SwinDAE: Electrocardiogram Quality Assessment Using 1D Swin Transformer and Denoising AutoEncoder

Objective: Electrocardiogram (ECG) signals have wide-ranging applications in various fields, and thus it is crucial to identify clean ECG signals under different sensors and collection scenarios. Despite the availability of a variety of deep learning algorithms for ECG quality assessment, these meth...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE journal of biomedical and health informatics Ročník 27; číslo 12; s. 5779 - 5790
Hlavní autoři: Chen, Guanyu, Shi, Tianyi, Xie, Baoxing, Zhao, Zhicheng, Meng, Zhu, Huang, Yadong, Dong, Jin
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.12.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:2168-2194, 2168-2208, 2168-2208
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Objective: Electrocardiogram (ECG) signals have wide-ranging applications in various fields, and thus it is crucial to identify clean ECG signals under different sensors and collection scenarios. Despite the availability of a variety of deep learning algorithms for ECG quality assessment, these methods still lack generalization across different datasets, hindering their widespread use. Methods: In this paper, an effective model named Swin Denoising AutoEncoder (SwinDAE) is proposed. Specifically, SwinDAE uses a DAE as the basic architecture, and incorporates a 1D Swin Transformer during the feature learning stage of the encoder and decoder. SwinDAE was first pre-trained on the public PTB-XL dataset after data augmentation, with the supervision of signal reconstruction loss and quality assessment loss. Specially, the waveform component localization loss is proposed in this paper and used for joint supervision, guiding the model to learn key information of signals. The model was then fine-tuned on the finely annotated BUT QDB dataset for quality assessment. Results: SwinDAE achieved 0.02-0.13 mean F1 score improvement on the BUT QDB dataset compared to multiple deep learning methods, and demonstrated applicability on two other datasets. Conclusion: The proposed SwinDAE shows strong generalization ability on different datasets, and surpasses other state-of-the-art deep learning methods on multiple evaluation metrics. In addition, the statistical analysis for SwinDAE prove the significance of the performance and the rationality of the prediction. Significance: SwinDAE can learn the commonality between high-quality ECG signals, exhibiting excellent performance in the application of cross-sensors and cross-collection scenarios.
AbstractList Electrocardiogram (ECG) signals have wide-ranging applications in various fields, and thus it is crucial to identify clean ECG signals under different sensors and collection scenarios. Despite the availability of a variety of deep learning algorithms for ECG quality assessment, these methods still lack generalization across different datasets, hindering their widespread use.OBJECTIVEElectrocardiogram (ECG) signals have wide-ranging applications in various fields, and thus it is crucial to identify clean ECG signals under different sensors and collection scenarios. Despite the availability of a variety of deep learning algorithms for ECG quality assessment, these methods still lack generalization across different datasets, hindering their widespread use.In this paper, an effective model named Swin Denoising AutoEncoder (SwinDAE) is proposed. Specifically, SwinDAE uses a DAE as the basic architecture, and incorporates a 1D Swin Transformer during the feature learning stage of the encoder and decoder. SwinDAE was first pre-trained on the public PTB-XL dataset after data augmentation, with the supervision of signal reconstruction loss and quality assessment loss. Specially, the waveform component localization loss is proposed in this paper and used for joint supervision, guiding the model to learn key information of signals. The model was then fine-tuned on the finely annotated BUT QDB dataset for quality assessment.METHODSIn this paper, an effective model named Swin Denoising AutoEncoder (SwinDAE) is proposed. Specifically, SwinDAE uses a DAE as the basic architecture, and incorporates a 1D Swin Transformer during the feature learning stage of the encoder and decoder. SwinDAE was first pre-trained on the public PTB-XL dataset after data augmentation, with the supervision of signal reconstruction loss and quality assessment loss. Specially, the waveform component localization loss is proposed in this paper and used for joint supervision, guiding the model to learn key information of signals. The model was then fine-tuned on the finely annotated BUT QDB dataset for quality assessment.SwinDAE achieved 0.02-0.13 mean F1 score improvement on the BUT QDB dataset compared to multiple deep learning methods, and demonstrated applicability on two other datasets.RESULTSSwinDAE achieved 0.02-0.13 mean F1 score improvement on the BUT QDB dataset compared to multiple deep learning methods, and demonstrated applicability on two other datasets.The proposed SwinDAE shows strong generalization ability on different datasets, and surpasses other state-of-the-art deep learning methods on multiple evaluation metrics. In addition, the statistical analysis for SwinDAE prove the significance of the performance and the rationality of the prediction.CONCLUSIONThe proposed SwinDAE shows strong generalization ability on different datasets, and surpasses other state-of-the-art deep learning methods on multiple evaluation metrics. In addition, the statistical analysis for SwinDAE prove the significance of the performance and the rationality of the prediction.SwinDAE can learn the commonality between high-quality ECG signals, exhibiting excellent performance in the application of cross-sensors and cross-collection scenarios.SIGNIFICANCESwinDAE can learn the commonality between high-quality ECG signals, exhibiting excellent performance in the application of cross-sensors and cross-collection scenarios.
Objective: Electrocardiogram (ECG) signals have wide-ranging applications in various fields, and thus it is crucial to identify clean ECG signals under different sensors and collection scenarios. Despite the availability of a variety of deep learning algorithms for ECG quality assessment, these methods still lack generalization across different datasets, hindering their widespread use. Methods: In this paper, an effective model named Swin Denoising AutoEncoder (SwinDAE) is proposed. Specifically, SwinDAE uses a DAE as the basic architecture, and incorporates a 1D Swin Transformer during the feature learning stage of the encoder and decoder. SwinDAE was first pre-trained on the public PTB-XL dataset after data augmentation, with the supervision of signal reconstruction loss and quality assessment loss. Specially, the waveform component localization loss is proposed in this paper and used for joint supervision, guiding the model to learn key information of signals. The model was then fine-tuned on the finely annotated BUT QDB dataset for quality assessment. Results: SwinDAE achieved 0.02–0.13 mean F1 score improvement on the BUT QDB dataset compared to multiple deep learning methods, and demonstrated applicability on two other datasets. Conclusion: The proposed SwinDAE shows strong generalization ability on different datasets, and surpasses other state-of-the-art deep learning methods on multiple evaluation metrics. In addition, the statistical analysis for SwinDAE prove the significance of the performance and the rationality of the prediction. Significance: SwinDAE can learn the commonality between high-quality ECG signals, exhibiting excellent performance in the application of cross-sensors and cross-collection scenarios.
Electrocardiogram (ECG) signals have wide-ranging applications in various fields, and thus it is crucial to identify clean ECG signals under different sensors and collection scenarios. Despite the availability of a variety of deep learning algorithms for ECG quality assessment, these methods still lack generalization across different datasets, hindering their widespread use. In this paper, an effective model named Swin Denoising AutoEncoder (SwinDAE) is proposed. Specifically, SwinDAE uses a DAE as the basic architecture, and incorporates a 1D Swin Transformer during the feature learning stage of the encoder and decoder. SwinDAE was first pre-trained on the public PTB-XL dataset after data augmentation, with the supervision of signal reconstruction loss and quality assessment loss. Specially, the waveform component localization loss is proposed in this paper and used for joint supervision, guiding the model to learn key information of signals. The model was then fine-tuned on the finely annotated BUT QDB dataset for quality assessment. SwinDAE achieved 0.02-0.13 mean F1 score improvement on the BUT QDB dataset compared to multiple deep learning methods, and demonstrated applicability on two other datasets. The proposed SwinDAE shows strong generalization ability on different datasets, and surpasses other state-of-the-art deep learning methods on multiple evaluation metrics. In addition, the statistical analysis for SwinDAE prove the significance of the performance and the rationality of the prediction. SwinDAE can learn the commonality between high-quality ECG signals, exhibiting excellent performance in the application of cross-sensors and cross-collection scenarios.
Author Chen, Guanyu
Zhao, Zhicheng
Xie, Baoxing
Huang, Yadong
Meng, Zhu
Dong, Jin
Shi, Tianyi
Author_xml – sequence: 1
  givenname: Guanyu
  orcidid: 0000-0002-1070-0911
  surname: Chen
  fullname: Chen, Guanyu
  email: louischen0104@foxmail.com
  organization: Beijing Academy of Blockchain and Edge Computing, Beijing, China
– sequence: 2
  givenname: Tianyi
  surname: Shi
  fullname: Shi, Tianyi
  email: sty0622@bupt.edu.cn
  organization: Beijing University of Posts and Telecommunications, Beijing, China
– sequence: 3
  givenname: Baoxing
  surname: Xie
  fullname: Xie, Baoxing
  email: xiebaoxing@bupt.edu.cn
  organization: Beijing University of Posts and Telecommunications, Beijing, China
– sequence: 4
  givenname: Zhicheng
  orcidid: 0000-0001-6506-7298
  surname: Zhao
  fullname: Zhao, Zhicheng
  email: zhaozc@bupt.edu.cn
  organization: Beijing University of Posts and Telecommunications, Beijing, China
– sequence: 5
  givenname: Zhu
  orcidid: 0000-0002-7519-4124
  surname: Meng
  fullname: Meng, Zhu
  email: bamboo@bupt.edu.cn
  organization: Beijing University of Posts and Telecommunications, Beijing, China
– sequence: 6
  givenname: Yadong
  surname: Huang
  fullname: Huang, Yadong
  email: huang-yd14@tsinghua.org.cn
  organization: Zhoushan Academy of Marine Data Science, Zhoushan, China
– sequence: 7
  givenname: Jin
  surname: Dong
  fullname: Dong, Jin
  email: jin_tung@hotmail.com
  organization: Beijing Academy of Blockchain and Edge Computing, Beijing, China
BackLink https://www.ncbi.nlm.nih.gov/pubmed/37698969$$D View this record in MEDLINE/PubMed
BookMark eNp9kU1rGzEQhkVJyVfzAwqlCHrpxa4-drVSb07sJimBUpKchawdBYVdKZW0lPz7yrENJYfoMmJ4nmGY9wQdhBgAoY-UzCkl6tvP86vrOSOMzzmnjVDyHTpmVMgZY0Qe7P9UNUfoLOdHUp-sLSUO0RHvKq-EOkbm9q8Py8XqO14NYEuK1qTex4dkRvx7MoMvz3iRM-Q8Qij4PvvwgOkSbzR8l0zILqYREjahx0sI0b8Qi6nEVbCxh_QBvXdmyHC2q6fo_sfq7uJqdvPr8vpicTOzvCVlZp2EVorO2VathQFh6rLMUsfXTWuEM0b0re0s9MxCq6Rk0jJuiFqTzvWO8lP0dTv3KcU_E-SiR58tDIMJEKesmRSNoFJSWdEvr9DHOKVQt6uUUow0bccq9XlHTesRev2U_GjSs94frwLdFrAp5pzAaeuLKT6GkowfNCV6k5TeJKU3SeldUtWkr8z98LecT1vHA8B_PGu6llP-D75-neE
CODEN IJBHA9
CitedBy_id crossref_primary_10_1109_TFUZZ_2025_3573405
crossref_primary_10_1109_ACCESS_2025_3531705
crossref_primary_10_1016_j_dsp_2025_105053
crossref_primary_10_1016_j_measurement_2025_118743
crossref_primary_10_1016_j_compeleceng_2025_110177
crossref_primary_10_1109_TIM_2024_3368495
crossref_primary_10_1016_j_bspc_2024_106668
crossref_primary_10_1016_j_jnca_2025_104279
crossref_primary_10_1109_TIM_2025_3533644
crossref_primary_10_1145_3749457
Cites_doi 10.1109/iciinfs.2017.8300342
10.23919/CinC53138.2021.9662919
10.1016/j.patrec.2018.03.028
10.1016/j.cmpb.2021.106269
10.1109/TBME.2015.2422378
10.1109/51.932724
10.1016/j.jbi.2023.104556
10.1109/ICCV48922.2021.00986
10.1109/TPAMI.2018.2858826
10.1109/JBHI.2016.2615316
10.1088/0967-3334/33/9/1419
10.1016/j.aap.2022.106830
10.1109/EMBC.2018.8513537
10.1109/CVPR.2016.207
10.1109/RBME.2015.2414661
10.3758/s13428-020-01516-y
10.2307/2531595
10.3389/fphys.2022.905447
10.1145/1961189.1961199
10.18653/v1/2021.findings-emnlp.59
10.1145/1390156.1390294
10.1038/s41597-020-0495-6
10.1109/TBME.2021.3108621
10.1145/3065386
10.1109/TAFFC.2020.3014842
10.1016/j.bspc.2022.104064
10.1016/j.bbe.2023.01.006
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
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
K9.
KR7
L7M
L~C
L~D
NAPCQ
P64
7X8
DOI 10.1109/JBHI.2023.3314698
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
ProQuest Health & Medical Complete (Alumni)
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Nursing & Allied Health Premium
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
ProQuest Health & Medical Complete (Alumni)
Ceramic Abstracts
Materials Business File
METADEX
Biotechnology and BioEngineering Abstracts
Computer and Information Systems Abstracts Professional
Aerospace Database
Nursing & Allied Health Premium
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 MEDLINE - Academic
Materials Research Database

MEDLINE
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/IET Electronic Library (IEL) (UW System Shared)
  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
EISSN 2168-2208
EndPage 5790
ExternalDocumentID 37698969
10_1109_JBHI_2023_3314698
10247531
Genre orig-research
Research Support, Non-U.S. Gov't
Journal Article
GrantInformation_xml – fundername: National Key Research and Development Program of China
  grantid: 2022YFC0868500
– fundername: Zhoushan Academy of Marine Data Science
GroupedDBID 0R~
4.4
6IF
6IH
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
ACPRK
AENEX
AFRAH
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
HZ~
IFIPE
IPLJI
JAVBF
M43
O9-
OCL
PQQKQ
RIA
RIE
RNS
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
RIG
7QF
7QO
7QQ
7SC
7SE
7SP
7SR
7TA
7TB
7U5
8BQ
8FD
F28
FR3
H8D
JG9
JQ2
K9.
KR7
L7M
L~C
L~D
NAPCQ
P64
7X8
ID FETCH-LOGICAL-c350t-cf8e5867fc59b6ae6a1682c1f3b45a6faa6d5c7ced2ce598828c23a09b07fdf13
IEDL.DBID RIE
ISICitedReferencesCount 14
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001147165700009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2168-2194
2168-2208
IngestDate Sat Sep 27 21:13:45 EDT 2025
Sun Nov 09 08:02:53 EST 2025
Mon Jul 21 05:51:29 EDT 2025
Sat Nov 29 04:18:34 EST 2025
Tue Nov 18 21:49:30 EST 2025
Wed Aug 27 02:36:17 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 12
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-c350t-cf8e5867fc59b6ae6a1682c1f3b45a6faa6d5c7ced2ce598828c23a09b07fdf13
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-7519-4124
0000-0001-6506-7298
0000-0002-1070-0911
PMID 37698969
PQID 2899204572
PQPubID 85417
PageCount 12
ParticipantIDs crossref_citationtrail_10_1109_JBHI_2023_3314698
ieee_primary_10247531
proquest_journals_2899204572
crossref_primary_10_1109_JBHI_2023_3314698
proquest_miscellaneous_2864618818
pubmed_primary_37698969
PublicationCentury 2000
PublicationDate 2023-12-01
PublicationDateYYYYMMDD 2023-12-01
PublicationDate_xml – month: 12
  year: 2023
  text: 2023-12-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Piscataway
PublicationTitle IEEE journal of biomedical and health informatics
PublicationTitleAbbrev JBHI
PublicationTitleAlternate IEEE J Biomed Health Inform
PublicationYear 2023
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
ref12
ref34
ref15
ref14
ref11
ref10
ref2
ref1
ref17
ref16
ref19
ref18
Silva (ref5) 2011
Zheng (ref32) 2022
Moody (ref33) 1984; 11
ref24
ref23
ref25
ref20
ref21
Liu (ref31) 2023
ref28
ref27
ref29
ref8
ref7
Vaswani (ref22) 2017
Lilly (ref26) 2015
ref9
Nemcova (ref30) 2020; 101
ref4
ref3
ref6
References_xml – ident: ref8
  doi: 10.1109/iciinfs.2017.8300342
– year: 2023
  ident: ref31
  article-title: OpenDriver: An open-road driver state detection dataset
– ident: ref12
  doi: 10.23919/CinC53138.2021.9662919
– ident: ref3
  doi: 10.1016/j.patrec.2018.03.028
– ident: ref11
  doi: 10.1016/j.cmpb.2021.106269
– volume-title: Pathophysiology of Heart Disease: A Collaborative Project of Medical Students and Faculty
  year: 2015
  ident: ref26
– ident: ref2
  doi: 10.1109/TBME.2015.2422378
– ident: ref10
  doi: 10.1109/51.932724
– start-page: 5999
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  year: 2017
  ident: ref22
  article-title: Attention is all you need
– ident: ref19
  doi: 10.1016/j.jbi.2023.104556
– ident: ref20
  doi: 10.1109/ICCV48922.2021.00986
– ident: ref28
  doi: 10.1109/TPAMI.2018.2858826
– ident: ref7
  doi: 10.1109/JBHI.2016.2615316
– ident: ref6
  doi: 10.1088/0967-3334/33/9/1419
– volume-title: PhysioNet
  year: 2022
  ident: ref32
  article-title: A large scale 12-lead electrocardiodiogram database for arrhythmia study
– ident: ref18
  doi: 10.1016/j.aap.2022.106830
– ident: ref9
  doi: 10.1109/EMBC.2018.8513537
– ident: ref25
  doi: 10.1109/CVPR.2016.207
– ident: ref1
  doi: 10.1109/RBME.2015.2414661
– ident: ref27
  doi: 10.3758/s13428-020-01516-y
– ident: ref34
  doi: 10.2307/2531595
– ident: ref15
  doi: 10.3389/fphys.2022.905447
– volume: 101
  start-page: e215
  year: 2020
  ident: ref30
  article-title: Brno University of Technology ECG quality database (BUT QDB)
  publication-title: PhysioNet
– ident: ref21
  doi: 10.1145/1961189.1961199
– ident: ref23
  doi: 10.18653/v1/2021.findings-emnlp.59
– volume: 11
  start-page: 381
  issue: 3
  year: 1984
  ident: ref33
  article-title: Noise stress test for arrhythmia detectors
  publication-title: Comput. Cardiol.
– ident: ref24
  doi: 10.1145/1390156.1390294
– ident: ref29
  doi: 10.1038/s41597-020-0495-6
– start-page: 273
  volume-title: Proc. IEEE Comput. Cardiol.
  year: 2011
  ident: ref5
  article-title: Improving the quality of ECGs collected using mobile phones: The PhysioNet/Computing in Cardiology Challenge
– ident: ref14
  doi: 10.1109/TBME.2021.3108621
– ident: ref13
  doi: 10.1145/3065386
– ident: ref4
  doi: 10.1109/TAFFC.2020.3014842
– ident: ref16
  doi: 10.1016/j.bspc.2022.104064
– ident: ref17
  doi: 10.1016/j.bbe.2023.01.006
SSID ssj0000816896
Score 2.4653635
Snippet Objective: Electrocardiogram (ECG) signals have wide-ranging applications in various fields, and thus it is crucial to identify clean ECG signals under...
Electrocardiogram (ECG) signals have wide-ranging applications in various fields, and thus it is crucial to identify clean ECG signals under different sensors...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 5779
SubjectTerms Algorithms
Benchmarking
Commonality
Data augmentation
Data models
Datasets
Deep learning
Denoising AutoEncoder
ECG quality assessment
EKG
Electric Power Supplies
Electrocardiography
Encoding
Feature extraction
Humans
Localization
Machine learning
Noise reduction
Quality assessment
Quality control
Research Design
Sensitivity
Sensors
Signal quality
Signal reconstruction
Statistical analysis
swin Transfromer
Teaching methods
Transfer learning
Transformers
waveform component localization
Waveforms
Title SwinDAE: Electrocardiogram Quality Assessment Using 1D Swin Transformer and Denoising AutoEncoder
URI https://ieeexplore.ieee.org/document/10247531
https://www.ncbi.nlm.nih.gov/pubmed/37698969
https://www.proquest.com/docview/2899204572
https://www.proquest.com/docview/2864618818
Volume 27
WOSCitedRecordID wos001147165700009&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) (UW System Shared)
  customDbUrl:
  eissn: 2168-2208
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816896
  issn: 2168-2194
  databaseCode: RIE
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3da9RAEB-0SOmLH22t0Vq24JOQa7LZbLK-nd6VKloEW7i3sB-zcFCScr1T_O_d2eSCPrTgWyCzyTIf7MzOxw_gXVYr6wkjzJSOp8Jpk5ocyzQzrgjnIRpvYqPw1-rysl4s1PehWT32wiBiLD7DCT3GXL7r7IauyoKFcxHc6xDsPK4q2TdrjRcqEUEi4nHx8JAGSxRDFjPP1NmXjxefJwQVPimKnFAT92A32JYKK9Q_R1LEWLnf3YzHzvmz_9zwc3g6-Jds2ivEC3iE7T7sfhsy6Aegf_xatrPp_AOb9wA4NhakUo0W6-dp_GbTcVonixUFLJ8xWsautl4urphuHZth2y0jxXSz7uYt9cevDuH6fH716SIdYBZSW5TZOrW-xrKWlbelMlKj1IF_3Oa-MKLU0mstXWkri45Tz1ZwyWvLC50pk1Xe-bx4CTtt1-IrYM6GWLukFjethOW1NhhCJC4xcFoI4RPItpxu7DCDnKAwbpoYi2SqITk1JKdmkFMC78clt_0AjoeID0kIfxH2_E_geCvPZrDRu4ZCTRrGX_EETsfXwbooZaJb7DZEI4XM6-DVJHDU68H48a36vL7np29gj_bW174cw856tcG38MT-XC_vVidBhRf1SVThP8sJ6gE
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3di9NAEB_klLMvft550VNX8ElIb7PZTbK-Vdujp70iWOHewn5CQZKj1yr-9-5s0qAPJ_gWyGyyzAc7s_PxA3hLK2k8YoRpYVnKrdKpzpxIqbZ5OA-d9jo2Ci_K5bK6upJf-mb12AvjnIvFZ26MjzGXb1uzw6uyYOGMB_c6BDt3BeeMdu1aw5VKxJCIiFwsPKTBFnmfx8yoPPv0YX4xRrDwcZ5niJs4gsNgXTKskH8dShFl5XaHMx485w__c8uP4EHvYZJJpxKP4Y5rnsDhZZ9Dfwrq6891M53M3pNZB4FjYkkqVmmRbqLGLzIZ5nWSWFNAsinBZWS193PdhqjGkqlr2nWkmOy27azBDvnNEXw7n60-ztMeaCE1uaDb1PjKiaoovRFSF8oVKvCPmcznmgtVeKUKK0xpnGXYtRWc8sqwXFGpaemtz_JjOGjaxp0AsSZE2wKb3JTkhlVKuxAkscIFTnPOfQJ0z-na9FPIEQzjex2jESprlFONcqp7OSXwblhy3Y3g-BfxEQrhD8KO_wmc7uVZ91Z6U2OwieP4S5bAm-F1sC9MmqjGtTukKXiRVcGvSeBZpwfDx_fq8_yWn76G-_PV5aJeXCw_v4AR7rOrhDmFg-1m517CPfNju77ZvIqK_BubDuxg
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=SwinDAE%3A+Electrocardiogram+Quality+Assessment+Using+1D+Swin+Transformer+and+Denoising+AutoEncoder&rft.jtitle=IEEE+journal+of+biomedical+and+health+informatics&rft.au=Chen%2C+Guanyu&rft.au=Shi%2C+Tianyi&rft.au=Xie%2C+Baoxing&rft.au=Zhao%2C+Zhicheng&rft.date=2023-12-01&rft.pub=IEEE&rft.issn=2168-2194&rft.volume=27&rft.issue=12&rft.spage=5779&rft.epage=5790&rft_id=info:doi/10.1109%2FJBHI.2023.3314698&rft_id=info%3Apmid%2F37698969&rft.externalDocID=10247531
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2168-2194&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2168-2194&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2168-2194&client=summon