Arrhythmia classification algorithm based on multi-head self-attention mechanism

•ECG signal preprocessing method based on wavelet transform to reduce noise.•Linear projection layer is designed to acquire semantic features of ECG signal.•Novel position encoding is proposed to obtain time and voltage series information.•Novel arrhythmia classification algorithm based on multihead...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Biomedical signal processing and control Jg. 79; S. 104206
Hauptverfasser: Wang, Yue, Yang, Guanci, Li, Shaobo, Li, Yang, He, Ling, Liu, Dan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.01.2023
Schlagworte:
ISSN:1746-8094, 1746-8108
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract •ECG signal preprocessing method based on wavelet transform to reduce noise.•Linear projection layer is designed to acquire semantic features of ECG signal.•Novel position encoding is proposed to obtain time and voltage series information.•Novel arrhythmia classification algorithm based on multihead self-attention mechanism.•The proposed ACA-MA outperforms other state-of-the-art methods. Cardiovascular disease is a major illness that causes human death, especially in the elderly. Timely and accurate diagnosis of arrhythmia types is the key to early prevention and diagnosis of cardiovascular diseases. This paper proposed an arrhythmia classification algorithm based on multi-head self-attention mechanism (ACA-MA). First, an ECG signal preprocessing algorithm based on wavelet transform is put forward and implemented using db6 wavelet transform to focus on improving the data quality of ECG signals and reduce the noise of ECG signals. Second, a linear projection layer for acquiring semantic features of ECG signals is designed using the matching relationship between ECG tag and segmented ECG signals. Third, a position encoding-based spatiotemporal characterization method of ECG signal sequences is designed to integrate time series information into a matrix operation. Fourth, a multi-head self-attentive mechanism capable of capturing global contextual information is proposed to extract relationships and semantic features between ECG segments and achieve semantic association and information stitching of nonadjacent ECG signals. Finally, experimental results on the arrhythmia dataset MIT/BIH show that ACA-MA outperforms other state-of-the-art methods with an overall classification accuracy of 99.4%, a specific rate of 99.41%, and a sensitivity of 97.36%.
AbstractList •ECG signal preprocessing method based on wavelet transform to reduce noise.•Linear projection layer is designed to acquire semantic features of ECG signal.•Novel position encoding is proposed to obtain time and voltage series information.•Novel arrhythmia classification algorithm based on multihead self-attention mechanism.•The proposed ACA-MA outperforms other state-of-the-art methods. Cardiovascular disease is a major illness that causes human death, especially in the elderly. Timely and accurate diagnosis of arrhythmia types is the key to early prevention and diagnosis of cardiovascular diseases. This paper proposed an arrhythmia classification algorithm based on multi-head self-attention mechanism (ACA-MA). First, an ECG signal preprocessing algorithm based on wavelet transform is put forward and implemented using db6 wavelet transform to focus on improving the data quality of ECG signals and reduce the noise of ECG signals. Second, a linear projection layer for acquiring semantic features of ECG signals is designed using the matching relationship between ECG tag and segmented ECG signals. Third, a position encoding-based spatiotemporal characterization method of ECG signal sequences is designed to integrate time series information into a matrix operation. Fourth, a multi-head self-attentive mechanism capable of capturing global contextual information is proposed to extract relationships and semantic features between ECG segments and achieve semantic association and information stitching of nonadjacent ECG signals. Finally, experimental results on the arrhythmia dataset MIT/BIH show that ACA-MA outperforms other state-of-the-art methods with an overall classification accuracy of 99.4%, a specific rate of 99.41%, and a sensitivity of 97.36%.
ArticleNumber 104206
Author He, Ling
Wang, Yue
Li, Shaobo
Li, Yang
Yang, Guanci
Liu, Dan
Author_xml – sequence: 1
  givenname: Yue
  surname: Wang
  fullname: Wang, Yue
  organization: The Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education, Guizhou University, Guiyang, China
– sequence: 2
  givenname: Guanci
  surname: Yang
  fullname: Yang, Guanci
  email: gcyang@gzu.edu.cn
  organization: The Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education, Guizhou University, Guiyang 550025, China
– sequence: 3
  givenname: Shaobo
  surname: Li
  fullname: Li, Shaobo
  organization: The State Key Laboratory of Public Big Data, Guizhou University, Guiyang, China
– sequence: 4
  givenname: Yang
  surname: Li
  fullname: Li, Yang
  organization: The Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education, Guizhou University, Guiyang, China
– sequence: 5
  givenname: Ling
  surname: He
  fullname: He, Ling
  organization: The Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education, Guizhou University, Guiyang, China
– sequence: 6
  givenname: Dan
  surname: Liu
  fullname: Liu, Dan
  organization: The Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education, Guizhou University, Guiyang, China
BookMark eNp9kE1LAzEQhoNUsK3-AU_7B7Ym2e0mAS-l-AUFPeg5TLITN2U_ShKF_nu3rV489DTDzDwD7zMjk37okZBbRheMsupuuzBxZxeccj4OSk6rCzJloqxyyaic_PVUlVdkFuOW0lIKVk7J2yqEZp-azkNmW4jRO28h-aHPoP0cgh9XmYGIdTaOuq82-bxBqLOIrcshJeyPxx3aBnofu2ty6aCNePNb5-Tj8eF9_ZxvXp9e1qtNbgtKUw68KHGJUkmuCiEMkwIdcGVqVjGmBLdGFTUY5oQpjBSGsyWvlXPMKVlVppgTfvprwxBjQKd3wXcQ9ppRfXCit_rgRB-c6JOTEZL_IOvTMW0K4Nvz6P0JxTHUt8ego_XYW6x9QJt0Pfhz-A-_34Ak
CitedBy_id crossref_primary_10_1016_j_jprocont_2023_103007
crossref_primary_10_1016_j_bspc_2024_106650
crossref_primary_10_1002_acs_3926
crossref_primary_10_1002_acs_3604
crossref_primary_10_1016_j_measurement_2025_118149
crossref_primary_10_1007_s10044_025_01519_5
crossref_primary_10_1109_JSEN_2024_3361980
crossref_primary_10_1177_01423312241252459
crossref_primary_10_1016_j_bspc_2025_108119
crossref_primary_10_1016_j_cam_2023_115297
crossref_primary_10_4018_JOEUC_337607
crossref_primary_10_1177_09287329241290941
crossref_primary_10_1016_j_autcon_2024_105300
crossref_primary_10_1016_j_bspc_2022_104552
crossref_primary_10_1155_psyc_2385170
crossref_primary_10_1002_rnc_6951
crossref_primary_10_1002_rnc_7007
crossref_primary_10_1007_s11071_023_08458_y
crossref_primary_10_1016_j_engappai_2023_106374
crossref_primary_10_1002_rnc_6796
crossref_primary_10_1080_1448837X_2024_2326272
crossref_primary_10_1016_j_engappai_2024_109480
crossref_primary_10_1177_14759217251329289
crossref_primary_10_1007_s00034_022_02285_z
crossref_primary_10_1088_2631_8695_ae038c
crossref_primary_10_1371_journal_pone_0326079
crossref_primary_10_1002_acs_3699
crossref_primary_10_1016_j_cam_2023_115107
crossref_primary_10_1109_ACCESS_2024_3350036
crossref_primary_10_1109_ACCESS_2024_3451054
crossref_primary_10_1016_j_ress_2025_111247
crossref_primary_10_1080_10255842_2025_2480264
crossref_primary_10_1016_j_inffus_2024_102721
crossref_primary_10_1002_rnc_6657
crossref_primary_10_32604_cmc_2024_053817
crossref_primary_10_1016_j_cam_2023_115104
crossref_primary_10_1371_journal_pone_0305079
crossref_primary_10_3389_fnins_2024_1479570
crossref_primary_10_1109_TFUZZ_2024_3416217
crossref_primary_10_1007_s13042_024_02484_x
crossref_primary_10_1038_s41598_025_93906_5
crossref_primary_10_1136_heartjnl_2024_323947
crossref_primary_10_1016_j_bspc_2023_105506
crossref_primary_10_1007_s12555_021_0845_y
crossref_primary_10_1007_s12530_024_09647_9
crossref_primary_10_1177_09544062241305515
crossref_primary_10_1002_acs_3669
crossref_primary_10_1049_cvi2_12231
crossref_primary_10_1016_j_bspc_2024_106073
crossref_primary_10_1016_j_energy_2025_137225
crossref_primary_10_1177_01423312241273855
crossref_primary_10_1109_JSEN_2024_3404141
crossref_primary_10_1002_oca_2982
crossref_primary_10_1038_s41598_024_82705_z
crossref_primary_10_32604_cmc_2024_052437
crossref_primary_10_1002_cpe_8056
crossref_primary_10_3390_s24092954
crossref_primary_10_1016_j_bspc_2025_107722
crossref_primary_10_1016_j_aej_2025_05_069
crossref_primary_10_1016_j_asoc_2025_113448
crossref_primary_10_1007_s00034_025_03068_y
crossref_primary_10_1007_s12555_021_1028_6
crossref_primary_10_1007_s10846_023_01926_y
crossref_primary_10_1038_s41598_025_08323_5
crossref_primary_10_3390_informatics12030080
crossref_primary_10_1007_s40747_024_01417_z
crossref_primary_10_1016_j_ijrefrig_2024_10_026
crossref_primary_10_1007_s11042_024_19352_z
crossref_primary_10_1007_s12555_024_0430_2
crossref_primary_10_3390_s24248124
crossref_primary_10_1088_1361_6501_ad53f1
crossref_primary_10_1002_acs_3712
crossref_primary_10_1155_2024_9954821
crossref_primary_10_1109_ACCESS_2024_3401254
crossref_primary_10_1007_s11042_024_18357_y
crossref_primary_10_1007_s10462_025_11259_x
crossref_primary_10_1002_acs_3871
crossref_primary_10_1002_rnc_6917
crossref_primary_10_1016_j_compbiomed_2025_109924
crossref_primary_10_1016_j_arcontrol_2024_100942
crossref_primary_10_1049_bme2_12110
crossref_primary_10_3390_electronics12163400
crossref_primary_10_1002_rnc_7014
crossref_primary_10_1007_s12555_022_0867_0
crossref_primary_10_1186_s12911_024_02822_7
Cites_doi 10.22489/CinC.2017.363-223
10.1016/j.bspc.2020.101874
10.3390/s19071718
10.3390/a11030028
10.1007/s10916-019-1511-2
10.1016/j.compbiomed.2018.03.016
10.1049/iet-spr.2020.0104
10.1109/ACCESS.2018.2833841
10.1109/ACCESS.2019.2963560
10.1016/j.bspc.2019.101673
10.1007/s00034-018-0754-3
10.1016/j.bspc.2020.102262
10.3390/electronics9010121
10.1016/j.bspc.2017.12.004
10.1016/j.bspc.2021.102843
10.3390/math7050428
10.1016/j.ymeth.2021.04.021
10.1016/j.ijcard.2011.01.087
10.1161/01.CIR.101.23.e215
10.1016/j.scib.2020.05.029
10.1186/s12911-021-01546-2
10.3390/su11215959
10.1016/j.bspc.2021.103270
10.1109/JSEN.2019.2939391
10.1109/ACCESS.2021.3095248
10.1109/BIBM47256.2019.8983326
10.1109/IJCNN.2019.8852037
10.3390/polym11122014
10.1155/2017/9295029
10.1155/2018/5767864
10.1109/TBME.2015.2468589
10.1016/j.compbiomed.2017.08.022
10.3390/s18051530
10.1007/s12555-019-0140-3
10.1109/JBHI.2016.2631247
10.1016/j.neunet.2020.09.001
10.1016/j.isatra.2020.12.029
10.1007/s12555-016-0081-z
ContentType Journal Article
Copyright 2022 Elsevier Ltd
Copyright_xml – notice: 2022 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.bspc.2022.104206
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1746-8108
ExternalDocumentID 10_1016_j_bspc_2022_104206
S1746809422006607
GroupedDBID ---
--K
--M
.~1
0R~
1B1
1~.
1~5
23N
4.4
457
4G.
5GY
5VS
6J9
7-5
71M
8P~
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXUO
AAYFN
ABBOA
ABFNM
ABFRF
ABJNI
ABMAC
ABXDB
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADMUD
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
AKRWK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HZ~
IHE
J1W
JJJVA
KOM
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RIG
ROL
RPZ
SDF
SDG
SES
SPC
SPCBC
SST
SSV
SSZ
T5K
UNMZH
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AIGII
AIIUN
AKBMS
AKYEP
ANKPU
APXCP
CITATION
EFKBS
EFLBG
~HD
ID FETCH-LOGICAL-c300t-a234e5e89829377b187efa29bd1611972cb93dab1f7b3b87b2152d9ff1f9866b3
ISICitedReferencesCount 104
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000862883700009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1746-8094
IngestDate Sat Nov 29 07:04:35 EST 2025
Tue Nov 18 22:32:20 EST 2025
Tue Jul 16 04:31:06 EDT 2024
IsPeerReviewed true
IsScholarly true
Keywords Attention mechanism
Arrhythmia classification
Feature extraction
Electrocardiogram (ECG)
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c300t-a234e5e89829377b187efa29bd1611972cb93dab1f7b3b87b2152d9ff1f9866b3
ParticipantIDs crossref_primary_10_1016_j_bspc_2022_104206
crossref_citationtrail_10_1016_j_bspc_2022_104206
elsevier_sciencedirect_doi_10_1016_j_bspc_2022_104206
PublicationCentury 2000
PublicationDate January 2023
2023-01-00
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – month: 01
  year: 2023
  text: January 2023
PublicationDecade 2020
PublicationTitle Biomedical signal processing and control
PublicationYear 2023
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References X. Zhai, and C. Tin, “Automated ECG Classification Using Dual Heartbeat Coupling Based on Convolutional Neural Network”, IEEE Access 6 (2018) 27465-27472. doi:10.1109/ACCESS.2018.2833841.
Che, Zhang, Zhu, Qu, Jin (b0145) 2021; 21
Rahul, Sharma (b0155) 2022; 71
Ding, Pan, Alsaedi, Hayat (b0040) 2019; 7
Wang, Shi, Chen, Zhao, Huang, Liu (b0095) 2020; 44
Mohebbian, Alam, Wahid, Dinh (b0080) 2020; 57
Maruyama (b0010) 2012; 155
Liu, Zhou, Cao, Wang, Wang, Zhang (b0110) 2019
J. Gehring, M. Auli, D. Grangier, D. Yarats, and Y. N. Dauphin, “Convolutional Sequence to Sequence Learning,” International conference on machine learning.(PMLR), 2017: 1243-1252.
Tang, Ma, Hu, Tang (b0055) 2020; 67
D. Berwal, V. C. R., S. Dewan, J. C. V., and M. S. Baghini, “Motion Artifact Removal in Ambulatory ECG Signal for Heart Rate Variability Analysis”, IEEE Sens. J. 19(24) (2019) 12432-12442. doi:10.1109/JSEN.2019.2939391.
Mathunjwa, Lin, Lin, Abbod, Shieh (b0195) 2021; 64
Rajesh, Dhuli (b0230) 2018; 41
S. Kiranyaz, T. Ince, and M. Gabbouj, “Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks,” IEEE T. Bio.-Med. Eng., 63(3) (2016) 664-675. doi:10.1109/TBME.2015.2468589.
Wu, Song, Yu (b0005) 2019; 11
Lin, Li, Yang (b0035) 2021; 133
Lenis, Pilia, Loewe, Schulze, Dössel (b0070) 2017; 2017
Chen, Lin, Lee, Tsai, Huang, Liu, Cheng, Dai (b0120) 2022; 202
Wang, Shi, Lin, Qin, Zhao, Huang, Liu (b0135) 2020; 58
Zheng, Chen, Hu, Zhu, Tang, Liang (b0140) 2020; 9
Cui, Wang, He, De Albuquerque, AlQahtani, Hassan (b0125) 2021
Z. Su, Y. Li, and G. Yang, “Dietary Composition Perception Algorithm Using Social Robot Audition for Mandarin Chinese,” IEEE Access 8{ } (2020) 8768-8782. doi:10.1109/ACCESS.2019.2963560}.
Teijeiro, Felix, Presedo, Castro (b0065) 2018; 22
Uwaechia, Ramli (b0025) 2021; 9
Ding, Lv, Pan, Wan, Jin (b0050) 2020; 18
Ma, Zhao, Zhang, Wang, Chen, Li, Ju, Yu (b0045) 2019; 11
Chatterjee, Thakur, Yadav, Gupta, Raghuvanshi (b0175) 2020; 14
Dosovitskiy, Beyer, Kolesnikov, Weissenborn, Houlsby (b0210) 2020
Goldberger (b0205) 2000; 101
Yildirim (b0105) 2018; 96
Vaswani (b0170) 2017; 30
G. Yan, S. Liang, Y. Zhang, and F. Liu, “Fusing Transformer Model with Temporal Features for ECG Heartbeat Classification,” 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2019: 898-905.
Yang, Yang (b0235) 2018; 11
Jin, Dong, Shu, Wang (b0075) 2019; 19
Kumar, Tomar, Mehla, Komaragiri, Kumar (b0185) 2021; 114
Liu, Liu, Li, Huang, Yang, Chen, Liu, Cao, Shen, Yu, Zhao, Wu, Zhao, Li, Hu, Lu, Huang, Gu (b0015) 2020; 65
Zhang, Huang, Wang, Liu (b0220) 2019
Pan, Jiang, Wan, Ding (b0180) 2017; 15
P. Schwab, G. C. Scebba, J. Zhang, M. Delai, and W. Karlen, “Beat by beat: Classifying cardiac arrhythmias with recurrent neural networks,” 2017 Computing in Cardiology (CinC). IEEE, 2017: 1-4.
Kumar, Berwal, Kumar (b0085) 2018; 37
Jun, Nguyen, Kang, Kim, Kim, Kim (b0150) 2018
F. Liu, et al., “An Attention-based Hybrid LSTM-CNN Model for Arrhythmias Classification,” 2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 2019: 1-8.
Karunathilake, Ganegoda, Martinez (b0020) 2018; 2018
Yang, Yang, Sheng, Junior, Li (b0165) 2018; 18
L. M. L. J. XIONG Hui, “Arrhythmia Classification Algorithm Based on Convolutional Neural Network Hybrid Model,” Harbin Gongye Daxue Xuebao/Journal of Harbin Institute of Technology 53(2) (2021).
Lu, Jiang, Wei, Zhang, Wang, Wei, Xia (b0160) 2021; 69
Acharya (b0215) 2017; 89
Ding (10.1016/j.bspc.2022.104206_b0040) 2019; 7
Che (10.1016/j.bspc.2022.104206_b0145) 2021; 21
10.1016/j.bspc.2022.104206_b0190
10.1016/j.bspc.2022.104206_b0090
Dosovitskiy (10.1016/j.bspc.2022.104206_b0210) 2020
Rajesh (10.1016/j.bspc.2022.104206_b0230) 2018; 41
Mohebbian (10.1016/j.bspc.2022.104206_b0080) 2020; 57
Zhang (10.1016/j.bspc.2022.104206_b0220) 2019
Vaswani (10.1016/j.bspc.2022.104206_b0170) 2017; 30
Goldberger (10.1016/j.bspc.2022.104206_b0205) 2000; 101
Karunathilake (10.1016/j.bspc.2022.104206_b0020) 2018; 2018
10.1016/j.bspc.2022.104206_b0130
10.1016/j.bspc.2022.104206_b0030
Lu (10.1016/j.bspc.2022.104206_b0160) 2021; 69
Yang (10.1016/j.bspc.2022.104206_b0165) 2018; 18
Rahul (10.1016/j.bspc.2022.104206_b0155) 2022; 71
Lenis (10.1016/j.bspc.2022.104206_b0070) 2017; 2017
10.1016/j.bspc.2022.104206_b0115
Ding (10.1016/j.bspc.2022.104206_b0050) 2020; 18
Chatterjee (10.1016/j.bspc.2022.104206_b0175) 2020; 14
Cui (10.1016/j.bspc.2022.104206_b0125) 2021
Pan (10.1016/j.bspc.2022.104206_b0180) 2017; 15
Maruyama (10.1016/j.bspc.2022.104206_b0010) 2012; 155
Liu (10.1016/j.bspc.2022.104206_b0015) 2020; 65
10.1016/j.bspc.2022.104206_b0060
Yildirim (10.1016/j.bspc.2022.104206_b0105) 2018; 96
Kumar (10.1016/j.bspc.2022.104206_b0185) 2021; 114
Liu (10.1016/j.bspc.2022.104206_b0110) 2019
Jun (10.1016/j.bspc.2022.104206_b0150) 2018
10.1016/j.bspc.2022.104206_b0200
Acharya (10.1016/j.bspc.2022.104206_b0215) 2017; 89
10.1016/j.bspc.2022.104206_b0100
Teijeiro (10.1016/j.bspc.2022.104206_b0065) 2018; 22
Zheng (10.1016/j.bspc.2022.104206_b0140) 2020; 9
Lin (10.1016/j.bspc.2022.104206_b0035) 2021; 133
Kumar (10.1016/j.bspc.2022.104206_b0085) 2018; 37
10.1016/j.bspc.2022.104206_b0225
Uwaechia (10.1016/j.bspc.2022.104206_b0025) 2021; 9
Jin (10.1016/j.bspc.2022.104206_b0075) 2019; 19
Wang (10.1016/j.bspc.2022.104206_b0095) 2020; 44
Ma (10.1016/j.bspc.2022.104206_b0045) 2019; 11
Chen (10.1016/j.bspc.2022.104206_b0120) 2022; 202
Yang (10.1016/j.bspc.2022.104206_b0235) 2018; 11
Wu (10.1016/j.bspc.2022.104206_b0005) 2019; 11
Wang (10.1016/j.bspc.2022.104206_b0135) 2020; 58
Mathunjwa (10.1016/j.bspc.2022.104206_b0195) 2021; 64
Tang (10.1016/j.bspc.2022.104206_b0055) 2020; 67
References_xml – volume: 37
  start-page: 3995
  year: 2018
  end-page: 4014
  ident: b0085
  article-title: Design of High-Performance ECG Detector for Implantable Cardiac Pacemaker Systems using Biorthogonal Wavelet Transform
  publication-title: Circuits, Systems, and Signal Processing
– reference: L. M. L. J. XIONG Hui, “Arrhythmia Classification Algorithm Based on Convolutional Neural Network Hybrid Model,” Harbin Gongye Daxue Xuebao/Journal of Harbin Institute of Technology 53(2) (2021).
– volume: 58
  year: 2020
  ident: b0135
  article-title: A high-precision arrhythmia classification method based on dual fully connected neural network
  publication-title: Biomed. Signal Proces.
– volume: 64
  year: 2021
  ident: b0195
  article-title: ECG arrhythmia classification by using a recurrence plot and convolutional neural network
  publication-title: Biomed. Signal Proces.
– reference: D. Berwal, V. C. R., S. Dewan, J. C. V., and M. S. Baghini, “Motion Artifact Removal in Ambulatory ECG Signal for Heart Rate Variability Analysis”, IEEE Sens. J. 19(24) (2019) 12432-12442. doi:10.1109/JSEN.2019.2939391.
– reference: P. Schwab, G. C. Scebba, J. Zhang, M. Delai, and W. Karlen, “Beat by beat: Classifying cardiac arrhythmias with recurrent neural networks,” 2017 Computing in Cardiology (CinC). IEEE, 2017: 1-4.
– volume: 202
  start-page: 127
  year: 2022
  end-page: 135
  ident: b0120
  article-title: Automated ECG classification based on 1D deep learning network
  publication-title: Methods
– volume: 11
  start-page: 2014
  year: 2019
  ident: b0045
  article-title: Influence of Infiltration Pressure on the Microstructure and Properties of 2D-CFRP Prepared by the Vacuum Infiltration Hot Pressing Molding Process
  publication-title: Polymers
– reference: X. Zhai, and C. Tin, “Automated ECG Classification Using Dual Heartbeat Coupling Based on Convolutional Neural Network”, IEEE Access 6 (2018) 27465-27472. doi:10.1109/ACCESS.2018.2833841.
– volume: 69
  start-page: 102843
  year: 2021
  ident: b0160
  article-title: Automated arrhythmia classification using depthwise separable convolutional neural network with focal loss
  publication-title: Biomedical Signal Processing and Control
– volume: 67
  start-page: 978
  year: 2020
  end-page: 986
  ident: b0055
  article-title: “A Real-Time Arrhythmia Heartbeats Classification Algorithm Using Parallel Delta Modulations and Rotated Linear-Kernel Support Vector Machines,”
  publication-title: Bio.-Med. Eng.
– volume: 96
  start-page: 189
  year: 2018
  end-page: 202
  ident: b0105
  article-title: A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification
  publication-title: Comput. Biol. Med.
– year: 2019
  ident: b0220
  article-title: Arrhythmia classification using parallel combination of LSTM and CNN
  publication-title: Journal of Harbin Institute of Technology
– volume: 71
  year: 2022
  ident: b0155
  article-title: Artificial intelligence-based approach for atrial fibrillation detection using normalised and short-duration time-frequency ECG
  publication-title: Biomed. Signal Proces.
– year: 2018
  ident: b0150
  article-title: ECG arrhythmia classification using a 2-D convolutional neural network
  publication-title: ArXiv preprint
– volume: 114
  start-page: 251
  year: 2021
  end-page: 262
  ident: b0185
  article-title: Stationary wavelet transform based ECG signal denoising method
  publication-title: ISA T.
– year: 2020
  ident: b0210
  article-title: “An Image is Worth 16x16 Words
  publication-title: Transformers for Image Recognition at Scale,“
– volume: 41
  start-page: 242
  year: 2018
  end-page: 254
  ident: b0230
  article-title: Classification of imbalanced ECG beats using re-sampling techniques and AdaBoost ensemble classifier
  publication-title: Biomed. Signal Proces.
– volume: 9
  start-page: 97760
  year: 2021
  end-page: 97802
  ident: b0025
  article-title: A Comprehensive Survey on ECG Signals as New Biometric Modality for Human Authentication: Recent Advances and Future Challenges
  publication-title: IEEE Access
– volume: 44
  year: 2020
  ident: b0095
  article-title: An Improved Convolutional Neural Network Based Approach for Automated Heartbeat Classification
  publication-title: J Med Syst
– volume: 65
  start-page: 1760
  year: 2020
  end-page: 1766
  ident: b0015
  article-title: Sedentary behavior and risk of incident cardiovascular disease among Chinese adults
  publication-title: Science Bulletin
– reference: F. Liu, et al., “An Attention-based Hybrid LSTM-CNN Model for Arrhythmias Classification,” 2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 2019: 1-8.
– volume: 30
  year: 2017
  ident: b0170
  article-title: Attention Is All You Need
  publication-title: Advances in neural information processing systems
– reference: J. Gehring, M. Auli, D. Grangier, D. Yarats, and Y. N. Dauphin, “Convolutional Sequence to Sequence Learning,” International conference on machine learning.(PMLR), 2017: 1243-1252.
– year: 2019
  ident: b0110
  article-title: Arrhythmias Classification by Integrating Stacked Bidirectional LSTM and Two-Dimensional CNN
  publication-title: Presented at the Advances in Knowledge Discovery and Data Mining
– volume: 9
  start-page: 121
  year: 2020
  ident: b0140
  article-title: An Automatic Diagnosis of Arrhythmias Using a Combination of CNN and LSTM Technology
  publication-title: Electronics
– volume: 18
  start-page: 886
  year: 2020
  end-page: 896
  ident: b0050
  article-title: Two-stage Gradient-based Iterative Estimation Methods for Controlled Autoregressive Systems Using the Measurement Data
  publication-title: International Journal of Control, Automation and Systems
– volume: 18
  start-page: 1530
  year: 2018
  ident: b0165
  article-title: Convolutional Neural Network-Based Embarrassing Situation Detection under Camera for Social Robot in Smart Homes
  publication-title: Sensors
– volume: 57
  year: 2020
  ident: b0080
  article-title: Single channel high noise level ECG deconvolution using optimized blind adaptive filtering and fixed-point convolution kernel compensation
  publication-title: Biomed. Signal Proces.
– volume: 11
  start-page: 5959
  year: 2019
  ident: b0005
  article-title: Spatial Differences in China’s Population Aging and Influencing Factors: The Perspectives of Spatial Dependence and Spatial Heterogeneity
  publication-title: Sustainability
– volume: 11
  start-page: 28
  year: 2018
  ident: b0235
  article-title: Modified Convolutional Neural Network Based on Dropout and the Stochastic Gradient Descent Optimizer
  publication-title: Algorithms
– reference: S. Kiranyaz, T. Ince, and M. Gabbouj, “Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks,” IEEE T. Bio.-Med. Eng., 63(3) (2016) 664-675. doi:10.1109/TBME.2015.2468589.
– volume: 2017
  start-page: 1
  year: 2017
  end-page: 13
  ident: b0070
  article-title: Comparison of Baseline Wander Removal Techniques considering the Preservation of ST Changes in the Ischemic ECG: A Simulation Study
  publication-title: Comput. Math. Method. M.
– volume: 14
  start-page: 569
  year: 2020
  end-page: 590
  ident: b0175
  article-title: Review of noise removal techniques in ECG signals
  publication-title: IET Signal Process.
– volume: 133
  start-page: 132
  year: 2021
  end-page: 147
  ident: b0035
  article-title: FPGAN: Face de-identification method with generative adversarial networks for social robots
  publication-title: Neural Networks
– volume: 89
  year: 2017
  ident: b0215
  article-title: A deep convolutional neural network model to classify heartbeats
  publication-title: Comput. Biol. Med.
– volume: 22
  start-page: 409
  year: 2018
  end-page: 420
  ident: b0065
  article-title: Heartbeat Classification Using Abstract Features From the Abductive Interpretation of the ECG
  publication-title: IEEE J. Biomed. Health
– reference: G. Yan, S. Liang, Y. Zhang, and F. Liu, “Fusing Transformer Model with Temporal Features for ECG Heartbeat Classification,” 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE, 2019: 898-905.
– volume: 2018
  start-page: 5767864
  year: 2018
  ident: b0020
  article-title: Secondary Prevention of Cardiovascular Diseases and Application of Technology for Early Diagnosis
  publication-title: Biomed Res. Int.
– volume: 7
  start-page: 428
  year: 2019
  ident: b0040
  article-title: Gradient-Based Iterative Parameter Estimation Algorithms for Dynamical Systems from Observation Data
  publication-title: Mathematics
– volume: 21
  year: 2021
  ident: b0145
  article-title: Constrained transformer network for ECG signal processing and arrhythmia classification
  publication-title: BMC Med Inform Decis Mak
– reference: Z. Su, Y. Li, and G. Yang, “Dietary Composition Perception Algorithm Using Social Robot Audition for Mandarin Chinese,” IEEE Access 8{ } (2020) 8768-8782. doi:10.1109/ACCESS.2019.2963560}.
– volume: 19
  start-page: 1718
  year: 2019
  ident: b0075
  article-title: Sparse ECG Denoising with Generalized Minimax Concave Penalty
  publication-title: Sensors-Basel
– volume: 15
  start-page: 1189
  year: 2017
  end-page: 1197
  ident: b0180
  article-title: A filtering based multi-innovation extended stochastic gradient algorithm for multivariable control systems
  publication-title: International Journal of Control, Automation and Systems
– volume: 101
  start-page: E215
  year: 2000
  end-page: E220
  ident: b0205
  article-title: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals
  publication-title: Circulation
– volume: 155
  start-page: 14
  year: 2012
  end-page: 19
  ident: b0010
  article-title: Aging and arterial-cardiac interactions in the elderly
  publication-title: Int. J. Cardiol.
– year: 2021
  ident: b0125
  article-title: “Deep learning-based multidimensional feature fusion for classification of ECG arrhythmia,”
  publication-title: Appl.
– ident: 10.1016/j.bspc.2022.104206_b0100
  doi: 10.22489/CinC.2017.363-223
– volume: 58
  year: 2020
  ident: 10.1016/j.bspc.2022.104206_b0135
  article-title: A high-precision arrhythmia classification method based on dual fully connected neural network
  publication-title: Biomed. Signal Proces.
  doi: 10.1016/j.bspc.2020.101874
– volume: 19
  start-page: 1718
  issue: 7
  year: 2019
  ident: 10.1016/j.bspc.2022.104206_b0075
  article-title: Sparse ECG Denoising with Generalized Minimax Concave Penalty
  publication-title: Sensors-Basel
  doi: 10.3390/s19071718
– year: 2020
  ident: 10.1016/j.bspc.2022.104206_b0210
  article-title: “An Image is Worth 16x16 Words
  publication-title: Transformers for Image Recognition at Scale,“
– volume: 11
  start-page: 28
  issue: 3
  year: 2018
  ident: 10.1016/j.bspc.2022.104206_b0235
  article-title: Modified Convolutional Neural Network Based on Dropout and the Stochastic Gradient Descent Optimizer
  publication-title: Algorithms
  doi: 10.3390/a11030028
– volume: 44
  issue: 2
  year: 2020
  ident: 10.1016/j.bspc.2022.104206_b0095
  article-title: An Improved Convolutional Neural Network Based Approach for Automated Heartbeat Classification
  publication-title: J Med Syst
  doi: 10.1007/s10916-019-1511-2
– volume: 96
  start-page: 189
  year: 2018
  ident: 10.1016/j.bspc.2022.104206_b0105
  article-title: A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification
  publication-title: Comput. Biol. Med.
  doi: 10.1016/j.compbiomed.2018.03.016
– volume: 14
  start-page: 569
  issue: 9
  year: 2020
  ident: 10.1016/j.bspc.2022.104206_b0175
  article-title: Review of noise removal techniques in ECG signals
  publication-title: IET Signal Process.
  doi: 10.1049/iet-spr.2020.0104
– volume: 30
  year: 2017
  ident: 10.1016/j.bspc.2022.104206_b0170
  article-title: Attention Is All You Need
  publication-title: Advances in neural information processing systems
– ident: 10.1016/j.bspc.2022.104206_b0130
  doi: 10.1109/ACCESS.2018.2833841
– ident: 10.1016/j.bspc.2022.104206_b0030
  doi: 10.1109/ACCESS.2019.2963560
– year: 2019
  ident: 10.1016/j.bspc.2022.104206_b0220
  article-title: Arrhythmia classification using parallel combination of LSTM and CNN
  publication-title: Journal of Harbin Institute of Technology
– volume: 57
  year: 2020
  ident: 10.1016/j.bspc.2022.104206_b0080
  article-title: Single channel high noise level ECG deconvolution using optimized blind adaptive filtering and fixed-point convolution kernel compensation
  publication-title: Biomed. Signal Proces.
  doi: 10.1016/j.bspc.2019.101673
– volume: 37
  start-page: 3995
  issue: 9
  year: 2018
  ident: 10.1016/j.bspc.2022.104206_b0085
  article-title: Design of High-Performance ECG Detector for Implantable Cardiac Pacemaker Systems using Biorthogonal Wavelet Transform
  publication-title: Circuits, Systems, and Signal Processing
  doi: 10.1007/s00034-018-0754-3
– volume: 64
  year: 2021
  ident: 10.1016/j.bspc.2022.104206_b0195
  article-title: ECG arrhythmia classification by using a recurrence plot and convolutional neural network
  publication-title: Biomed. Signal Proces.
  doi: 10.1016/j.bspc.2020.102262
– volume: 67
  start-page: 978
  issue: 4
  year: 2020
  ident: 10.1016/j.bspc.2022.104206_b0055
  article-title: “A Real-Time Arrhythmia Heartbeats Classification Algorithm Using Parallel Delta Modulations and Rotated Linear-Kernel Support Vector Machines,” IEEE T
  publication-title: Bio.-Med. Eng.
– volume: 9
  start-page: 121
  issue: 1
  year: 2020
  ident: 10.1016/j.bspc.2022.104206_b0140
  article-title: An Automatic Diagnosis of Arrhythmias Using a Combination of CNN and LSTM Technology
  publication-title: Electronics
  doi: 10.3390/electronics9010121
– volume: 41
  start-page: 242
  year: 2018
  ident: 10.1016/j.bspc.2022.104206_b0230
  article-title: Classification of imbalanced ECG beats using re-sampling techniques and AdaBoost ensemble classifier
  publication-title: Biomed. Signal Proces.
  doi: 10.1016/j.bspc.2017.12.004
– volume: 69
  start-page: 102843
  year: 2021
  ident: 10.1016/j.bspc.2022.104206_b0160
  article-title: Automated arrhythmia classification using depthwise separable convolutional neural network with focal loss
  publication-title: Biomedical Signal Processing and Control
  doi: 10.1016/j.bspc.2021.102843
– volume: 7
  start-page: 428
  issue: 5
  year: 2019
  ident: 10.1016/j.bspc.2022.104206_b0040
  article-title: Gradient-Based Iterative Parameter Estimation Algorithms for Dynamical Systems from Observation Data
  publication-title: Mathematics
  doi: 10.3390/math7050428
– volume: 202
  start-page: 127
  year: 2022
  ident: 10.1016/j.bspc.2022.104206_b0120
  article-title: Automated ECG classification based on 1D deep learning network
  publication-title: Methods
  doi: 10.1016/j.ymeth.2021.04.021
– volume: 155
  start-page: 14
  issue: 1
  year: 2012
  ident: 10.1016/j.bspc.2022.104206_b0010
  article-title: Aging and arterial-cardiac interactions in the elderly
  publication-title: Int. J. Cardiol.
  doi: 10.1016/j.ijcard.2011.01.087
– volume: 101
  start-page: E215
  issue: 23
  year: 2000
  ident: 10.1016/j.bspc.2022.104206_b0205
  article-title: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals
  publication-title: Circulation
  doi: 10.1161/01.CIR.101.23.e215
– volume: 65
  start-page: 1760
  issue: 20
  year: 2020
  ident: 10.1016/j.bspc.2022.104206_b0015
  article-title: Sedentary behavior and risk of incident cardiovascular disease among Chinese adults
  publication-title: Science Bulletin
  doi: 10.1016/j.scib.2020.05.029
– year: 2019
  ident: 10.1016/j.bspc.2022.104206_b0110
  article-title: Arrhythmias Classification by Integrating Stacked Bidirectional LSTM and Two-Dimensional CNN
– volume: 21
  issue: 1
  year: 2021
  ident: 10.1016/j.bspc.2022.104206_b0145
  article-title: Constrained transformer network for ECG signal processing and arrhythmia classification
  publication-title: BMC Med Inform Decis Mak
  doi: 10.1186/s12911-021-01546-2
– volume: 11
  start-page: 5959
  issue: 21
  year: 2019
  ident: 10.1016/j.bspc.2022.104206_b0005
  article-title: Spatial Differences in China’s Population Aging and Influencing Factors: The Perspectives of Spatial Dependence and Spatial Heterogeneity
  publication-title: Sustainability
  doi: 10.3390/su11215959
– volume: 71
  year: 2022
  ident: 10.1016/j.bspc.2022.104206_b0155
  article-title: Artificial intelligence-based approach for atrial fibrillation detection using normalised and short-duration time-frequency ECG
  publication-title: Biomed. Signal Proces.
  doi: 10.1016/j.bspc.2021.103270
– ident: 10.1016/j.bspc.2022.104206_b0090
  doi: 10.1109/JSEN.2019.2939391
– ident: 10.1016/j.bspc.2022.104206_b0200
– volume: 9
  start-page: 97760
  year: 2021
  ident: 10.1016/j.bspc.2022.104206_b0025
  article-title: A Comprehensive Survey on ECG Signals as New Biometric Modality for Human Authentication: Recent Advances and Future Challenges
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2021.3095248
– ident: 10.1016/j.bspc.2022.104206_b0190
  doi: 10.1109/BIBM47256.2019.8983326
– ident: 10.1016/j.bspc.2022.104206_b0115
  doi: 10.1109/IJCNN.2019.8852037
– ident: 10.1016/j.bspc.2022.104206_b0225
– volume: 11
  start-page: 2014
  issue: 12
  year: 2019
  ident: 10.1016/j.bspc.2022.104206_b0045
  article-title: Influence of Infiltration Pressure on the Microstructure and Properties of 2D-CFRP Prepared by the Vacuum Infiltration Hot Pressing Molding Process
  publication-title: Polymers
  doi: 10.3390/polym11122014
– volume: 2017
  start-page: 1
  year: 2017
  ident: 10.1016/j.bspc.2022.104206_b0070
  article-title: Comparison of Baseline Wander Removal Techniques considering the Preservation of ST Changes in the Ischemic ECG: A Simulation Study
  publication-title: Comput. Math. Method. M.
  doi: 10.1155/2017/9295029
– year: 2021
  ident: 10.1016/j.bspc.2022.104206_b0125
  article-title: “Deep learning-based multidimensional feature fusion for classification of ECG arrhythmia,” Neural Comput
  publication-title: Appl.
– volume: 2018
  start-page: 5767864
  year: 2018
  ident: 10.1016/j.bspc.2022.104206_b0020
  article-title: Secondary Prevention of Cardiovascular Diseases and Application of Technology for Early Diagnosis
  publication-title: Biomed Res. Int.
  doi: 10.1155/2018/5767864
– ident: 10.1016/j.bspc.2022.104206_b0060
  doi: 10.1109/TBME.2015.2468589
– year: 2018
  ident: 10.1016/j.bspc.2022.104206_b0150
  article-title: ECG arrhythmia classification using a 2-D convolutional neural network
– volume: 89
  year: 2017
  ident: 10.1016/j.bspc.2022.104206_b0215
  article-title: A deep convolutional neural network model to classify heartbeats
  publication-title: Comput. Biol. Med.
  doi: 10.1016/j.compbiomed.2017.08.022
– volume: 18
  start-page: 1530
  issue: 5
  year: 2018
  ident: 10.1016/j.bspc.2022.104206_b0165
  article-title: Convolutional Neural Network-Based Embarrassing Situation Detection under Camera for Social Robot in Smart Homes
  publication-title: Sensors
  doi: 10.3390/s18051530
– volume: 18
  start-page: 886
  issue: 4
  year: 2020
  ident: 10.1016/j.bspc.2022.104206_b0050
  article-title: Two-stage Gradient-based Iterative Estimation Methods for Controlled Autoregressive Systems Using the Measurement Data
  publication-title: International Journal of Control, Automation and Systems
  doi: 10.1007/s12555-019-0140-3
– volume: 22
  start-page: 409
  issue: 2
  year: 2018
  ident: 10.1016/j.bspc.2022.104206_b0065
  article-title: Heartbeat Classification Using Abstract Features From the Abductive Interpretation of the ECG
  publication-title: IEEE J. Biomed. Health
  doi: 10.1109/JBHI.2016.2631247
– volume: 133
  start-page: 132
  year: 2021
  ident: 10.1016/j.bspc.2022.104206_b0035
  article-title: FPGAN: Face de-identification method with generative adversarial networks for social robots
  publication-title: Neural Networks
  doi: 10.1016/j.neunet.2020.09.001
– volume: 114
  start-page: 251
  year: 2021
  ident: 10.1016/j.bspc.2022.104206_b0185
  article-title: Stationary wavelet transform based ECG signal denoising method
  publication-title: ISA T.
  doi: 10.1016/j.isatra.2020.12.029
– volume: 15
  start-page: 1189
  issue: 3
  year: 2017
  ident: 10.1016/j.bspc.2022.104206_b0180
  article-title: A filtering based multi-innovation extended stochastic gradient algorithm for multivariable control systems
  publication-title: International Journal of Control, Automation and Systems
  doi: 10.1007/s12555-016-0081-z
SSID ssj0048714
Score 2.5836244
Snippet •ECG signal preprocessing method based on wavelet transform to reduce noise.•Linear projection layer is designed to acquire semantic features of ECG...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 104206
SubjectTerms Arrhythmia classification
Attention mechanism
Electrocardiogram (ECG)
Feature extraction
Title Arrhythmia classification algorithm based on multi-head self-attention mechanism
URI https://dx.doi.org/10.1016/j.bspc.2022.104206
Volume 79
WOSCitedRecordID wos000862883700009&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: 1746-8108
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0048714
  issn: 1746-8094
  databaseCode: AIEXJ
  dateStart: 20060101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3dS-NAEF9K9UEfxPMDP488-FYiySbN7j4W8TgPEUGF-hSyya6N1LSkVbz__may-Wo9RAVfQplmkzDzY3Z2d-Y3hJzAkgEmXR3bOugnth8EwpaOr8EZchqByXmiC57ZS3Z1xYdDcd3p6KoW5mXMsoy_vorpt5oaZGBsLJ39hLnrh4IAfoPR4Qpmh-uHDD_I89Hf-egpxbJHCI0xF8hYORo_TPIU_urh3JXgOUGRT2iDQ056MzXWNrJtmvzHJ4U1wRXBYHXsWxTrm0rK9AED2akpNKhKHcvM92ab3riS--caP_elCLCZxWmdD1QkFdyMoomcLMrw_vbWBPWWtibqmpkmQQldLPORAtm0Nj5VLZnr8LZfNk1m3rh4s9vweCpnU6SgpBSPqamzxKddzNA3-Fx8FS2OmJB0YIWyvuBdsjK4OB_-qeZsWLUVLPD1t5XlVSYTcPlN_w9hWmHJ7SbZKNcT1sDg4AfpqGyLrLdYJrfJdYMIaxERVo0Iq0CEBaIGEdYiIqwaETvk7tf57dlvu2ykYcee48ztiHq-6isuOAR3jEmXM6UjKmQC8T72nYul8JJIuppJT3ImsdlxIrR2teBBIL1d0s0mmdojlqs95UFULoUf-IJq7EcAQWYQxI52Ein2iVvpJoxLlnlsdjIOq3TCxxD1GaI-Q6PPfdKrx0wNx8q7d_crlYdllGiivxAQ8s64gy-OOyRrDbaPSHeeP6tjshq_zNNZ_rME0j_kVoxS
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=Arrhythmia+classification+algorithm+based+on+multi-head+self-attention+mechanism&rft.jtitle=Biomedical+signal+processing+and+control&rft.au=Wang%2C+Yue&rft.au=Yang%2C+Guanci&rft.au=Li%2C+Shaobo&rft.au=Li%2C+Yang&rft.date=2023-01-01&rft.pub=Elsevier+Ltd&rft.issn=1746-8094&rft.eissn=1746-8108&rft.volume=79&rft_id=info:doi/10.1016%2Fj.bspc.2022.104206&rft.externalDocID=S1746809422006607
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1746-8094&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1746-8094&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1746-8094&client=summon