{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T22:34:37Z","timestamp":1773354877338,"version":"3.50.1"},"reference-count":40,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2020,7,22]],"date-time":"2020-07-22T00:00:00Z","timestamp":1595376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["PD\/BDE\/130216\/2017"],"award-info":[{"award-number":["PD\/BDE\/130216\/2017"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The field of biometrics is a pattern recognition problem, where the individual traits are coded, registered, and compared with other database records. Due to the difficulties in reproducing Electrocardiograms (ECG), their usage has been emerging in the biometric field for more secure applications. Inspired by the high performance shown by Deep Neural Networks (DNN) and to mitigate the intra-variability challenges displayed by the ECG of each individual, this work proposes two architectures to improve current results in both identification (finding the registered person from a sample) and authentication (prove that the person is whom it claims) processes: Temporal Convolutional Neural Network (TCNN) and Recurrent Neural Network (RNN). Each architecture produces a similarity score, based on the prediction error of the former and the logits given by the last, and fed to the same classifier, the Relative Score Threshold Classifier (RSTC).The robustness and applicability of these architectures were trained and tested on public databases used by literature in this context: Fantasia, MIT-BIH, and CYBHi databases. Results show that overall the TCNN outperforms the RNN achieving almost 100%, 96%, and 90% accuracy, respectively, for identification and 0.0%, 0.1%, and 2.2% equal error rate (EER) for authentication processes. When comparing to previous work, both architectures reached results beyond the state-of-the-art. Nevertheless, the improvement of these techniques, such as enriching training with extra varied data and transfer learning, may provide more robust systems with a reduced time required for validation.<\/jats:p>","DOI":"10.3390\/s20154078","type":"journal-article","created":{"date-parts":[[2020,7,22]],"date-time":"2020-07-22T07:31:28Z","timestamp":1595403088000},"page":"4078","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["ECG Biometrics Using Deep Learning and Relative Score Threshold Classification"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5337-0430","authenticated-orcid":false,"given":"David","family":"Belo","sequence":"first","affiliation":[{"name":"LIBPhys, Physics Department, Faculty of Sciences and Technology, Nova University of Lisbon, 2825-149 Caparica, Portugal"}]},{"given":"Nuno","family":"Bento","sequence":"additional","affiliation":[{"name":"LIBPhys, Physics Department, Faculty of Sciences and Technology, Nova University of Lisbon, 2825-149 Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6764-8432","authenticated-orcid":false,"given":"Hugo","family":"Silva","sequence":"additional","affiliation":[{"name":"Instituto de Telecomunicacoes, Instituto Superior Tecnico (IST), Technical University of Lisbon, 1049-001 Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1320-5024","authenticated-orcid":false,"given":"Ana","family":"Fred","sequence":"additional","affiliation":[{"name":"Instituto de Telecomunicacoes, Instituto Superior Tecnico (IST), Technical University of Lisbon, 1049-001 Lisboa, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4022-7424","authenticated-orcid":false,"given":"Hugo","family":"Gamboa","sequence":"additional","affiliation":[{"name":"LIBPhys, Physics Department, Faculty of Sciences and Technology, Nova University of Lisbon, 2825-149 Caparica, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2020,7,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1016\/j.patcog.2014.01.016","article-title":"A review of biometric technology along with trends and prospects","volume":"47","author":"Unar","year":"2014","journal-title":"Pattern Recognit."},{"key":"ref_2","first-page":"5","article-title":"Market report: Border biometrics","volume":"2015","author":"Caldwell","year":"2015","journal-title":"Biom. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2511","DOI":"10.1016\/j.procs.2010.04.284","article-title":"Beyond biometrics","volume":"1","year":"2010","journal-title":"Procedia Comput. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Nait-Ali, A. (2011, January 9\u201311). Hidden biometrics: Towards using biosignals and biomedical images for security applications. Proceedings of the 7th International Workshop on Systems, Signal Processing and their Applications (WoSSPA), Tipaza, Algeria.","DOI":"10.1109\/WOSSPA.2011.5931509"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Louren\u00e7o, A., Silva, H., and Fred, A. (2012, January 23\u201326). ECG-based biometrics: A real time classification approach. Proceedings of the International Workshop on Machine Learning for Signal Processing (MLSP), Santander, Spain.","DOI":"10.1109\/MLSP.2012.6349735"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1109\/TPAMI.2017.2669035","article-title":"Demographic Analysis from Biometric Data: Achievements, Challenges, and New Frontiers","volume":"40","author":"Sun","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1109\/TPAMI.2005.57","article-title":"Large-scale evaluation of multimodal biometric authentication using state-of-the-art systems","volume":"27","author":"Snelick","year":"2005","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1109\/JSTSP.2017.2671435","article-title":"ASVspoof: The automatic speaker verification spoofing and countermeasures challenge","volume":"11","author":"Wu","year":"2017","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"738","DOI":"10.1109\/TPAMI.2007.1013","article-title":"Biometrics from Brain Electrical Activity: A Machine Learning Approach","volume":"29","author":"Palaniappan","year":"2007","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Nait-Ali, A. (2011, January 4\u20136). Beyond classical biometrics: When using hidden biometrics to identify individuals. Proceedings of the 3rd European Workshop on Visual Information Processing, Paris, France.","DOI":"10.1109\/EuVIP.2011.6045559"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.compbiomed.2017.06.009","article-title":"Noise detection on ECG based on agglomerative clustering of morphological features","volume":"87","author":"Rodrigues","year":"2017","journal-title":"Comput. Biol. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1016\/j.patrec.2012.11.005","article-title":"QRS detection-free electrocardiogram biometrics in the reconstructed phase space","volume":"34","author":"Fang","year":"2013","journal-title":"Pattern Recognit. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.eswa.2016.09.030","article-title":"ECG databases for biometric systems: A systematic review","volume":"67","author":"Merone","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1172","DOI":"10.1016\/j.patrec.2007.01.014","article-title":"Verification of humans using the electrocardiogram","volume":"28","author":"Stavridis","year":"2007","journal-title":"Pattern Recognit. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.cmpb.2015.05.012","article-title":"Subject identification via ECG fiducial-based systems: Influence of the type of QT interval correction","volume":"121","author":"Gargiulo","year":"2015","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_16","unstructured":"Da Silva, H.P., Fred, A., Louren\u00e7o, A., and Jain, A.K. (October, January 29). Finger ECG signal for user authentication: Usability and performance. Proceedings of the Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS), Washington, DC, USA."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"R1078","DOI":"10.1152\/ajpregu.1996.271.4.R1078","article-title":"Age-related alterations in the fractal scaling of cardiac interbeat interval dynamics","volume":"271","author":"Iyengar","year":"1996","journal-title":"Am. J. -Physiol.-Regul. Integr. Comp. Physiol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/51.932724","article-title":"The impact of the MIT-BIH arrhythmia database","volume":"20","author":"Moody","year":"2001","journal-title":"IEEE Eng. Med. Biol. Mag."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1016\/j.cmpb.2013.11.017","article-title":"Check Your Biosignals Here: A new dataset for off-the-person ECG biometrics","volume":"113","author":"Fred","year":"2014","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chamatidis, I., Katsika, A., and Spathoulas, G. (2017, January 23\u201326). Using deep learning neural networks for ECG based authentication. Proceedings of the International Carnahan Conference on Security Technology (ICCST), Madrid, Spain.","DOI":"10.1109\/CCST.2017.8167816"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wieclaw, L., Khoma, Y., Fa\u0142at, P., Sabodashko, D., and Herasymenko, V. (2017, January 21\u201323). Biometrie identification from raw ECG signal using deep learning techniques. Proceedings of the 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Bucharest, Romania.","DOI":"10.1109\/IDAACS.2017.8095063"},{"key":"ref_22","unstructured":"Labati, R.D., Mu\u00f1oz, E., Piuri, V., Sassi, R., and Scotti, F. (2018). Deep-ECG: Convolutional Neural Networks for ECG biometric recognition. Pattern Recognit. Lett."},{"key":"ref_23","unstructured":"Pourbabaee, B., Howe-Patterson, M., Reiher, E., and Benard, F. (2018, January 8\u201311). Deep convolutional neural network for ECG-based human identification. Proceedings of the CMBES Proceedings, Charlottetown, EI, Canada."},{"key":"ref_24","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_25","doi-asserted-by":"crossref","first-page":"145395","DOI":"10.1109\/ACCESS.2019.2939947","article-title":"A Deep Bidirectional GRU Network Model for Biometric Electrocardiogram Classification Based on Recurrent Neural Networks","volume":"7","author":"Lynn","year":"2019","journal-title":"IEEE Access."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1109\/TIFS.2017.2784362","article-title":"Learning Deep Off-the-Person Heart Biometrics Representations","volume":"13","author":"Moreira","year":"2018","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_27","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_28","unstructured":"Tantawi, M., Revett, K., and Salem, A.B. (2013, January 25\u201327). ECG based Biometric Recognition using Wavelets and RBF Neural Network 1 Introduction 2 Related Work. Proceedings of the 7th European Computing Conference, Dubrovnik, Croatia."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s10844-012-0214-7","article-title":"Fiducial feature reduction analysis for electrocardiogram (ECG) based biometric recognition","volume":"40","author":"Tantawi","year":"2013","journal-title":"J. Intell. Inf. Syst."},{"key":"ref_30","unstructured":"Shen, J., Bao, S.D., Yang, L.C., and Li, Y. (September, January 30). The PLR-DTW method for ECG based biometric identification. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, Boston, MA, USA."},{"key":"ref_31","unstructured":"Rabhi, E., and Lachiri, Z. (2013, January 22\u201325). Biometric personal identification system using the ECG signal. Proceedings of the Computing in Cardiology Conference (CinC), Zaragoza, Spain."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.jnca.2014.04.008","article-title":"Data mining in mobile ECG based biometric identification","volume":"44","author":"Sidek","year":"2014","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2930","DOI":"10.1109\/TBME.2012.2213253","article-title":"Heartbeat classification using morphological and dynamic features of ECG signals","volume":"59","author":"Ye","year":"2012","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1186\/s12938-017-0405-0","article-title":"Biosignals learning and synthesis using deep neural networks","volume":"16","author":"Belo","year":"2017","journal-title":"Biomed. Eng. Online"},{"key":"ref_35","first-page":"15","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"Tieleman","year":"2012","journal-title":"Coursera: Neural Networks Mach. Learn."},{"key":"ref_36","unstructured":"Bai, S., Kolter, J.Z., and Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"259","DOI":"10.18178\/ijmlc.2020.10.2.929","article-title":"ECG Biometrics Using Spectrograms and Deep Neural Networks","volume":"10","author":"Bento","year":"2019","journal-title":"Int. J. Mach. Learn. Comput."},{"key":"ref_38","unstructured":"Kingma, D., and Ba, J. (2015, January 7\u20139). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference for Learning Representations, San Diego, CA, USA."},{"key":"ref_39","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":"2008","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Fatemian, S.Z., and Hatzinakos, D. (2009, January 5\u20137). A new ECG feature extractor for biometric recognition. Proceedings of the DSP 2009: 16th International Conference on Digital Signal Processing, Santorini, Greece.","DOI":"10.1109\/ICDSP.2009.5201143"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/15\/4078\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:50:43Z","timestamp":1760176243000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/15\/4078"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,22]]},"references-count":40,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2020,8]]}},"alternative-id":["s20154078"],"URL":"https:\/\/doi.org\/10.3390\/s20154078","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,22]]}}}