Annals of Biomedical Engineering

, Volume 46, Issue 1, pp 122–134 | Cite as

Deep Arm/Ear-ECG Image Learning for Highly Wearable Biometric Human Identification

  • Qingxue ZhangEmail author
  • Dian Zhou


In this study, to advance smart health applications which have increasing security/privacy requirements, we propose a novel highly wearable ECG-based user identification system, empowered by both non-standard convenient ECG lead configurations and deep learning techniques. Specifically, to achieve a super wearability, we suggest situating all the ECG electrodes on the left upper-arm, or behind the ears, and successfully obtain weak but distinguishable ECG waveforms. Afterwards, to identify individuals from weak ECG, we further present a two-stage framework, including ECG imaging and deep feature learning/identification. In the former stage, the ECG heartbeats are projected to a 2D state space, to reveal heartbeats’ trajectory behaviors and produce 2D images by a split-then-hit method. In the second stage, a convolutional neural network is introduced to automatically learn the intricate patterns directly from the ECG image representations without heavy feature engineering, and then perform user identification. Experimental results on two acquired datasets using our wearable prototype, show a promising identification rate of 98.4% (single-arm-ECG) and 91.1% (ear-ECG), respectively. To the best of our knowledge, it is the first study on the feasibility of using single-arm-ECG/ear-ECG for user identification purpose, which is expected to contribute to pervasive ECG-based user identification in smart health applications.


Smart health Biometric User identification Wearable computers ECG Deep learning Machine learning Convolutional neural network Representation learning 



This research is supported by the Recruitment of Global Experts (the Thousand Talents Plan) and National Natural Science Foundation of China (61574044).


  1. 1.
    Berry, M. J., and G. Linoff. Data mining techniques: for marketing, sales, and customer support. Hoboken: Wiley, 1997.Google Scholar
  2. 2.
    Bojarski M., D. Del Testa, D. Dworakowski, B. Firner, B. Flepp, P. Goyal, L. D. Jackel, M. Monfort, U. Muller, and J. Zhang. End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316, 2016
  3. 3.
    Coutinho, D. P., H. Silva, H. Gamboa, A. Fred, and M. Figueiredo. Novel fiducial and non-fiducial approaches to electrocardiogram-based biometric systems. IET Biom. 2:64–75, 2013.CrossRefGoogle Scholar
  4. 4.
    Fernández-Alemán, J. L., I. C. Señor, P. Á. O. Lozoya, and A. Toval. Security and privacy in electronic health records: a systematic literature review. J. Biomed. Inform. 46:541–562, 2013.CrossRefPubMedGoogle Scholar
  5. 5.
    Gravina, R., P. Alinia, H. Ghasemzadeh, and G. Fortino. Multi-sensor fusion in body sensor networks: state-of-the-art and research challenges. Inf. Fusion 35:68–80, 2017.CrossRefGoogle Scholar
  6. 6.
  7. 7.
    Hejazi M., S. Al-Haddad, S. J. Hashim, A. F. A. Aziz, and Y. P. Singh. Feature level fusion for biometric verification with two-lead ECG signals. In: Signal processing & its applications (CSPA), 2016 IEEE 12th International Colloquium on IEEE, 2016, p. 54–59.Google Scholar
  8. 8.
    Israel, S. A., J. M. Irvine, A. Cheng, M. D. Wiederhold, and B. K. Wiederhold. ECG to identify individuals. Pattern Recognit. 38:133–142, 2005.CrossRefGoogle Scholar
  9. 9.
    Kennel, M. B., R. Brown, and H. D. Abarbanel. Determining embedding dimension for phase-space reconstruction using a geometrical construction. Phys. Rev. A 45:3403, 1992.CrossRefPubMedGoogle Scholar
  10. 10.
    Keras: Deep learning library for theano and tensorFlow.
  11. 11.
    LeCun, Y., Y. Bengio, and G. Hinton. Deep learning. Nature 521:436–444, 2015.CrossRefPubMedGoogle Scholar
  12. 12.
    Lourenço, A., H. Silva, and A. Fred. Unveiling the biometric potential of finger-based ECG signals. Comput. Intell. Neurosci. 2011:5, 2011.CrossRefGoogle Scholar
  13. 13.
    Montano, N., A. Porta, C. Cogliati, G. Costantino, E. Tobaldini, K. R. Casali, and F. Iellamo. Heart rate variability explored in the frequency domain: a tool to investigate the link between heart and behavior. Neurosci. Biobehav. Rev. 33:71–80, 2009.CrossRefPubMedGoogle Scholar
  14. 14.
    Nurminen, H., T. Ardeshiri, R. Piche, and F. Gustafsson. Robust inference for state-space models with skewed measurement noise. IEEE Signal Process. Lett. 22:1898–1902, 2015.CrossRefGoogle Scholar
  15. 15.
    Nvidia. CUDA parallel computing platformGoogle Scholar
  16. 16.
    Riera A., S. Dunne, I. Cester, and G. Ruffini. STARFAST: a wireless wearable EEG/ECG biometric system based on the ENOBIO sensor. In: Proceedings of the International Workshop on Wearable Micro and Nanosystems for Personalised Health, 2008Google Scholar
  17. 17.
    Semmlow, J. L., and B. Griffel. Biosignal and Medical Image Processing. Boca Raton: CRC Press, 2014.Google Scholar
  18. 18.
    Shen, T.-W. D., W. J. Tompkins, and Y. H. Hu. Implementation of a one-lead ECG human identification system on a normal population. J. Eng. Comput. Innov. 2:12–21, 2010.Google Scholar
  19. 19.
    Srivastava, N., G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15:1929–1958, 2014.Google Scholar
  20. 20.
    Tang, X., and L. Shu. Classification of electrocardiogram signals with RS and quantum neural networks. Int. J. Multimed. Ubiquitous Eng. 9:363–372, 2014.CrossRefGoogle Scholar
  21. 21.
    Ting C.-M., and S.-H. Salleh. ECG based personal identification using extended Kalman filter. In: 10th International Conference on Information Science, Signal Processing and their Applications, 2010, pp. 774–777Google Scholar
  22. 22.
    Wichard J. D., M. J. Ogorzałek, and C. Merkwirth. CNN in drug design—recent developments. In: Circuits and Systems (ISCAS), 2015 IEEE International Symposium on IEEE, 2015, pp. 405–408Google Scholar
  23. 23.
    Yan, J., and L. Lu. Improved Hilbert-Huang transform based weak signal detection methodology and its application on incipient fault diagnosis and ECG signal analysis. Signal Process. 98:74–87, 2014.CrossRefGoogle Scholar
  24. 24.
    Yao J., and Y. Wan. A wavelet method for biometric identification using wearable ECG sensors. In: Medical Devices and Biosensors, 2008. ISSS-MDBS 2008. 5th International Summer School and Symposium on IEEE, 2008, pp. 297–300Google Scholar
  25. 25.
    Zhang Q., C. Zahed, V. Nathan, D. A. Hall, and R. Jafari. An ECG dataset representing real-world signal characteristics for wearable computers. In: Biomedical Circuits and Systems Conference (BioCAS), IEEE, 2015, pp. 1–4Google Scholar
  26. 26.
    Zhang Q., D. Zhou, and X. Zeng. A novel framework for motion-tolerant instantaneous heart rate estimation by phase-domain multi-view dynamic time warping. In: IEEE Transactions on Biomedical Engineering Preprint, 2016Google Scholar
  27. 27.
    Zhang, Q., D. Zhou, and X. Zeng. A novel machine learning-enabled framework for instantaneous heart rate monitoring from motion-artifact-corrupted electrocardiogram signals. Physiol. Meas. 37:1945, 2016.CrossRefPubMedGoogle Scholar
  28. 28.
    Zhang, Q., D. Zhou, and X. Zeng. Highly wearable cuff-less blood pressure and heart rate monitoring with single-arm electrocardiogram and photoplethysmogram signals. Biomed. Eng. Online 16:23, 2017.CrossRefPubMedPubMedCentralGoogle Scholar
  29. 29.
    Zhang, Q., D. Zhou, and X. Zeng. A machine learning-empowered system for long-term motion-tolerant wearable monitoring of blood pressure and heart rate with ear-ECG/PPG. IEEE Access 5:10547–10561, 2017.CrossRefGoogle Scholar

Copyright information

© Biomedical Engineering Society 2017

Authors and Affiliations

  1. 1.Department of Electrical EngineeringUniversity of Texas at DallasRichardsonUSA
  2. 2.Department of MicroelectronicsFudan UniversityShanghaiChina
  3. 3.Harvard Medical SchoolBostonUSA
  4. 4.Massachusetts General HospitalBostonUSA

Personalised recommendations