Singh, Prateek email: psingh@ee.iitr.ac.in organization: Electrical Engineering Department, Indian Institute of Technology Roorkee, Roorkee, India – sequence: 2 givenname: Ambalika orcidid: 0000-0002-7112-8410 surname: Sharma fullname: Sharma, Ambalika organization: Electrical Engineering Department, Indian Institute of Technology Roorkee, Roorkee, India
BookMark	eNp9kMFLwzAUxoNMcJveBS8Fz51JmjTNsdY5BxMv81yyNHEZXTKTVNl_b-eGiAdPDx7f73vv-0ZgYJ1VAFwjOEEI8rvl_HmCIcaTDHHGKDsDQ0QpS3me4wEYQoiKlBOaX4BRCBsIIcsJG4K2jFHZaJxN70VQTVI5--Ha7rARbfKgrDPB2Lek7KJTVrpG-UQ7nyw_XbpQokmm1eyXTNgmKb1f7-N6a0RStSIEo40UB8NLcK5FG9TVaY7B6-N0WT2li5fZvCoXqcQcxZQiwjTnSvKiYFLIlV5hzSGTKwRXOcGU64wI0qdVvGCa5lwi3TAlIckYISwbg9uj7867906FWG9c5_s8ocYM0oJiQmmvgkeV9C4Er3S982Yr_L5GsD50Wved1odO61OnPZL_QaSJ39GiF6b9D7w5gkYp9XOHFzTL-6e_AG6xhkE
CODEN	IEIMAO
CitedBy_id	crossref_primary_10_1109_TIFS_2023_3346647 crossref_primary_10_1155_2022_5054641 crossref_primary_10_1109_TIM_2025_3551836 crossref_primary_10_1109_JBHI_2024_3355960 crossref_primary_10_1016_j_bspc_2024_107225 crossref_primary_10_1080_03772063_2025_2470375 crossref_primary_10_1109_TIM_2024_3406829 crossref_primary_10_1109_TIM_2025_3552477 crossref_primary_10_1109_TCSI_2025_3533544 crossref_primary_10_1109_JSEN_2024_3397656 crossref_primary_10_1109_TIM_2024_3400302 crossref_primary_10_1109_TIM_2025_3545169 crossref_primary_10_1109_ACCESS_2025_3550949 crossref_primary_10_3390_s24061959 crossref_primary_10_1109_TBME_2023_3307400 crossref_primary_10_1016_j_engappai_2023_106713 crossref_primary_10_1109_TIM_2023_3335528 crossref_primary_10_1109_TIM_2022_3204316 crossref_primary_10_1371_journal_pone_0326079 crossref_primary_10_1109_TIM_2023_3251408 crossref_primary_10_1109_TIM_2024_3522425 crossref_primary_10_1109_TIM_2024_3376017 crossref_primary_10_1109_TIM_2025_3551006 crossref_primary_10_1109_TIM_2025_3574904 crossref_primary_10_1016_j_bspc_2023_104863 crossref_primary_10_1109_TIM_2025_3570370 crossref_primary_10_1038_s41598_025_93906_5 crossref_primary_10_1109_TIM_2023_3312698 crossref_primary_10_3390_bios14040183 crossref_primary_10_1109_TIM_2024_3368495
Cites_doi	10.1109/TIM.2019.2910342 10.1016/j.bspc.2013.01.005 10.1109/JBHI.2017.2706298 10.1088/0967-3334/37/12/2214 10.1016/j.bspc.2020.102194 10.1016/j.compbiomed.2015.03.005 10.1177/2048872616661693 10.1016/j.bspc.2011.11.003 10.1109/TIM.2021.3126019 10.1109/cvpr42600.2020.01155 10.1016/j.compbiomed.2017.12.007 10.1109/INDICON.2017.8488064 10.1109/TIM.2019.2917735 10.1109/ICCV.2017.74 10.1109/TIM.2020.3027930 10.1016/j.bspc.2021.103431 10.1161/01.CTR.101.23.e215 10.1109/CSPA48992.2020.9068696 10.1109/ACCESS.2019.2912036 10.1109/TBME.2003.821031 10.1109/TIM.2020.3039614 10.1145/1390156.1390294 10.1016/j.eswa.2018.07.030 10.1016/j.eswa.2018.08.011 10.1109/TIM.2019.2922054 10.1109/10.959322 10.1109/ACCESS.2020.3012904 10.1016/j.engappai.2016.02.015 10.1109/CVPR.2018.00745 10.1049/iet-spr.2020.0104 10.1109/MECBME.2014.6783250 10.1016/j.bspc.2021.102992 10.1088/1361-6579/ac34ea
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SP 7U5 8FD L7M
DOI	10.1109/TIM.2022.3197757
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Electronics & Communications Abstracts Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Solid State and Superconductivity Abstracts Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Solid State and Superconductivity Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Physics
EISSN	1557-9662
EndPage	10
ExternalDocumentID	10_1109_TIM_2022_3197757 9853604
Genre	orig-research
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 85S 8WZ 97E A6W AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TN5 TWZ VH1 VJK AAYXX CITATION 7SP 7U5 8FD L7M
ID	FETCH-LOGICAL-c291t-5147f99ec9887cacbfb2f907cb10b64259f34a4202e987f569c1fd7ec04374473
IEDL.DBID	RIE
ISICitedReferencesCount	71
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000844142300003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-9456
IngestDate	Mon Jun 30 10:11:27 EDT 2025 Sat Nov 29 04:38:25 EST 2025 Tue Nov 18 22:18:25 EST 2025 Wed Aug 27 02:28:35 EDT 2025
IsPeerReviewed	true
IsScholarly	true
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-5147f99ec9887cacbfb2f907cb10b64259f34a4202e987f569c1fd7ec04374473
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-8398-9867 0000-0002-7112-8410
PQID	2705852455
PQPubID	85462
PageCount	10
ParticipantIDs	crossref_primary_10_1109_TIM_2022_3197757 ieee_primary_9853604 proquest_journals_2705852455 crossref_citationtrail_10_1109_TIM_2022_3197757
PublicationCentury	2000
PublicationDate	20220000 2022-00-00 20220101
PublicationDateYYYYMMDD	2022-01-01
PublicationDate_xml	– year: 2022 text: 20220000
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on instrumentation and measurement
PublicationTitleAbbrev	TIM
PublicationYear	2022
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	ref13 ref35 ref12 ref34 ref15 ref37 ref14 ref36 ref31 ref11 ref33 ref10 ref32 ref2 ref16 ref38 ref19 ref18 (ref1) 2014 Moody (ref20) 1984; 11 ref24 ref23 Mao (ref17); 29 ref26 ref25 ref22 ref28 ref27 Carreiras (ref21) 2015 ref29 O’Malley (ref30) 2019 ref8 ref7 ref9 ref4 ref3 ref6 ref5
References_xml	– ident: ref23 doi: 10.1109/TIM.2019.2910342 – ident: ref5 doi: 10.1016/j.bspc.2013.01.005 – ident: ref33 doi: 10.1109/JBHI.2017.2706298 – ident: ref12 doi: 10.1088/0967-3334/37/12/2214 – ident: ref37 doi: 10.1016/j.bspc.2020.102194 – ident: ref35 doi: 10.1016/j.compbiomed.2015.03.005 – ident: ref2 doi: 10.1177/2048872616661693 – ident: ref10 doi: 10.1016/j.bspc.2011.11.003 – volume-title: World Health Organization year: 2014 ident: ref1 article-title: Global status report on noncommunicable diseases 2014 – ident: ref25 doi: 10.1109/TIM.2021.3126019 – ident: ref29 doi: 10.1109/cvpr42600.2020.01155 – ident: ref36 doi: 10.1016/j.compbiomed.2017.12.007 – ident: ref8 doi: 10.1109/INDICON.2017.8488064 – ident: ref24 doi: 10.1109/TIM.2019.2917735 – volume: 29 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref17 article-title: Image restoration using very deep convolutional encoder–decoder networks with symmetric skip connections – ident: ref34 doi: 10.1109/ICCV.2017.74 – ident: ref3 doi: 10.1109/TIM.2020.3027930 – ident: ref31 doi: 10.1016/j.bspc.2021.103431 – ident: ref19 doi: 10.1161/01.CTR.101.23.e215 – ident: ref7 doi: 10.1109/CSPA48992.2020.9068696 – ident: ref14 doi: 10.1109/ACCESS.2019.2912036 – ident: ref9 doi: 10.1109/TBME.2003.821031 – volume: 11 start-page: 381 issue: 3 year: 1984 ident: ref20 article-title: A noise stress test for arrhythmia detectors publication-title: Comput. Cardiol. – ident: ref26 doi: 10.1109/TIM.2020.3039614 – volume-title: BioSPPy: Biosignal Processing in Python year: 2015 ident: ref21 – ident: ref27 doi: 10.1145/1390156.1390294 – ident: ref11 doi: 10.1016/j.eswa.2018.07.030 – ident: ref38 doi: 10.1016/j.eswa.2018.08.011 – ident: ref4 doi: 10.1109/TIM.2019.2922054 – ident: ref6 doi: 10.1109/10.959322 – ident: ref22 doi: 10.1109/ACCESS.2020.3012904 – volume-title: Kerastuner year: 2019 ident: ref30 – ident: ref13 doi: 10.1016/j.engappai.2016.02.015 – ident: ref28 doi: 10.1109/CVPR.2018.00745 – ident: ref18 doi: 10.1049/iet-spr.2020.0104 – ident: ref32 doi: 10.1109/MECBME.2014.6783250 – ident: ref15 doi: 10.1016/j.bspc.2021.102992 – ident: ref16 doi: 10.1088/1361-6579/ac34ea
SSID	ssj0007647
Score	2.5668187
Snippet	This article presents a fast and accurate electrocardiogram (ECG) denoising and classification method for low-quality ECG signals. To achieve this, a novel...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Arrhythmia Arrhythmias atrial fibrillation (AF) Cardiac stress tests Classification Codes Convolution convolutional neural network (CNN) denoising autoencoder (DAE) electrocardiogram (ECG) Electrocardiography Feature extraction Modules Noise reduction Random noise Recording Signal quality Signal to noise ratio
Title	Attention-Based Convolutional Denoising Autoencoder for Two-Lead ECG Denoising and Arrhythmia Classification
URI	https://ieeexplore.ieee.org/document/9853604 https://www.proquest.com/docview/2705852455
Volume	71
WOSCitedRecordID	wos000844142300003&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/IET Electronic Library (IEL) customDbUrl: eissn: 1557-9662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0007647 issn: 0018-9456 databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFH_MoaAHPzbF6ZQevAjWtV26LMc5NxV0eJiwW2nzwQazla6b-N_7knZloAjeeshHyS_Je7_k5fcArijryjYRxHYiypCgKM-OlIps5GGuTkClBDcPhZ_paNSdTNhrBW7KtzBSShN8Jm_1p7nLFwlf6qOyFkPb0tHin1uU0vytVrnr0g7J9TFdXMDoFayvJB3WGj-9IBH0POSn6O1oQ7RhgkxOlR8bsbEuw4P__dch7BdepNXLYT-CioxrsLehLViDHRPbyRd1mPeyLA9qtO_QZgmrn8SrYsZhI_cyTmb6xMDqLbNE61oKmVroy1rjz8TWKTitQf9ho1gYC-w5nX5l0_dZaJm0mjrgyGB8DG_Dwbj_aBdJFmzuMTez0WGiijHJGW43POSRijyFSPHIdSIkJz5TbRISHD_JulT5HcZdJajkWhSJENo-gWqcxPIULBwETkNc0lpvuCvQ2fBF5HFfdUJOSBg2oLUe94AXCuQ6EcY8MEzEYQEiFWikggKpBlyXNT5y9Y0_ytY1MmW5ApQGNNfQBsXyXAQedZAmecT3z36vdQ67uu38rKUJ1SxdygvY5qtstkgvzcz7BgdN1ko
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JTsMwEB1VLAIOLAVEWXPggkRo4jp1fSxlaUWpOBSJW5R4USuVBLVpEX_P2EmrSiAkbjl4ifxszzx7_AbgkvGGqlFJXS9mHAmKJm6sdewiD_NNAiothX0o3GW9XuPtjb-U4HrxFkYpZYPP1I35tHf5MhVTc1RW5Whb6kb8czWglPj5a63FvsvqNFfI9HEJo18wv5T0eLXfeUYqSAgyVPR3jClaMkI2q8qPrdjal4ed__3ZLmwXfqTTzIHfg5JKyrC1pC5YhnUb3Skm-zBqZlke1ujeotWSTitNZsWcw0buVJIOzZmB05xmqVG2lGrsoDfr9D9T1yThdO5bj0vFokRiz-PBVzZ4H0aOTaxpQo4sygfw-nDfb7XdIs2CKwj3MxddJqY5V4LjhiMiEeuYaMRKxL4XIz0JuK7RiOL4Kd5gOqhz4WvJlDCySJSy2iGsJGmijsDBQRAswkVtFIcbEt2NQMZEBLoeCUqjqALV-biHotAgN6kwRqHlIh4PEanQIBUWSFXgalHjI9ff-KPsvkFmUa4ApQKnc2jDYoFOQsI8JEqEBsHx77UuYKPdf-6G3U7v6QQ2TT_5ycsprGTjqTqDNTHLhpPxuZ2F31UW2ZE
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=Attention-Based+Convolutional+Denoising+Autoencoder+for+Two-Lead+ECG+Denoising+and+Arrhythmia+Classification&rft.jtitle=IEEE+transactions+on+instrumentation+and+measurement&rft.au=Singh%2C+Prateek&rft.au=Sharma%2C+Ambalika&rft.date=2022&rft.pub=IEEE&rft.issn=0018-9456&rft.volume=71&rft.spage=1&rft.epage=10&rft_id=info:doi/10.1109%2FTIM.2022.3197757&rft.externalDocID=9853604
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9456&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9456&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9456&client=summon