Hypergraph and cross-attention-based unsupervised domain adaptation framework for cross-domain myocardial infarction localization
Solving individual differences between subjects is critical for the promotion of electrocardiogram (ECG) classification algorithms in the intelligent health monitoring industry. Popular inter-subject-based solutions usually require the manual labeling of heartbeats and frequent updating of the model...
Saved in:
| Published in | Information sciences Vol. 633; pp. 245 - 263 |
|---|---|
| Main Authors | , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Inc
01.07.2023
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0020-0255 1872-6291 |
| DOI | 10.1016/j.ins.2023.03.078 |
Cover
| Abstract | Solving individual differences between subjects is critical for the promotion of electrocardiogram (ECG) classification algorithms in the intelligent health monitoring industry. Popular inter-subject-based solutions usually require the manual labeling of heartbeats and frequent updating of the model for new subjects. To track these problems, we propose a hypergraph and cross-attention-based unsupervised domain adaptation (HGCA-UDA) framework for the myocardial infarction localization. Specifically, we first build a hypergraph-based dual-channel network, that can simultaneously learn specific feature representations from an ECG lead and disease category levels for samples from different domains. We then design a cross-attention module to align cross-domain locally similar samples. Subsequently, a domain alignment strategy based on the Wasserstein distance is proposed to align the global edge feature distribution. Finally, a pseudo-label generation scheme is proposed to further align fine-grained category information. We conduct extensive experiments on two public benchmark datasets (the Physikalisch-Technische Bundesanstalt (PTB) and PTB_XL database), and the results show that the proposed HGCR-UDA (with unlabeled patients) achieves comparable results compared with state-of-the-art inter-patient-based methods (with labeled patients) and has excellent applications prospects in the field of intelligent health monitoring. |
|---|---|
| AbstractList | Solving individual differences between subjects is critical for the promotion of electrocardiogram (ECG) classification algorithms in the intelligent health monitoring industry. Popular inter-subject-based solutions usually require the manual labeling of heartbeats and frequent updating of the model for new subjects. To track these problems, we propose a hypergraph and cross-attention-based unsupervised domain adaptation (HGCA-UDA) framework for the myocardial infarction localization. Specifically, we first build a hypergraph-based dual-channel network, that can simultaneously learn specific feature representations from an ECG lead and disease category levels for samples from different domains. We then design a cross-attention module to align cross-domain locally similar samples. Subsequently, a domain alignment strategy based on the Wasserstein distance is proposed to align the global edge feature distribution. Finally, a pseudo-label generation scheme is proposed to further align fine-grained category information. We conduct extensive experiments on two public benchmark datasets (the Physikalisch-Technische Bundesanstalt (PTB) and PTB_XL database), and the results show that the proposed HGCR-UDA (with unlabeled patients) achieves comparable results compared with state-of-the-art inter-patient-based methods (with labeled patients) and has excellent applications prospects in the field of intelligent health monitoring. |
| Author | Zhao, Jianhui Yuan, Shuaiying Yuan, Zhiyong Alenezi, Fayadh He, Ziyang Alhudhaif, Adi |
| Author_xml | – sequence: 1 givenname: Shuaiying surname: Yuan fullname: Yuan, Shuaiying organization: School of Computer Science, Wuhan University, Wuhan 430072, China – sequence: 2 givenname: Ziyang surname: He fullname: He, Ziyang organization: School of Computer Science, Wuhan University, Wuhan 430072, China – sequence: 3 givenname: Jianhui surname: Zhao fullname: Zhao, Jianhui email: jianhuizhao@whu.edu.cn organization: School of Computer Science, Wuhan University, Wuhan 430072, China – sequence: 4 givenname: Zhiyong surname: Yuan fullname: Yuan, Zhiyong email: zhiyongyuan@whu.edu.cn organization: School of Computer Science, Wuhan University, Wuhan 430072, China – sequence: 5 givenname: Adi surname: Alhudhaif fullname: Alhudhaif, Adi organization: Department of Computer Science, College of Computer Engineering and Sciences in Al-kharj, Prince Sattam bin Abdulaziz University, P.O. Box 151, Al-Kharj 11942, Saudi Arabia – sequence: 6 givenname: Fayadh orcidid: 0000-0002-4099-1254 surname: Alenezi fullname: Alenezi, Fayadh organization: Department of Electrical Engineering, College of Engineering, Jouf University, 72238, Saudi Arabia |
| BookMark | eNp9kMFOwzAMhiM0JLbBA3DrC3SkaZs04oQmYEiTuMA5clMHMtq0SrqhcePNabedOEz6JcvW_1n2PyMT1zok5Dahi4Qm_G6zsC4sGGXpgg4SxQWZJoVgMWcymZAppYzGlOX5FZmFsKGUZoLzKfld7Tv0Hx66zwhcFWnfhhBD36PrbeviEgJW0daF7WDb2bGp2gasi6CCrofRFBkPDX63_isyrT-tOLmafavBVxbqyDoDXh-AehjW9udAX5NLA3XAm1Odk_enx7flKl6_Pr8sH9axZlL0cUZNKbkAwzNeQikRJehUM5TIgOaVkGLos1KnPMlzyVOeGZ3rQmZZWRiJ6Zwkx72H-zwa1XnbgN-rhKoxQ7VRQ4ZqzFDRQaIYGPGP0fb4c-_B1mfJ-yOJw0s7i14FbdFprKxH3auqtWfoP-rck2I |
| CitedBy_id | crossref_primary_10_1016_j_knosys_2024_112708 crossref_primary_10_1016_j_knosys_2024_112085 crossref_primary_10_1016_j_knosys_2024_112769 crossref_primary_10_3390_app13148551 crossref_primary_10_1088_1361_6579_ad3d25 crossref_primary_10_1016_j_eswa_2024_124352 crossref_primary_10_1016_j_knosys_2024_111906 |
| Cites_doi | 10.1016/j.cmpb.2019.105138 10.1016/j.ins.2021.09.031 10.1016/j.knosys.2020.106162 10.1016/j.patrec.2019.02.016 10.1016/j.ins.2022.07.011 10.1016/j.knosys.2020.106122 10.1161/01.CIR.101.23.e215 10.1016/j.ins.2022.05.070 10.1016/j.ins.2021.08.095 10.1016/j.patcog.2020.107637 10.3390/s20041020 10.1016/j.engappai.2020.104092 10.1016/j.bspc.2016.07.007 10.1016/j.ins.2021.07.073 10.1016/j.cmpb.2021.106379 10.1016/j.bspc.2018.05.013 10.1561/116.00000192 10.1067/mhj.2001.113571 10.1053/euhj.1999.1748 10.1038/s41597-020-0495-6 10.3390/bios12010015 10.3390/ijerph191710707 10.1016/j.ins.2021.09.046 10.1016/j.knosys.2022.108649 10.1109/TBME.1985.325532 10.1109/TIP.2018.2862625 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier Inc. |
| Copyright_xml | – notice: 2023 Elsevier Inc. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ins.2023.03.078 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Library & Information Science |
| EISSN | 1872-6291 |
| EndPage | 263 |
| ExternalDocumentID | 10_1016_j_ins_2023_03_078 S0020025523003882 |
| GroupedDBID | --K --M --Z -~X .DC .~1 0R~ 1B1 1OL 1RT 1~. 1~5 29I 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN 9JO AAAKF AAAKG AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AARIN AAXUO AAYFN ABAOU ABBOA ABEFU ABFNM ABJNI ABMAC ABTAH ABUCO ABXDB ABYKQ ACAZW ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFFNX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGVJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD APLSM ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HAMUX HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM LG9 LY1 M41 MHUIS MO0 MS~ N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SSB SSD SST SSV SSW SSZ T5K TN5 TWZ UHS WH7 WUQ XPP YYP ZMT ZY4 ~02 ~G- 77I AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO ADVLN AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c297t-40fb967af646bab9ee9ac3c2e9e2a05d797ac34bc3615596364fc5c8944b8f9e3 |
| IEDL.DBID | .~1 |
| ISSN | 0020-0255 |
| IngestDate | Thu Sep 25 00:36:12 EDT 2025 Thu Apr 24 23:04:25 EDT 2025 Fri Feb 23 02:37:25 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Hypergraph Myocardial infarction Unsupervised domain adaptation Patient individual differences Electrocardiogram |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c297t-40fb967af646bab9ee9ac3c2e9e2a05d797ac34bc3615596364fc5c8944b8f9e3 |
| ORCID | 0000-0002-4099-1254 |
| PageCount | 19 |
| ParticipantIDs | crossref_primary_10_1016_j_ins_2023_03_078 crossref_citationtrail_10_1016_j_ins_2023_03_078 elsevier_sciencedirect_doi_10_1016_j_ins_2023_03_078 |
| PublicationCentury | 2000 |
| PublicationDate | July 2023 2023-07-00 |
| PublicationDateYYYYMMDD | 2023-07-01 |
| PublicationDate_xml | – month: 07 year: 2023 text: July 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Information sciences |
| PublicationYear | 2023 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Sun, Saenko (br0480) 2016 Van der Maaten, Hinton (br0490) 2008; 9 Feng, You, Zhang, Ji, Gao (br0170) 2019; vol. 33 Du, He, Wang, Zhang (br0390) 2020; 204 Sejdinovic, Sriperumbudur, Gretton, Fukumizu (br0370) 2013 Goldberger, Amaral, Glass, Hausdorff, Ivanov, Mark, Mietus, Moody, Peng, Stanley (br0410) 2000; 101 Liu, Ji, Chang, Wang, He, Huang (br0470) 2021; 12 Liu, Yoo, Xing, Oh, El Fakhri, Kang, Woo (br0090) 2022; 11 Zhang, Liu, Xiong, Du, Zhang, Lin, Hou, Liu (br0030) 2021; 97 Pan, Tompkins (br0430) 1985; 3 Fu, Lu, Nie, Peng, Liu, Pi (br0460) 2020; 20 He, Yuan, Zhao, Du, Yuan, Alhudhaif, Alenezi, Althubiti (br0080) 2022; 606 Feng, Fu, Ge, Wang, Zhou, Zhou, Wang (br0020) 2022; 582 Niu, Chen, Liu, Zhou, Shu (br0120) 2020 Andayeshgar, Abdali-Mohammadi, Sepahvand, Daneshkhah, Almasi, Salari (br0220) 2022; 19 Ye, Pan, Meng, Li, Lu (br0210) 2022 Yadati, Nimishakavi, Yadav, Nitin, Louis, Talukdar (br0180) 2019; 32 Fan, Zhang, Wei, Li, Zou, Gao, Dai (br0160) 2021; 44 Bai, Zhang, Torr (br0190) 2021; 110 Zhang, Zhao (br0230) 2021; 575 Shen, Jones, Kumar, Xie, HaoChen, Ma, Liang (br0280) 2022 Syeda Nishat (br0010) 2021 Gulrajani, Ahmed, Arjovsky, Dumoulin, Courville (br0380) 2017; 30 Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhin (br0340) 2017; 30 Zhang, Lin, Zhao, Ji, Gao (br0150) 2018; 27 Wu, Yan, Ng (br0200) 2022; 45 Feng, You, Zhang, Ji, Gao (br0330) 2019; vol. 33 Han, Shi (br0040) 2020; 185 Xie, Pratama (br0240) 2022; 582 Shen, Qu, Zhang, Yu (br0360) 2018; vol. 32 Hou, Yu, Tao (br0400) 2022 Agarwal, Branson, Belongie (br0130) 2006 Wang, Zhou, Zhou, Niu, Zhang, Wang (br0070) 2021; 581 Sgarbossa, Birnbaum, Parrillo (br0310) 2001; 141 Whitney (br0320) 1992 Chen, Wang, Ding, Li, Yang (br0110) 2020 Jiao, Zhong, Liu, Wu, Wong (br0100) 2022; 608 Han, Sun, Yin (br0270) 2021 He, Yuan, An, Zhao, Mfb-lann (br0060) 2021; 210 Menown, Mackenzie, Adgey (br0300) 2000; 21 Padhy, Dandapat (br0450) 2017; 31 Raghu, Unterthiner, Kornblith, Zhang, Dosovitskiy (br0350) 2021; 34 Wagner, Strodthoff, Bousseljot, Kreiseler, Lunze, Samek, Schaeffter (br0420) 2020; 7 Baloglu, Talo, Yildirim, San Tan, Acharya (br0050) 2019; 122 Xu, Chen, Wang, Wang, Li, Jin (br0260) 2021 Jin, Qin, Liu, Lin, Shi, Huang, Liu (br0290) 2020; 203 Fu, Liu (br0250) 2022; 245 Liu, Huang, Chang, Wang, He (br0440) 2018; 45 Yang, Qu, Yang, Cudre-Mauroux (br0140) 2019 Baloglu (10.1016/j.ins.2023.03.078_br0050) 2019; 122 Wagner (10.1016/j.ins.2023.03.078_br0420) 2020; 7 Raghu (10.1016/j.ins.2023.03.078_br0350) 2021; 34 Padhy (10.1016/j.ins.2023.03.078_br0450) 2017; 31 Feng (10.1016/j.ins.2023.03.078_br0330) 2019; vol. 33 He (10.1016/j.ins.2023.03.078_br0080) 2022; 606 Agarwal (10.1016/j.ins.2023.03.078_br0130) 2006 Zhang (10.1016/j.ins.2023.03.078_br0230) 2021; 575 Fan (10.1016/j.ins.2023.03.078_br0160) 2021; 44 Whitney (10.1016/j.ins.2023.03.078_br0320) 1992 Pan (10.1016/j.ins.2023.03.078_br0430) 1985; 3 Jin (10.1016/j.ins.2023.03.078_br0290) 2020; 203 Han (10.1016/j.ins.2023.03.078_br0040) 2020; 185 Goldberger (10.1016/j.ins.2023.03.078_br0410) 2000; 101 Fu (10.1016/j.ins.2023.03.078_br0460) 2020; 20 Fu (10.1016/j.ins.2023.03.078_br0250) 2022; 245 Liu (10.1016/j.ins.2023.03.078_br0470) 2021; 12 Bai (10.1016/j.ins.2023.03.078_br0190) 2021; 110 Vaswani (10.1016/j.ins.2023.03.078_br0340) 2017; 30 Chen (10.1016/j.ins.2023.03.078_br0110) 2020 Sejdinovic (10.1016/j.ins.2023.03.078_br0370) 2013 Feng (10.1016/j.ins.2023.03.078_br0020) 2022; 582 Sun (10.1016/j.ins.2023.03.078_br0480) 2016 Hou (10.1016/j.ins.2023.03.078_br0400) 2022 Andayeshgar (10.1016/j.ins.2023.03.078_br0220) 2022; 19 Zhang (10.1016/j.ins.2023.03.078_br0030) 2021; 97 Menown (10.1016/j.ins.2023.03.078_br0300) 2000; 21 Xu (10.1016/j.ins.2023.03.078_br0260) Feng (10.1016/j.ins.2023.03.078_br0170) 2019; vol. 33 Du (10.1016/j.ins.2023.03.078_br0390) 2020; 204 Niu (10.1016/j.ins.2023.03.078_br0120) 2020 Wu (10.1016/j.ins.2023.03.078_br0200) 2022; 45 Shen (10.1016/j.ins.2023.03.078_br0280) 2022 Xie (10.1016/j.ins.2023.03.078_br0240) 2022; 582 Sgarbossa (10.1016/j.ins.2023.03.078_br0310) 2001; 141 Liu (10.1016/j.ins.2023.03.078_br0090) 2022; 11 Liu (10.1016/j.ins.2023.03.078_br0440) 2018; 45 He (10.1016/j.ins.2023.03.078_br0060) 2021; 210 Ye (10.1016/j.ins.2023.03.078_br0210) 2022 Shen (10.1016/j.ins.2023.03.078_br0360) 2018; vol. 32 Yang (10.1016/j.ins.2023.03.078_br0140) 2019 Zhang (10.1016/j.ins.2023.03.078_br0150) 2018; 27 Yadati (10.1016/j.ins.2023.03.078_br0180) 2019; 32 Gulrajani (10.1016/j.ins.2023.03.078_br0380) 2017; 30 Syeda Nishat (10.1016/j.ins.2023.03.078_br0010) 2021 Van der Maaten (10.1016/j.ins.2023.03.078_br0490) 2008; 9 Han (10.1016/j.ins.2023.03.078_br0270) Wang (10.1016/j.ins.2023.03.078_br0070) 2021; 581 Jiao (10.1016/j.ins.2023.03.078_br0100) 2022; 608 |
| References_xml | – volume: 19 year: 2022 ident: br0220 article-title: Developing graph convolutional networks and mutual information for arrhythmic diagnosis based on multichannel ECG signals publication-title: Int. J. Environ. Res. Public Health – volume: 7 start-page: 1 year: 2020 end-page: 15 ident: br0420 article-title: PTB-XL, a large publicly available electrocardiography dataset publication-title: Sci. Data – volume: 45 start-page: 22 year: 2018 end-page: 32 ident: br0440 article-title: Multiple-feature-branch convolutional neural network for myocardial infarction diagnosis using electrocardiogram publication-title: Biomed. Signal Process. Control – start-page: 437 year: 2020 ident: br0120 article-title: A deep-learning approach to ECG classification based on adversarial domain adaptation publication-title: Healthcare, vol. 8 – volume: 204 year: 2020 ident: br0390 article-title: Wasserstein based transfer network for cross-domain sentiment classification publication-title: Knowl.-Based Syst. – volume: 245 year: 2022 ident: br0250 article-title: Contrastive transformer based domain adaptation for multi-source cross-domain sentiment classification publication-title: Knowl.-Based Syst. – volume: 582 start-page: 480 year: 2022 end-page: 494 ident: br0240 article-title: Automatic online multi-source domain adaptation publication-title: Inf. Sci. – volume: 606 start-page: 649 year: 2022 end-page: 668 ident: br0080 article-title: A novel myocardial infarction localization method using multi-branch densenet and spatial matching-based active semi-supervised learning publication-title: Inf. Sci. – volume: 122 start-page: 23 year: 2019 end-page: 30 ident: br0050 article-title: Classification of myocardial infarction with multi-lead ECG signals and deep CNN publication-title: Pattern Recognit. Lett. – volume: 575 start-page: 599 year: 2021 end-page: 610 ident: br0230 article-title: Deep discriminative domain adaptation publication-title: Inf. Sci. – volume: 9 year: 2008 ident: br0490 article-title: Visualizing data using t-SNE publication-title: J. Mach. Learn. Res. – volume: 581 start-page: 42 year: 2021 end-page: 59 ident: br0070 article-title: Interactive ECG annotation: an artificial intelligence method for smart ECG manipulation publication-title: Inf. Sci. – volume: 20 start-page: 1020 year: 2020 ident: br0460 article-title: Hybrid network with attention mechanism for detection and location of myocardial infarction based on 12-lead electrocardiogram signals publication-title: Sensors – volume: vol. 33 start-page: 3558 year: 2019 end-page: 3565 ident: br0330 article-title: Hypergraph neural networks publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – start-page: 2263 year: 2013 end-page: 2291 ident: br0370 article-title: Equivalence of distance-based and RKHS-based statistics in hypothesis testing publication-title: Ann. Stat. – volume: 44 start-page: 4125 year: 2021 end-page: 4138 ident: br0160 article-title: Heterogeneous hypergraph variational autoencoder for link prediction publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 31 start-page: 71 year: 2017 end-page: 78 ident: br0450 article-title: Third-order tensor based analysis of multilead ECG for classification of myocardial infarction publication-title: Biomed. Signal Process. Control – volume: 3 start-page: 230 year: 1985 end-page: 236 ident: br0430 article-title: A real-time QRS detection algorithm publication-title: IEEE Trans. Biomed. Eng. – volume: 203 year: 2020 ident: br0290 article-title: A novel domain adaptive residual network for automatic atrial fibrillation detection publication-title: Knowl.-Based Syst. – volume: 185 year: 2020 ident: br0040 article-title: ML–ResNet: a novel network to detect and locate myocardial infarction using 12 leads ECG publication-title: Comput. Methods Programs Biomed. – volume: 582 start-page: 509 year: 2022 end-page: 528 ident: br0020 article-title: Unsupervised semantic-aware adaptive feature fusion network for arrhythmia detection publication-title: Inf. Sci. – start-page: 17 year: 2006 end-page: 24 ident: br0130 article-title: Higher order learning with graphs publication-title: Proceedings of the 23rd International Conference on Machine Learning – volume: 30 year: 2017 ident: br0380 article-title: Improved training of Wasserstein GANs publication-title: Adv. Neural Inf. Process. Syst. – start-page: 304 year: 2020 end-page: 307 ident: br0110 article-title: Unsupervised domain adaptation for ECG arrhythmia classification publication-title: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) – volume: 11 year: 2022 ident: br0090 article-title: Deep unsupervised domain adaptation: a review of recent advances and perspectives publication-title: APSIPA Trans. Signal Inf. Process. – volume: 21 start-page: 275 year: 2000 end-page: 283 ident: br0300 article-title: Optimizing the initial 12-lead electrocardiographic diagnosis of acute myocardial infarction publication-title: Eur. Heart J. – start-page: 19847 year: 2022 end-page: 19878 ident: br0280 article-title: Connect Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation – volume: 32 year: 2019 ident: br0180 article-title: Hypergcn: a new method for training graph convolutional networks on hypergraphs publication-title: Adv. Neural Inf. Process. Syst. – year: 2021 ident: br0270 article-title: Learning transferable parameters for unsupervised domain adaptation – volume: 34 start-page: 12116 year: 2021 end-page: 12128 ident: br0350 article-title: Do vision transformers see like convolutional neural networks? publication-title: Adv. Neural Inf. Process. Syst. – year: 2021 ident: br0010 article-title: An update on myocardial infarction publication-title: Current Research and Trends in Medical Science and Technology, vol. 1 – volume: 27 start-page: 5957 year: 2018 end-page: 5968 ident: br0150 article-title: Inductive multi-hypergraph learning and its application on view-based 3d object classification publication-title: IEEE Trans. Image Process. – volume: vol. 32 year: 2018 ident: br0360 article-title: Wasserstein distance guided representation learning for domain adaptation publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – volume: 608 start-page: 1183 year: 2022 end-page: 1201 ident: br0100 article-title: Perturbation-insensitive cross-domain image enhancement for low-quality face verification publication-title: Inf. Sci. – volume: 12 start-page: 15 year: 2021 ident: br0470 article-title: EvoMBN: evolving multi-branch networks on myocardial infarction diagnosis using 12-lead electrocardiograms publication-title: Biosensors – start-page: 2147 year: 2019 end-page: 2157 ident: br0140 article-title: Revisiting user mobility and social relationships in lbsns: a hypergraph embedding approach publication-title: The World Wide Web Conference – start-page: 443 year: 2016 end-page: 450 ident: br0480 article-title: Deep coral: correlation alignment for deep domain adaptation publication-title: European Conference on Computer Vision – volume: 141 start-page: 507 year: 2001 end-page: 517 ident: br0310 article-title: Electrocardiographic diagnosis of acute myocardial infarction: current concepts for the clinician publication-title: Am. Heart J. – volume: 97 year: 2021 ident: br0030 article-title: A multi-dimensional association information analysis approach to automated detection and localization of myocardial infarction publication-title: Eng. Appl. Artif. Intell. – volume: 101 start-page: e215 year: 2000 end-page: e220 ident: br0410 article-title: Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals publication-title: Circulation – volume: vol. 33 start-page: 3558 year: 2019 end-page: 3565 ident: br0170 article-title: Hypergraph neural networks publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – volume: 45 start-page: 3245 year: 2022 end-page: 3258 ident: br0200 article-title: Hypergraph collaborative network on vertices and hyperedges publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 110 year: 2021 ident: br0190 article-title: Hypergraph convolution and hypergraph attention publication-title: Pattern Recognit. – start-page: 23 year: 2022 end-page: 29 ident: br0210 article-title: Online ECG emotion recognition for unknown subjects via hypergraph-based transfer learning publication-title: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence – volume: 210 year: 2021 ident: br0060 article-title: A lightweight and updatable myocardial infarction diagnosis system based on convolutional neural networks and active learning publication-title: Comput. Methods Programs Biomed. – volume: 30 year: 2017 ident: br0340 article-title: Attention is all you need publication-title: Adv. Neural Inf. Process. Syst. – year: 2021 ident: br0260 article-title: Cdtrans: cross-domain transformer for unsupervised domain adaptation. arXiv preprint – start-page: 61 year: 1992 end-page: 79 ident: br0320 article-title: Congruent graphs and the connectivity of graphs publication-title: Hassler Whitney Collected Papers – start-page: 7256 year: 2022 end-page: 7266 ident: br0400 article-title: Batchformer: learning to explore sample relationships for robust representation learning publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – volume: 185 year: 2020 ident: 10.1016/j.ins.2023.03.078_br0040 article-title: ML–ResNet: a novel network to detect and locate myocardial infarction using 12 leads ECG publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2019.105138 – volume: 582 start-page: 480 year: 2022 ident: 10.1016/j.ins.2023.03.078_br0240 article-title: Automatic online multi-source domain adaptation publication-title: Inf. Sci. doi: 10.1016/j.ins.2021.09.031 – volume: 204 year: 2020 ident: 10.1016/j.ins.2023.03.078_br0390 article-title: Wasserstein based transfer network for cross-domain sentiment classification publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2020.106162 – start-page: 61 year: 1992 ident: 10.1016/j.ins.2023.03.078_br0320 article-title: Congruent graphs and the connectivity of graphs – volume: 122 start-page: 23 year: 2019 ident: 10.1016/j.ins.2023.03.078_br0050 article-title: Classification of myocardial infarction with multi-lead ECG signals and deep CNN publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2019.02.016 – start-page: 2147 year: 2019 ident: 10.1016/j.ins.2023.03.078_br0140 article-title: Revisiting user mobility and social relationships in lbsns: a hypergraph embedding approach – volume: 30 year: 2017 ident: 10.1016/j.ins.2023.03.078_br0340 article-title: Attention is all you need publication-title: Adv. Neural Inf. Process. Syst. – volume: 608 start-page: 1183 year: 2022 ident: 10.1016/j.ins.2023.03.078_br0100 article-title: Perturbation-insensitive cross-domain image enhancement for low-quality face verification publication-title: Inf. Sci. doi: 10.1016/j.ins.2022.07.011 – volume: 44 start-page: 4125 issue: 8 year: 2021 ident: 10.1016/j.ins.2023.03.078_br0160 article-title: Heterogeneous hypergraph variational autoencoder for link prediction publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 9 issue: 11 year: 2008 ident: 10.1016/j.ins.2023.03.078_br0490 article-title: Visualizing data using t-SNE publication-title: J. Mach. Learn. Res. – start-page: 23 year: 2022 ident: 10.1016/j.ins.2023.03.078_br0210 article-title: Online ECG emotion recognition for unknown subjects via hypergraph-based transfer learning – volume: 203 year: 2020 ident: 10.1016/j.ins.2023.03.078_br0290 article-title: A novel domain adaptive residual network for automatic atrial fibrillation detection publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2020.106122 – ident: 10.1016/j.ins.2023.03.078_br0270 – start-page: 19847 year: 2022 ident: 10.1016/j.ins.2023.03.078_br0280 – volume: 101 start-page: e215 issue: 23 year: 2000 ident: 10.1016/j.ins.2023.03.078_br0410 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: vol. 32 year: 2018 ident: 10.1016/j.ins.2023.03.078_br0360 article-title: Wasserstein distance guided representation learning for domain adaptation – volume: 606 start-page: 649 year: 2022 ident: 10.1016/j.ins.2023.03.078_br0080 article-title: A novel myocardial infarction localization method using multi-branch densenet and spatial matching-based active semi-supervised learning publication-title: Inf. Sci. doi: 10.1016/j.ins.2022.05.070 – start-page: 437 year: 2020 ident: 10.1016/j.ins.2023.03.078_br0120 article-title: A deep-learning approach to ECG classification based on adversarial domain adaptation – volume: vol. 33 start-page: 3558 year: 2019 ident: 10.1016/j.ins.2023.03.078_br0330 article-title: Hypergraph neural networks – volume: 581 start-page: 42 year: 2021 ident: 10.1016/j.ins.2023.03.078_br0070 article-title: Interactive ECG annotation: an artificial intelligence method for smart ECG manipulation publication-title: Inf. Sci. doi: 10.1016/j.ins.2021.08.095 – volume: 110 year: 2021 ident: 10.1016/j.ins.2023.03.078_br0190 article-title: Hypergraph convolution and hypergraph attention publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2020.107637 – volume: 20 start-page: 1020 issue: 4 year: 2020 ident: 10.1016/j.ins.2023.03.078_br0460 article-title: Hybrid network with attention mechanism for detection and location of myocardial infarction based on 12-lead electrocardiogram signals publication-title: Sensors doi: 10.3390/s20041020 – start-page: 7256 year: 2022 ident: 10.1016/j.ins.2023.03.078_br0400 article-title: Batchformer: learning to explore sample relationships for robust representation learning – volume: 45 start-page: 3245 issue: 3 year: 2022 ident: 10.1016/j.ins.2023.03.078_br0200 article-title: Hypergraph collaborative network on vertices and hyperedges publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 97 year: 2021 ident: 10.1016/j.ins.2023.03.078_br0030 article-title: A multi-dimensional association information analysis approach to automated detection and localization of myocardial infarction publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2020.104092 – start-page: 443 year: 2016 ident: 10.1016/j.ins.2023.03.078_br0480 article-title: Deep coral: correlation alignment for deep domain adaptation – volume: 31 start-page: 71 year: 2017 ident: 10.1016/j.ins.2023.03.078_br0450 article-title: Third-order tensor based analysis of multilead ECG for classification of myocardial infarction publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2016.07.007 – volume: 575 start-page: 599 year: 2021 ident: 10.1016/j.ins.2023.03.078_br0230 article-title: Deep discriminative domain adaptation publication-title: Inf. Sci. doi: 10.1016/j.ins.2021.07.073 – volume: 210 year: 2021 ident: 10.1016/j.ins.2023.03.078_br0060 article-title: A lightweight and updatable myocardial infarction diagnosis system based on convolutional neural networks and active learning publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2021.106379 – start-page: 304 year: 2020 ident: 10.1016/j.ins.2023.03.078_br0110 article-title: Unsupervised domain adaptation for ECG arrhythmia classification – start-page: 17 year: 2006 ident: 10.1016/j.ins.2023.03.078_br0130 article-title: Higher order learning with graphs – volume: 45 start-page: 22 year: 2018 ident: 10.1016/j.ins.2023.03.078_br0440 article-title: Multiple-feature-branch convolutional neural network for myocardial infarction diagnosis using electrocardiogram publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2018.05.013 – volume: vol. 33 start-page: 3558 year: 2019 ident: 10.1016/j.ins.2023.03.078_br0170 article-title: Hypergraph neural networks – volume: 34 start-page: 12116 year: 2021 ident: 10.1016/j.ins.2023.03.078_br0350 article-title: Do vision transformers see like convolutional neural networks? publication-title: Adv. Neural Inf. Process. Syst. – volume: 11 issue: 1 year: 2022 ident: 10.1016/j.ins.2023.03.078_br0090 article-title: Deep unsupervised domain adaptation: a review of recent advances and perspectives publication-title: APSIPA Trans. Signal Inf. Process. doi: 10.1561/116.00000192 – ident: 10.1016/j.ins.2023.03.078_br0260 – volume: 141 start-page: 507 issue: 4 year: 2001 ident: 10.1016/j.ins.2023.03.078_br0310 article-title: Electrocardiographic diagnosis of acute myocardial infarction: current concepts for the clinician publication-title: Am. Heart J. doi: 10.1067/mhj.2001.113571 – volume: 21 start-page: 275 issue: 4 year: 2000 ident: 10.1016/j.ins.2023.03.078_br0300 article-title: Optimizing the initial 12-lead electrocardiographic diagnosis of acute myocardial infarction publication-title: Eur. Heart J. doi: 10.1053/euhj.1999.1748 – volume: 7 start-page: 1 issue: 1 year: 2020 ident: 10.1016/j.ins.2023.03.078_br0420 article-title: PTB-XL, a large publicly available electrocardiography dataset publication-title: Sci. Data doi: 10.1038/s41597-020-0495-6 – year: 2021 ident: 10.1016/j.ins.2023.03.078_br0010 article-title: An update on myocardial infarction – volume: 12 start-page: 15 issue: 1 year: 2021 ident: 10.1016/j.ins.2023.03.078_br0470 article-title: EvoMBN: evolving multi-branch networks on myocardial infarction diagnosis using 12-lead electrocardiograms publication-title: Biosensors doi: 10.3390/bios12010015 – volume: 19 issue: 17 year: 2022 ident: 10.1016/j.ins.2023.03.078_br0220 article-title: Developing graph convolutional networks and mutual information for arrhythmic diagnosis based on multichannel ECG signals publication-title: Int. J. Environ. Res. Public Health doi: 10.3390/ijerph191710707 – volume: 32 year: 2019 ident: 10.1016/j.ins.2023.03.078_br0180 article-title: Hypergcn: a new method for training graph convolutional networks on hypergraphs publication-title: Adv. Neural Inf. Process. Syst. – volume: 30 year: 2017 ident: 10.1016/j.ins.2023.03.078_br0380 article-title: Improved training of Wasserstein GANs publication-title: Adv. Neural Inf. Process. Syst. – start-page: 2263 year: 2013 ident: 10.1016/j.ins.2023.03.078_br0370 article-title: Equivalence of distance-based and RKHS-based statistics in hypothesis testing publication-title: Ann. Stat. – volume: 582 start-page: 509 year: 2022 ident: 10.1016/j.ins.2023.03.078_br0020 article-title: Unsupervised semantic-aware adaptive feature fusion network for arrhythmia detection publication-title: Inf. Sci. doi: 10.1016/j.ins.2021.09.046 – volume: 245 year: 2022 ident: 10.1016/j.ins.2023.03.078_br0250 article-title: Contrastive transformer based domain adaptation for multi-source cross-domain sentiment classification publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2022.108649 – volume: 3 start-page: 230 year: 1985 ident: 10.1016/j.ins.2023.03.078_br0430 article-title: A real-time QRS detection algorithm publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.1985.325532 – volume: 27 start-page: 5957 issue: 12 year: 2018 ident: 10.1016/j.ins.2023.03.078_br0150 article-title: Inductive multi-hypergraph learning and its application on view-based 3d object classification publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2018.2862625 |
| SSID | ssj0004766 |
| Score | 2.4540992 |
| Snippet | Solving individual differences between subjects is critical for the promotion of electrocardiogram (ECG) classification algorithms in the intelligent health... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 245 |
| SubjectTerms | Electrocardiogram Hypergraph Myocardial infarction Patient individual differences Unsupervised domain adaptation |
| Title | Hypergraph and cross-attention-based unsupervised domain adaptation framework for cross-domain myocardial infarction localization |
| URI | https://dx.doi.org/10.1016/j.ins.2023.03.078 |
| Volume | 633 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NS8MwFA9DL3oQnYpfkxzEg1DtmrRZjjKUqbiTg91KvgoT1xXdDl4E_3PfS1OdoB6EXlLympL38j547_1CyInVmWGmC5GqS1XEReIiCYY9YokyEH2wQvjrgO6H2WDEb8fpuEX6TS8MllUG3V_rdK-tw5uLsJsX1WSCPb6J94jBiUZIE9TDnAuU9fO3rzIPLup8JYZJOLvJbPoar0mJiN0J8zineNPaT7Zpyd5cb5KN4CjSy_pftkjLlW2yvgQf2Cad0HRAT2noKsJdpuG4bpP3AQSZzx6SmqrSUr9qhICavsQxQgtm6aJ8WVSoMXBgZ1M1Kamyqqpz9LRoqrcorBA-EWZNX8EQooA9UZBTODGewFvH0N25Q0bXVw_9QRSuXIhMIsUcoslCy0yoIuOZVlo6JxXwMnHSJSpOrZACxlwb5vOZGct4YVLTk5zrXiEd2yUr5ax0e4Rao1i3m8W2Ky1X4IdC6KhTpqSOmQM9uU_iZrNzE_DI8VqMp7wpPHvMgT858ieP4RG9fXL2SVLVYBx_TeYNB_NvEpWDsfid7OB_ZIdkDUd1Ie8RWZk_L1wH3JW5PvbyeExWL2_uBsMP-SrtKA |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEF6kHtSD-MT63IN4EKJpdpN0j1IsVVtPFnoL-wpUbBq0PXgR_OfObDZaQT0IuWyymw07k3kwM98QcmpUoplugadqYxnwNLKBAMUesEhq8D5Ynrp2QIP7pDfkt6N4tEQ6dS0MplV62V_JdCet_Z1Lf5qX5XiMNb6Rs4jBiEZIE5DDyxzbHABTX7x95XnwtApYop-E0-vQpkvyGhcI2R0xB3SKrdZ-Uk4LCqe7Qda9pUivqo_ZJEu22CJrC_iBW-TIVx3QM-rLivCYqf9ft8l7D7zMZ4dJTWVhqNs1QERNl-MYoAozdF68zEsUGTgw04kcF1QaWVZBeprX6VsUdvCv8LMmr6AJkcOeKDAq_DJugVOPvrxzhwy71w-dXuB7LgQ6EukM3MlciSSVecITJZWwVkggZmSFjWQYm1SkMOZKMxfQTFjCcx3rtuBctXNh2S5pFNPC7hFqtGStVhKaljBcgiEKvqOKmRQqZBYEZZOE9WFn2gOSY1-Mp6zOPHvMgD4Z0icL4UrbTXL-uaSs0Dj-msxrCmbfWCoDbfH7sv3_LTshK72HQT_r39zfHZBVfFJl9R6Sxux5bo_AdpmpY8ebH12t7rE |
| 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=Hypergraph+and+cross-attention-based+unsupervised+domain+adaptation+framework+for+cross-domain+myocardial+infarction+localization&rft.jtitle=Information+sciences&rft.au=Yuan%2C+Shuaiying&rft.au=He%2C+Ziyang&rft.au=Zhao%2C+Jianhui&rft.au=Yuan%2C+Zhiyong&rft.date=2023-07-01&rft.issn=0020-0255&rft.volume=633&rft.spage=245&rft.epage=263&rft_id=info:doi/10.1016%2Fj.ins.2023.03.078&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ins_2023_03_078 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0020-0255&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0020-0255&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0020-0255&client=summon |