ECG Based Reliable User Identification Using Deep Learning

Authors: R. N. Begum, Ambalika Sharma, G. K. Singh

Abstract:

Identity theft has serious ramifications beyond data and personal information loss. This necessitates the implementation of robust and efficient user identification systems. Therefore, automatic biometric recognition systems are the need of the hour, and electrocardiogram (ECG)-based systems are unquestionably the best choice due to their appealing inherent characteristics. The Convolutional Neural Networks (CNNs) are the recent state-of-the-art techniques for ECG-based user identification systems. However, the results obtained are significantly below standards, and the situation worsens as the number of users and types of heartbeats in the dataset grows. As a result, this study proposes a highly accurate and resilient ECG-based person identification system using CNN's dense learning framework. The proposed research explores explicitly the caliber of dense CNNs in the field of ECG-based human recognition. The study tests four different configurations of dense CNN which are trained on a dataset of recordings collected from eight popular ECG databases. With the highest False Acceptance Rate (FAR)  of 0.04% and the highest False Rejection Rate (FRR)  of 5%, the best performing network achieved an identification accuracy of 99.94%. The best network is also tested with various train/test split ratios. The findings show that DenseNets are not only extremely reliable, but also highly efficient. Thus, they might also be implemented in real-time ECG-based human recognition systems.

Keywords: Biometrics, dense networks, identification rate, train/test split ratio.

References:

[1] Abdeldayem SS, Bourlai T. A Novel Approach for ECG-Based Human Identification Using Spectral Correlation and Deep Learning. IEEE Trans Biometrics, Behav Identity Sci. 2019;2(1):1–14.
[2] Belgacem N, Amine Naït A, Fethi R. Person Identification System Based on Electrocardiogram Signal Using Lab VIEW. Int J Comput Sci Eng. 2012;4(06):974–81.
[3] Agrafioti F, Hatzinakos D. ECG based recognition using second order statistics. Proc 6th Annu Commun Networks Serv Res Conf CNSR 2008. 2008;82–7.
[4] Hoekema R, Uijen GJH, Van Oosterom A. Geometrical aspects of the interindividual variability of multilead ECG recordings. IEEE Trans Biomed Eng. 2001;48(5):551–9.
[5] Agrafioti F, Hatzinakos D. ECG biometric analysis in cardiac irregularity conditions. Signal, Image Video Process. 2009;3(4):329–43.
[6] Biel L, Pettersson O, Philipson L, Wide P. ECG analysis: A new approach in human identification. IEEE Trans Instrum Meas. 2001;50(3):808–12.
[7] Kyoso M, Uchiyama A. Development of an ECG identification system. In: Annual Reports of the Research Reactor Institute, Kyoto University. 2001. p. 3721–3.
[8] Israel SA, Irvine JM, Cheng A, Wiederhold MD, Wiederhold BK. ECG to identify individuals. Pattern Recognit. 2005;38(1):133–42.
[9] Wang Y, Plataniotis KN, Hatzinakos D. Integrating analytic and appearance attributes for human identification from ECG signals. Biometrics Symp BCC 2006. 2006;
[10] Plataniotis KN, Hatzinakos D, Lee JKM. ECG biometric recognition without fiducial detection. Biometrics Symp BCC 2006. 2006;(May 2014).
[11] Chan ADC, Hamdy MM, Badre A, Badee V. Wavelet distance measure for person identification using electrocardiograms. IEEE Trans Instrum Meas. 2008;57(2):248–53.
[12] Fatemian SZ, Agrafioti F, Hatzinakos D. HeartID: Cardiac biometric recognition. IEEE 4th Int Conf Biometrics Theory, Appl Syst BTAS 2010. 2010;1–5.
[13] Wang Y, Agrafioti F, Hatzinakos D, Plataniotis KN. Analysis of Human Electrocardiogram for Biometric Recognition. EURASIP J Adv Signal Process. 2007;2008(1).
[14] Coutinho DP, Fred ALN, Figueiredo MAT. One-lead ECG-based personal identification using Ziv-Merhav cross parsing. Proc - Int Conf Pattern Recognit. 2010;3858–61.
[15] Venkatesh N, Jayaraman S. Human electrocardiogram for biometrics using DTW and FLDA. Proc - Int Conf Pattern Recognit. 2010;3838–41.
[16] Choi HS, Lee B, Yoon S. Biometric Authentication Using Noisy Electrocardiograms Acquired by Mobile Sensors. IEEE Access. 2016;4:1266–73.
[17] Belgacem N, Fournier R, Nait-Ali A, Bereksi-Reguig F. A novel biometric authentication approach using ECG and EMG signals. J Med Eng Technol. 2015;39(4):226–38.
[18] Tan R, Perkowski M. Toward improving electrocardiogram (ECG) biometric verification using mobile sensors: A two-stage classifier approach. Sensors (Switzerland). 2017;17(2).
[19] Li M, Narayanan S. Robust ECG biometrics by fusing temporal and cepstral information. Proc - Int Conf Pattern Recognit. 2010;(January 2019):1326–9.
[20] Yadav N, Duhan M, Rose A. Biometric Human Recognition using ECG Signals. Iarjset. 2017;4(6):168–71.
[21] Patro K, extraction PK-. Optimized Feature Selection with Mutual Information for ECG based Bio-Metric Recognition system using Genetic Algorithm. ResearchgateNet (Internet). 2018;(May). Available from: https://www.researchgate.net/profile/Kiran_Patro/publication/325153313_Optimized_Feature_Selection_with_Mutual_Information_for_ECG_based_Bio-Metric_Recognition_system_using_Genetic_Algorithm/links/5afae6d2a6fdccacab1770a2/Optimized-Feature-Selection-with-
[22] Page A, Kulkarni A, Mohsenin T. Utilizing deep neural nets for an embedded ECG-based biometric authentication system. IEEE Biomed Circuits Syst Conf Eng Heal Minds Able Bodies, BioCAS 2015 - Proc. 2015;0–3.
[23] Wieclaw L, Khoma Y, Falat P, Sabodashko D, Herasymenko V. Biometrie identification from raw ECG signal using deep learning techniques. Proc 2017 IEEE 9th Int Conf Intell Data Acquis Adv Comput Syst Technol Appl IDAACS 2017. 2017;1:129–33.
[24] Zhang Q, Zhou D. Deep Arm/Ear-ECG Image Learning for Highly Wearable Biometric Human Identification. Ann Biomed Eng. 2018;46(1):122–34.
[25] Zhang Q, Zhou D, Zeng X. PulsePrint: Single-arm-ECG biometric human identification using deep learning. 2017 IEEE 8th Annu Ubiquitous Comput Electron Mob Commun Conf UEMCON 2017. 2017;2018-Janua:452–6.
[26] Eduardo A, Aidos H, Fred A. ECG-based biometrics using a deep auto encoder for feature learning an empirical study on transferability. ICPRAM 2017 - Proc 6th Int Conf Pattern Recognit Appl Methods. 2017;2017-Janua(Icpram):463–70.
[27] Donida Labati R, Muñoz E, Piuri V, Sassi R, Scotti F. Deep-ECG: Convolutional Neural Networks for ECG biometric recognition. Pattern Recognit Lett (Internet). 2019;126:78–85. Available from: https://doi.org/10.1016/j.patrec.2018.03.028
[28] Pourbabaee B. Deep Convolutional Neural Network for ECG-Based Human Identification. C Proc (Internet). 2017;41:7–10. Available from: https://omsignal.com/wp-content/uploads/2017/12/OMsignal-Note-2017-009.pdf
[29] Lynn HM, Yeom S, Kim P. ECG-based biometric human identification based on backpropagation neural network. Proc 2018 Res Adapt Converg Syst RACS 2018. 2018;(1):6–10.
[30] Bogdanov MR, Dumchikova IN, Dokuchaev IS. Deep Learning Based Person Biometric Identification. Int Sci J ‘Industry 40’. 2018;(4):219–22.
[31] Deshmane M, Madhe S. ECG Based Biometric Human Identification Using Convolutional Neural Network in Smart Health Applications. Proc - 2018 4th Int Conf Comput Commun Control Autom ICCUBEA 2018. 2018;1–6.
[32] Kim MG, Ko H, Pan SB. A study on user recognition using 2D ECG based on ensemble of deep convolutional neural networks. J Ambient Intell Humaniz Comput (Internet). 2019;0(0):0. Available from: http://dx.doi.org/10.1007/s12652-019-01195-4
[33] Kim JS, Kim SH, Pan SB. Personal recognition using convolutional neural network with ECG coupling image. J Ambient Intell Humaniz Comput (Internet). 2019;(0123456789). Available from: https://doi.org/10.1007/s12652-019-01401-3
[34] Bento N, Belo D, Gamboa H. ECG Biometrics using Spectrograms and Deep Neural Networks. Int J Mach Learn Comput (Internet). 2020;Vol. 10, N(February). Available from: https://www.researchgate.net/publication/333311161
[35] Moody GB, Mark RG. The impact of the MIT-BIH arrhythmia database. IEEE Eng Med Biol Mag. 2001;20(3):45–50.
[36] Bousseljot R, Kreiseler, D. A, Schnabel, A. N. EKG-Signaldatenbank CARDIODAT der PTB über das Internet. Biomed Tech / Biomed Eng. 1995;pp.317-318.
[37] Laguna P, Mark RG, Goldberg A, Moody GB. Database for evaluation of algorithms for measurement of QT and other waveform intervals in the ECG. Comput Cardiol. 1997;(October 1997):673–6.
[38] Tatiana S. L. Biometric Human Identification Based on Ecg. 2015. p. 1–15.
[39] Nolle FM, Badura FK, Catlett JM, Bowser RW, Sketch MH. Crei-Gard, a New Concept in Computerized Arrhythmia Monitoring Systems. Computers in Cardiology. 1987. p. 515–8.
[40] Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PC, Mark RG, et al. PhysioBank, PhysioToolkit, and PhysioNet Components of a New Research Resource for Complex Physiologic Signals. 2000;
[41] LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, et al. Backpropagation applied to digit recognition. Vol. 1, Neural computation. 1989. p. 541–51.
[42] Rumelhart DE, Hinton GE, Williams RJ. Output Patterns. Parallel Distrib Process Explor Microstruct Cogn (Internet). 1987;567. Available from: https://web.stanford.edu/class/psych209a/ReadingsByDate/02_06/PDPVolIChapter8.pdf
[43] Wolpert DH, Nowlan SJ. Simplifying Neural Networks by Soft Weight Sharing. The Mathematics of Generalization. 2018. p. 373–94.
[44] Yamashita R, Nishio M, Do RKG, Togashi K. Convolutional neural networks: an overview and application in radiology. Insights Imaging. 2018;9(4):611–29.
[45] Abdelwahab M, Busso C. Study of Dense Network Approaches for Speech Emotion Recognition. 2018 IEEE Int Conf Multimed Expo. 2018;5084–8.
[46] Wu J, Xie C-W, Luo J-H. Dense CNN Learning with Equivalent Mappings. 2016;(Nips). Available from: http://arxiv.org/abs/1605.07251
[47] Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. Proc - 30th IEEE Conf Comput Vis Pattern Recognition, CVPR 2017. 2017;2017-Janua:2261–9.
[48] Hammad M, Pławiak P, Wang K, Acharya UR. ResNet-Attention model for human authentication using ECG signals. Expert Syst. 2020; (November 2019):1–17.