Using Convolutional Neural Network and a Single Heartbeat for ECG Biometric Recognition

The electrocardiogram (ECG) signal has become a popular biometric modality due to characteristics that make it suitable for developing reliable authentication systems. However, the long segment of signal required for recognition is still one of the limitations of existing ECG biometric recognition methods and affects its acceptability as a biometric modality. This paper investigates how a short segment of an ECG signal can be effectively used for biometric recognition, using deep-learning techniques. A small convolutional neural network (CNN) is designed to achieve better generalization capability by entropy enhancement of a short segment of a heartbeat signal. Additionally, it investigates how various blind and feature-dependent segments with different lengths affect the performance of the recognition system. Experiments were carried out on two databases for performance evaluation that included single and multisession records. In addition, a comparison was made between the performance of the proposed classifier and four well-known CNN models: GoogLeNet, ResNet, MobileNet and EfficientNet. Using a time–frequency domain representation of a short segment of an ECG signal around the R-peak, the proposed model achieved an accuracy of 99.90% for PTB, 98.20% for the ECG-ID mixed-session, and 94.18% for ECG-ID multisession datasets. Using the preprinted ResNet, we obtained 97.28% accuracy for 0.5-second segments around the R-peaks for ECG-ID multisession datasets, outperforming existing methods. It was found that the time–frequency domain representation of a short segment of an ECG signal can be feasible for biometric recognition by achieving better accuracy and acceptability of this modality.

[1]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[2]  Rytis Maskeliunas,et al.  Combining Cryptography with EEG Biometrics , 2018, Comput. Intell. Neurosci..

[3]  Jiankun Hu,et al.  A fingerprint and finger-vein based cancelable multi-biometric system , 2018, Pattern Recognit..

[4]  Chin-Hui Lee,et al.  Hierarchical Bayesian combination of plug-in maximum a posteriori decoders in deep neural networks-based speech recognition and speaker adaptation , 2017, Pattern Recognit. Lett..

[5]  Abhishek Ranjan,et al.  Permanence of ECG Biometric: Experiments Using Convolutional Neural Networks , 2019, 2019 International Conference on Biometrics (ICB).

[6]  D. Hatzinakos,et al.  ECG Biometric Recognition Without Fiducial Detection , 2006, 2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference.

[7]  Md. Saiful Islam,et al.  End-to-End Deep Learning Fusion of Fingerprint and Electrocardiogram Signals for Presentation Attack Detection , 2020, Sensors.

[8]  Kalamullah Ramli,et al.  Fast and Accurate Algorithm for ECG Authentication Using Residual Depthwise Separable Convolutional Neural Networks , 2020, Applied Sciences.

[9]  Vivek Kanhangad,et al.  Gender classification in smartphones using gait information , 2018, Expert Syst. Appl..

[10]  Yu-Feng Yu,et al.  Discriminative multi-scale sparse coding for single-sample face recognition with occlusion , 2017, Pattern Recognit..

[11]  Haibin Shen,et al.  ECG Authentication Method Based on Parallel Multi-Scale One-Dimensional Residual Network With Center and Margin Loss , 2019, IEEE Access.

[12]  Shun-Chi Wu,et al.  ECG Biometric Recognition: Template-Free Approaches Based on Deep Learning , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[13]  Sung Bum Pan,et al.  Personal recognition using convolutional neural network with ECG coupling image , 2020, J. Ambient Intell. Humaniz. Comput..

[14]  Md. Saiful Islam,et al.  Single Heartbeat ECG Biometric Recognition using Convolutional Neural Network , 2020, 2020 International Conference on Advanced Science and Engineering (ICOASE).

[15]  Lambert Schomaker,et al.  Deep Adaptive Learning for Writer Identification based on Single Handwritten Word Images , 2018, Pattern Recognit..

[16]  I. Jekova,et al.  Biometric verification by cross-correlation analysis of 12-lead ECG patterns: Ranking of the most reliable peripheral and chest leads. , 2017, Journal of electrocardiology.

[17]  Wael Louis,et al.  Feature Selection for Nonstationary Data: Application to Human Recognition Using Medical Biometrics , 2018, IEEE Transactions on Cybernetics.

[18]  Sridha Sridharan,et al.  Super-resolution for biometrics: A comprehensive survey , 2018, Pattern Recognit..

[19]  Xiaolong Zhai,et al.  Automated ECG Classification Using Dual Heartbeat Coupling Based on Convolutional Neural Network , 2018, IEEE Access.

[20]  Vincenzo Piuri,et al.  Deep-ECG: Convolutional Neural Networks for ECG biometric recognition , 2019, Pattern Recognit. Lett..

[21]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[22]  Naif Alajlan,et al.  HBS: A Novel Biometric Feature Based on Heartbeat Morphology , 2012, IEEE Transactions on Information Technology in Biomedicine.

[23]  Xuelong Li,et al.  Toward improving ECG biometric identification using cascaded convolutional neural networks , 2020, Neurocomputing.

[24]  Naif Alajlan,et al.  Resampling of ECG signal for improved morphology alignment , 2012 .

[25]  Bibhas Chandra Dhara,et al.  Person identification using fusion of iris and periocular deep features , 2019, Neural Networks.

[26]  Ye Li,et al.  A Multiscale Autoregressive Model-Based Electrocardiogram Identification Method , 2018, IEEE Access.

[27]  Peter Corcoran,et al.  Deep Neural Network and Data Augmentation Methodology for off-axis iris segmentation in wearable headsets , 2019, Neural Networks.

[28]  Peng Zhang,et al.  A general tensor representation framework for cross-view gait recognition , 2019, Pattern Recognit..

[29]  Yogendra Narain Singh,et al.  PlexNet: A fast and robust ECG biometric system for human recognition , 2021, Inf. Sci..

[30]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Hyun-Soo Choi,et al.  Biometric Authentication Using Noisy Electrocardiograms Acquired by Mobile Sensors , 2016, IEEE Access.

[32]  Chia-Hung Lin,et al.  Optical sensor measurement and biometric-based fractal pattern classifier for fingerprint recognition , 2011, Expert Syst. Appl..

[33]  Jaime S. Cardoso,et al.  Evolution, Current Challenges, and Future Possibilities in ECG Biometrics , 2018, IEEE Access.

[34]  Pankoo Kim,et al.  A Deep Bidirectional GRU Network Model for Biometric Electrocardiogram Classification Based on Recurrent Neural Networks , 2019, IEEE Access.

[35]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[36]  Naif Alajlan,et al.  Biometric template extraction from a heartbeat signal captured from fingers , 2017, Multimedia Tools and Applications.

[37]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[38]  J. Bialasiewicz,et al.  Cross-correlation of bio-signals using continuous wavelet transform and genetic algorithm , 2015, Journal of Neuroscience Methods.

[39]  K P Tripathi,et al.  A Comparative Study of Biometric Technologies with Reference to Human Interface , 2011 .

[40]  Xiaohong Zhang,et al.  ECG authentication system design incorporating a convolutional neural network and generalized S-Transformation , 2018, Comput. Biol. Medicine.

[41]  David Menotti,et al.  Learning Deep Off-the-Person Heart Biometrics Representations , 2017, IEEE Transactions on Information Forensics and Security.

[42]  Duarte Dias,et al.  Beat-ID: Towards a computationally low-cost single heartbeat biometric identity check system based on electrocardiogram wave morphology , 2017, PloS one.

[43]  Arun Kumar Sangaiah,et al.  Lip biometric template security framework using spatial steganography , 2019, Pattern Recognit. Lett..

[44]  A. Lee Swindlehurst,et al.  ECG Biometric Recognition: Unlinkability, Irreversibility, and Security , 2021, IEEE Internet of Things Journal.

[45]  C.-C. Jay Kuo,et al.  ECG-based biometrics using recurrent neural networks , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[46]  Naif Alajlan,et al.  Model-based Alignment of Heartbeat Morphology for Enhancing Human Recognition Capability , 2015, Comput. J..

[47]  Jaime S. Cardoso,et al.  Towards a Continuous Biometric System Based on ECG Signals Acquired on the Steering Wheel , 2017, Sensors.

[48]  Kenta Takahashi,et al.  A measure of information gained through biometric systems , 2014, Image Vis. Comput..

[49]  Naif Alajlan,et al.  Fusion of fingerprint and heartbeat biometrics using fuzzy adaptive genetic algorithm , 2013, World Congress on Internet Security (WorldCIS-2013).

[50]  Sung Bum Pan,et al.  Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics , 2019, Sensors.

[51]  Naif Alajlan,et al.  Selection of Heart-Biometric Templates for Fusion , 2017, IEEE Access.

[52]  Naif Alajlan,et al.  Augmented-hilbert transform for detecting peaks of a finger-ECG signal , 2014, 2014 IEEE Conference on Biomedical Engineering and Sciences (IECBES).

[53]  Minho Lee,et al.  Sensitive deep convolutional neural network for face recognition at large standoffs with small dataset , 2017, Expert Syst. Appl..

[54]  Sérgio F. Chevtchenko,et al.  Multi-objective optimization for hand posture recognition , 2018, Expert Syst. Appl..

[55]  Imran Siddiqi,et al.  Improving handwriting based gender classification using ensemble classifiers , 2017, Expert Syst. Appl..

[56]  Wenyao Xu,et al.  Exploring EEG-based biometrics for user identification and authentication , 2014, 2014 IEEE Signal Processing in Medicine and Biology Symposium (SPMB).

[57]  Xuan Zeng,et al.  HeartID: A Multiresolution Convolutional Neural Network for ECG-Based Biometric Human Identification in Smart Health Applications , 2017, IEEE Access.

[58]  Dimitrios Hatzinakos,et al.  On Evaluating ECG Biometric Systems: Session-Dependence and Body Posture , 2014, IEEE Transactions on Information Forensics and Security.

[59]  Md. Saiful Islam,et al.  Improved sequential fusion of heart-signal and fingerprint for anti-spoofing , 2018, 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis (ISBA).

[60]  Naif Alajlan,et al.  An efficient QRS detection method for ECG signal captured from fingers , 2013, 2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW).

[61]  Atefeh Goshvarpour,et al.  Automatic EEG classification during rapid serial visual presentation task by a novel method based on dual-tree complex wavelet transform and Poincare plot indices , 2018 .

[62]  Hassan Mathkour,et al.  Enhancing the information content of fingerprint biometrics with heartbeat signal , 2015, 2015 World Symposium on Computer Networks and Information Security (WSCNIS).

[63]  Marek A. Perkowski,et al.  Toward Improving Electrocardiogram (ECG) Biometric Verification using Mobile Sensors: A Two-Stage Classifier Approach , 2017, Sensors.

[64]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).