Study on Matthew Effect Based Feature Extraction for ECG Biometric

  • Gang ZhengEmail author
  • Yu Wang
  • XiaoXia Sun
  • Ying Sun
  • ShengZhen Ji
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11266)


Electrocardiogram (ECG) is a “live” signal and is very difficult to be copied or forged, which make it becoming a competitive biology material for biometric. But, due to ECG signals are easily be affected by the external environment and human states (physiological or psychological), therefore, finding stable features becomes one of the key issues in the research. The paper proposed a feature extraction method based on ECG superposition matrix of single heartbeat ECG. By matrix segmentation and similarity comparison, ECG stable feature distribution area can be selected, and stable feature sets are constructed. And through further study, it is found that a large number of heartbeats are need to build superposition matrix. For solving the problem, the paper proposed a Matthew effect based method, by which superposition matrix can be constructed by only 10 heartbeats. Experiments results showed that average TPR of 100 heartbeats was reaching 83.21, 83.93 and 80% respectively. And that of 10 heartbeats with Matthew Effect reach 80.36, 82.68 and 80.77% respectively, which is competitive compare to 100 heartbeats superposition matrix.


ECG biometric Matthew effect Superposition matrix Identity recognition 



The paper was supported by TianJin Nature Science Foundation 16JCYBJC15300.


  1. 1.
    Ogawa, M., et al.: Fully automated biosignal acquisition system for home health monitoring. In: 1997 Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 6, pp. 2403–2405. IEEE, USA (1997)Google Scholar
  2. 2.
    Sidek, K.A., Khalil, I., Jelinek, H.F.: ECG biometric with abnormal cardiac conditions in remote monitoring system. IEEE Trans. Syst. Man Cybern. Syst. 44(11), 1498–1509 (2014)CrossRefGoogle Scholar
  3. 3.
    Zhao, Z., Yang, L., Chen, D., et al.: A human ECG identification system based on ensemble empirical mode decomposition. Sensors 13(5), 6832–6864 (2013)CrossRefGoogle Scholar
  4. 4.
    Belgacem, N., Fournier, R., et al.: A novel biometric authentication approach using ECG and EMG signals. J. Med. Eng. Technol. 39(4), 226–238 (2015)CrossRefGoogle Scholar
  5. 5.
  6. 6.
    Sansone, M., Fratini, A., Cesarelli, M., et al.: Influence of QT correction on temporal and amplitude features for human identification via ECG. In: 2013 Biometric Measurements and Systems for Security and Medical Applications, pp. 22–27. IEEE, Naples (2013)Google Scholar
  7. 7.
    Choi, H.S., Lee, B., Yoon, S.: Biometric authentication using noisy electrocardiograms acquired by mobile sensors. IEEE Access 4, 1266–1273 (2016)CrossRefGoogle Scholar
  8. 8.
    Arteaga-Falconi, J.S., Osman, H.A., Saddik, A.E.: ECG authentication for mobile devices. IEEE Trans. Instrum. Meas. 65(3), 591–600 (2016)CrossRefGoogle Scholar
  9. 9.
    Singh, Y.N.: Human recognition using Fisher’s discriminant analysis of heartbeat interval features and ECG morphology. Neurocomputing 167, 322–335 (2015)CrossRefGoogle Scholar
  10. 10.
    Islam, M.S., Alajlan, N., Bazi, Y., et al.: HBS: a novel biometric feature based on heartbeat morphology. IEEE Trans. Inf. Technol. Biomed. 16(3), 445–453 (2012)CrossRefGoogle Scholar
  11. 11.
    Kouchaki, S., Dehghani, A., Omranian, S., et al.: ECG-based personal identification using empirical mode decomposition and Hilbert transform. In: 2012 CSI International Symposium on Artificial Intelligence and Signal Processing, pp. 569–573. IEEE, Shiraz (2012)Google Scholar
  12. 12.
    Matos, A.C., et al.: Biometric recognition system using low bandwidth ECG signals. In: 2013 International Conference on E-Health Networking, Applications & Services, pp. 518–522. IEEE, Lisbon (2013)Google Scholar
  13. 13.
    Venugopalan, S., Savvides, M., Griofa, M.O., et al.: Analysis of low-dimensional radio-frequency impedance-based cardio-synchronous waveforms for biometric authentication. IEEE Trans. Biomed. Eng. 61(8), 2324–2335 (2014)CrossRefGoogle Scholar
  14. 14.
    Zeng, F., Tseng, K.K., Huang, H.N., et al.: A new statistical-based algorithm for ECG identification. In: 2012 Eighth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp. 301–304. IEEE Computer Society, Piraeus (2012)Google Scholar
  15. 15.
    Hejazi, M., Al-Haddad, S.A.R., et al.: ECG biometric authentication based on non-fiducial approach using kernel methods. Digit. Signal Process. 52(C), 72–86 (2016)CrossRefGoogle Scholar
  16. 16.
    Safie, S.I., Soraghan, J.J., Petropoulakis, L.: Pulse active mean (PAM): a PIN supporting feature extraction algorithm for doubly secure authentication. In: 2011 International Conference on Information Assurance and Security, pp. 210–214. IEEE, Melaka (2011)Google Scholar
  17. 17.
    Coutinho, D.P., Silva, H., Gamboa, H., et al.: Novel fiducial and non-fiducial approaches to electrocardiogram-based biometric systems. IET Biom. 2(2), 64–75 (2013)CrossRefGoogle Scholar
  18. 18.
    Chen, H., Zeng, F., Tseng, K.K., et al.: ECG human identification with statistical support vector machines. In: 2012 International Conference on Computing, Measurement, Control and Sensor Network, pp. 237–240. IEEE Computer Society, Taiyuan (2012)Google Scholar
  19. 19.
    Merone, M., Soda, P., Sansone, M., et al.: ECG databases for biometric systems: a systematic review. Expert Syst. Appl. 67, 189–202 (2017)CrossRefGoogle Scholar
  20. 20.
    Sidek, K., Khali, I.: Biometric sample extraction using Mahalanobis distance in Cardioid based graph using electrocardiogram signals. In: 2012 Engineering in Medicine and Biology Society, pp. 3396–3399. IEEE, San Diego (2012)Google Scholar
  21. 21.
    Wang, J., She, M., Nahavandi, S., et al.: Human identification from ECG signals via sparse representation of local segments. IEEE Signal Process. Lett. 20(10), 937–940 (2013)CrossRefGoogle Scholar
  22. 22.
    Lin, S.L., Chen, C.K., Lin, C.L., et al.: Individual identification based on chaotic electrocardiogram signals during muscular exercise. Biom. IET 3(4), 257–266 (2014)MathSciNetCrossRefGoogle Scholar
  23. 23.
    Sidek, K.A., Mai, V., Khalil, I.: Data mining in mobile ECG based biometric identification. J. Netw. Comput. Appl. 44(2), 83–91 (2014)CrossRefGoogle Scholar
  24. 24.
    Page, A., et al.: Utilizing deep neural nets for an embedded ECG-based biometric authentication system. In: 2015 Biomedical Circuits and Systems Conference, pp. 1–4. IEEE, Atlanta (2015)Google Scholar
  25. 25.
    Venkatesh, N., et al.: Human electrocardiogram for biometrics using DTW and FLDA. In: 2010 International Conference on Pattern Recognition, pp. 3838–3841. IEEE, Istanbul (2010)Google Scholar
  26. 26.
    Yang, L.U., Bao, S., Zhou, X., et al.: Real-time human identification algorithm based on dynamic electrocardiogram signal. J. Comput. Appl. 35(1), 262–264 (2015)Google Scholar
  27. 27.
    Rabhi, E., Lachiri, Z.: Biometric personal identification system using the ECG signal. In: 2014 Computing in Cardiology Conference, pp. 507–510. IEEE, Zaragoza (2014)Google Scholar
  28. 28.
    Sahadat, M.N., Jacobs, E.L., Morshed, B.I.: Hardware-efficient robust biometric identification from 0.58 second template and 12 features of limb (Lead I) ECG signal using logistic regression classifier. In: Conference Proceedings IEEE Engineering in Medicine and Biology Society, pp. 1440–1443 (2014)Google Scholar
  29. 29.
    Gutta, S., et al.: Joint feature extraction and classifier design for ECG based biometric recognition. IEEE J. Biomed. Health Inf. 20(2), 460–468 (2016)CrossRefGoogle Scholar
  30. 30.
    Hari, S., et al.: Design of a Hamming-distance classifier for ECG biometrics. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3009–3012. IEEE, Vancouver (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Gang Zheng
    • 1
    Email author
  • Yu Wang
    • 1
  • XiaoXia Sun
    • 1
  • Ying Sun
    • 1
  • ShengZhen Ji
    • 1
  1. 1.School of Computer Science and EngineeringTianjin University of TechnologyTianjinChina

Personalised recommendations