{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T21:00:39Z","timestamp":1786482039855,"version":"3.56.0"},"reference-count":41,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2022,4,30]],"date-time":"2022-04-30T00:00:00Z","timestamp":1651276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Higher Education Malaysia for Fundamental Research Grant Scheme","award":["FRGS\/1\/2020\/ICT03\/USM\/02\/1"],"award-info":[{"award-number":["FRGS\/1\/2020\/ICT03\/USM\/02\/1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The existing electrocardiogram (ECG) biometrics do not perform well when ECG changes after the enrollment phase because the feature extraction is not able to relate ECG collected during enrollment and ECG collected during classification. In this research, we propose the sequence pair feature extractor, inspired by Bidirectional Encoder Representations from Transformers (BERT)\u2019s sentence pair task, to obtain a dynamic representation of a pair of ECGs. We also propose using the self-attention mechanism of the transformer to draw an inter-identity relationship when performing ECG identification tasks. The model was trained once with datasets built from 10 ECG databases, and then, it was applied to six other ECG databases without retraining. We emphasize the significance of the time separation between enrollment and classification when presenting the results. The model scored 96.20%, 100.0%, 99.91%, 96.09%, 96.35%, and 98.10% identification accuracy on MIT-BIH Atrial Fibrillation Database (AFDB), Combined measurement of ECG, Breathing and Seismocardiograms (CEBSDB), MIT-BIH Normal Sinus Rhythm Database (NSRDB), MIT-BIH ST Change Database (STDB), ECG-ID Database (ECGIDDB), and PTB Diagnostic ECG Database (PTBDB), respectively, over a short time separation. The model scored 92.70% and 64.16% identification accuracy on ECGIDDB and PTBDB, respectively, over a long time separation, which is a significant improvement compared to state-of-the-art methods.<\/jats:p>","DOI":"10.3390\/s22093446","type":"journal-article","created":{"date-parts":[[2022,5,3]],"date-time":"2022-05-03T08:26:35Z","timestamp":1651566395000},"page":"3446","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Electrocardiogram Biometrics Using Transformer\u2019s Self-Attention Mechanism for Sequence Pair Feature Extractor and Flexible Enrollment Scope Identification"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3989-3411","authenticated-orcid":false,"given":"Kai Jye","family":"Chee","sequence":"first","affiliation":[{"name":"School of Electrical and Electronic Engineering, USM Engineering Campus, Universiti Sains Malaysia, Nibong Tebal 14300, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4392-2895","authenticated-orcid":false,"given":"Dzati Athiar","family":"Ramli","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, USM Engineering Campus, Universiti Sains Malaysia, Nibong Tebal 14300, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,4,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1109\/19.930458","article-title":"ECG Analysis: A New Approach in Human Identification","volume":"50","author":"Biel","year":"2001","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kim, H.J., and Lim, J.S. (2017, January 15\u201317). Study on a Biometric Authentication Model Based on ECG Using a Fuzzy Neural Network. Proceedings of the IOP Conference Series: Materials Science and Engineering, Shanghai, China.","DOI":"10.1088\/1757-899X\/317\/1\/012030"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Pinto, J.R., Cardoso, J.S., and Louren\u00e7o, A. (2020). Deep Neural Networks for Biometric Identification Based on Non-Intrusive ECG Acquisitions. The Biometric Computing, CRC Press.","DOI":"10.1201\/9781351013437-11"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Barros, A., Resque, P., Almeida, J., Mota, R., Oliveira, H., Ros\u00e1rio, D., and Cerqueira, E. (2020). Data Improvement Model Based on Ecg Biometric for User Authentication and Identification. Sensors, 20.","DOI":"10.3390\/s20102920"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Tan, R., and Perkowski, M. (2016, January 18\u201320). ECG Biometric Identification Using Wavelet Analysis Coupled with Probabilistic Random Forest. Proceedings of the 2016 15th IEEE International Conference on Machine Learning and Applications, ICMLA, Anaheim, CA, USA.","DOI":"10.1109\/ICMLA.2016.0038"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Sun, H., Guo, Y., Chen, B., and Chen, Y. (2019, January 9\u201313). A Practical Cross-Domain ECG Biometric Identification Method. Proceedings of the 2019 IEEE Global Communications Conference, GLOBECOM, Waikoloa, HI, USA.","DOI":"10.1109\/GLOBECOM38437.2019.9014278"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Agrafioti, F., and Hatzinakos, D. (2008, January 5\u20138). ECG Based Recognition Using Second Order Statistics. Proceedings of the 6th Annual Communication Networks and Services Research Conference, CNSR 2008, Halifax, NS, Canada.","DOI":"10.1109\/CNSR.2008.38"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"591","DOI":"10.1109\/TIM.2015.2503863","article-title":"ECG Authentication for Mobile Devices","volume":"65","year":"2016","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"467","DOI":"10.3389\/fpsyg.2018.00467","article-title":"Biometric and Emotion Identification: An ECG Compression Based Method","volume":"9","author":"Ferreira","year":"2018","journal-title":"Front. Psychol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"148658","DOI":"10.1155\/2008\/148658","article-title":"Analysis of Human Electrocardiogram for Biometric Recognition","volume":"2008","author":"Wang","year":"2007","journal-title":"EURASIP J. Adv. Signal. Process."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Sellami, A., Zouaghi, A., and Daamouche, A. (2017, January 29\u201331). ECG as a Biometric for Individual\u2019s Identification. Proceedings of the 2017 5th International Conference on Electrical Engineering\u2014Boumerdes, ICEE-B 2017, Boumerdes, Algeria.","DOI":"10.1109\/ICEE-B.2017.8192201"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yan, G., Liang, S., Zhang, Y., and Liu, F. (2019, January 18\u201321). Fusing Transformer Model with Temporal Features for ECG Heartbeat Classification. Proceedings of the 2019 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2019, San Diego, CA, USA.","DOI":"10.1109\/BIBM47256.2019.8983326"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2095","DOI":"10.1109\/TSMC.2017.2705582","article-title":"Deep Convolutional Neural Networks and Learning ECG Features for Screening Paroxysmal Atrial Fibrillation Patients","volume":"48","author":"Pourbabaee","year":"2018","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"117853","DOI":"10.1109\/ACCESS.2020.3004464","article-title":"ECG Biometric Authentication: A Comparative Analysis","volume":"8","author":"Ingale","year":"2020","journal-title":"IEEE Access"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Li, X., Wu, A., and Zheng, W.S. (2018). Adversarial Open-World Person Re-Identification. Computer Vision\u2014ECCV 2018, Springer. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-030-01216-8_18"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2286","DOI":"10.1109\/TIP.2017.2740564","article-title":"Fast Open-World Person Re-Identification","volume":"27","author":"Zhu","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Chan-Lang, S., Pham, Q.C., and Achard, C. (December, January 29). Closed and Open-World Person Re-Identification and Verification. Proceedings of the DICTA 2017\u20142017 International Conference on Digital Image Computing: Techniques and Applications, Sydney, Australia.","DOI":"10.1109\/DICTA.2017.8227416"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.patrec.2018.03.028","article-title":"Deep-ECG: Convolutional Neural Networks for ECG Biometric Recognition","volume":"126","author":"Piuri","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Pal, A., and Singh, Y.N. (2018, January 9\u201311). ECG Biometric Recognition. Proceedings of the Communications in Computer and Information Science, Varanasi, India.","DOI":"10.1007\/978-981-13-0023-3_7"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Page, A., Kulkarni, A., and Mohsenin, T. (2015, January 22\u201324). Utilizing Deep Neural Nets for an Embedded ECG-Based Biometric Authentication System. Proceedings of the IEEE Biomedical Circuits and Systems Conference: Engineering for Healthy Minds and Able Bodies, BioCAS 2015, Atlanta, GA, USA.","DOI":"10.1109\/BioCAS.2015.7348372"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.neucom.2020.01.019","article-title":"Toward Improving ECG Biometric Identification Using Cascaded Convolutional Neural Networks","volume":"391","author":"Li","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Salloum, R., and Kuo, C.C.J. (2017, January 5\u20139). ECG-Based Biometrics Using Recurrent Neural Networks. Proceedings of the ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, New Orleans, LA, USA.","DOI":"10.1109\/ICASSP.2017.7952519"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"11805","DOI":"10.1109\/ACCESS.2017.2707460","article-title":"HeartID: A Multiresolution Convolutional Neural Network for ECG-Based Biometric Human Identification in Smart Health Applications","volume":"5","author":"Zhang","year":"2017","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1812","DOI":"10.1109\/TIFS.2012.2215324","article-title":"ECG Biometric Recognition: A Comparative Analysis","volume":"7","author":"Odinaka","year":"2012","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1109\/JBHI.2016.2546300","article-title":"Multiple ECG Fiducial Points-Based Random Binary Sequence Generation for Securing Wireless Body Area Networks","volume":"21","author":"Zheng","year":"2017","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ko, H., Mesicek, L., and Pan, S.B. (2019). ECG Security Challenges: Case Study on Change of ECG According to Time for User Identification. Handbook of Multimedia Information Security: Techniques and Applications, Springer.","DOI":"10.1007\/978-3-030-15887-3_29"},{"key":"ref_27","first-page":"265","article-title":"On the Algorithmic Implementation of Multi-class Kernel-Based Vector Machines","volume":"2","author":"Crammer","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"809","DOI":"10.1007\/s10994-019-05786-2","article-title":"N-Ary Decomposition for Multi-Class Classification","volume":"108","author":"Zhou","year":"2019","journal-title":"Mach. Learn."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2335","DOI":"10.1109\/TPAMI.2015.2430325","article-title":"Joint Binary Classifier Learning for ECOC-Based Multi-Class Classification","volume":"38","author":"Liu","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1198\/016214504000000098","article-title":"Multicategory Support Vector Machines","volume":"99","author":"Lee","year":"2004","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_31","first-page":"1","article-title":"GenSVM: A Generalized Multiclass Support Vector Machine","volume":"17","author":"Groenen","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"136","DOI":"10.37936\/ecti-cit.201262.54335","article-title":"Binary Classication Tree for Multi-class Classication with Observation-Based Clustering","volume":"6","author":"Athimethphat","year":"1970","journal-title":"ECTI Trans. Comput. Inf. Technol. (ECTI-CIT)"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"S\u00e1nchez-Maro\u00f1o, N., Alonso-Betanzos, A., Garc\u00eda-Gonz\u00e1lez, P., and Bol\u00f3n-Canedo, V. (2010, January 18\u201323). Multiclass Classifiers vs. Multiple Binary Classifiers Using Filters for Feature Selection. Proceedings of the International Joint Conference on Neural Networks, Barcelona, Spain.","DOI":"10.1109\/IJCNN.2010.5596567"},{"key":"ref_34","unstructured":"Luo, Y. (2008, January 4\u20136). Can Subclasses Help a Multi-class Learning Problem?. Proceedings of the IEEE Intelligent Vehicles Symposium, Eindhoven, The Netherlands."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"e215","DOI":"10.1161\/01.CIR.101.23.e215","article-title":"PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals","volume":"101","author":"Goldberger","year":"2000","journal-title":"Circulation"},{"key":"ref_36","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention Is All You Need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_37","unstructured":"Kingma, D.P., and Ba, J.L. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations, San Diego, CA, USA."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_39","first-page":"227","article-title":"A New Method for Detecting Atrial Fibrillation Using R-R Intervals","volume":"10","author":"Moody","year":"1983","journal-title":"Comput. Cardiol."},{"key":"ref_40","unstructured":"Albrecht, P. (1983). ST Segment Characterization for Long-Term Automated ECG Analysis. [Master\u2019s Thesis, MIT Deptartment of Electrical Engineering and Computer Science]."},{"key":"ref_41","unstructured":"Garcia-Gonzalez, M.A., Argelagos-Palau, A., Fernandez-Chimeno, M., and Ramos-Castro, J. (2013, January 22\u201325). A Comparison of Heartbeat Detectors for the Seismocardiogram. Proceedings of the Computing in Cardiology, Zaragoza, Spain."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/9\/3446\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:05:10Z","timestamp":1760137510000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/9\/3446"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,30]]},"references-count":41,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["s22093446"],"URL":"https:\/\/doi.org\/10.3390\/s22093446","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,30]]}}}