Outlier Correction in ECG-Based Human Identification

  • Volodymyr Khoma
  • Mariusz Pelc
  • Yuriy Khoma
  • Dmytro Sabodashko
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 720)


In this article we have proposed a novel method for ECG signal processing in biometric applications. The main idea is to correct anomalies in various segments of ECG waveform rather than skipping a corrupted ECG heartbeat, as it is commonly done in most cases. The proposed approach is taking into consideration that biosignals are of quasi-periodic nature.

Neighbouring ECG heartbeats are analysed using a sliding window. Within such a window the analysis of samples distributions is being performed. This information allows to detect outlying samples and correct them with expected values. Such an approach allows to collect better statistical representation which improves identification models performance.

In order to validate our method we used open-source Physionet ECG-ID database. This database contains 310 records per 90 unique persons. The classification result reported on this data set using commonly known outlier detection approach was 91%. We carried out a number of experiments and then compared the obtained results to those obtained using the outlier correction method described above. Classification results for our method exceeded 95%. Thus, misclassification error rate has been improved twice.


Outlier correction Anomaly detection Biometrics Human identification ECG Physionet ECG-ID database 


  1. 1.
    Jenkins, D., Gerred, S.: ECGs by Example, 3rd edn., 238 p. Elsilver (2011)Google Scholar
  2. 2.
    Aslanger, E., Yalin, K.: Electromechanical association: a subtle electrocardiogram artifact. J. Electrocardiol. 45(1), 15–17 (2012)CrossRefGoogle Scholar
  3. 3.
    Urigüen, J.A., Garcia-Zapirain, B.: EEG artifact removal-state-of-the-art and guidelines. J. Neural Eng. 12(3), 031001 (2015)CrossRefGoogle Scholar
  4. 4.
    Fratini, A., Sansone, M., Bifulco, P., Cesarel, M.: Individual identification via electrocardiogram analysis. BioMed. Eng. OnLine 14, 1–23 (2015)CrossRefGoogle Scholar
  5. 5.
    Kaur, G., Singh, D., Kaur, S.: Electrocardiogram (ECG) as a biometric characteristic: a review. Int. J. Emerg. Res. Manage. Technol. 4(5), 202–206 (2015)Google Scholar
  6. 6.
    Shen, T.W., Tompkins, W.J., Hu, Y.H.: One-lead ECG for identity verification. In: Proceedings of the 2nd Joint Conference on the IEEE Engineering in Medicine and Biology Society and the Biomedical Engineering Society, vol. 1, pp. 62–63 (2002)Google Scholar
  7. 7.
    Cunha, J., Cunha, B., Xavier, W., Ferreira, N., Pereira, A.: Vital-Jacket: a wearable wireless vital signs monitor for patients’ mobility. In: Proceedings of the Avantex Symposium (2007)Google Scholar
  8. 8.
    Tax, D., Duin, R.: Outliers and data descriptions. In: Proceedings 7th Annual Conference on the Advanced School for Computing and Imaging (ASCI) (2001)Google Scholar
  9. 9.
    Hodge, V.J., Austin, J.: A survey of outlier detection methodologies. Artif. Intell. Rev. 22, 85–126 (2004)CrossRefzbMATHGoogle Scholar
  10. 10.
    Lourenço, A., Silva, H., Carreiras, C., Fred, A.: Outlier detection in non-intrusive ECG biometric system. In: Kamel, M., Campilho, A. (eds.) ICIAR 2013. LNCS, vol. 7950, pp. 43–52. Springer, Heidelberg (2013). Scholar
  11. 11.
    Matos A.C., Lourenc A., Nascimento, J.: Embedded system for individual recognition based on ECG Biometrics. In: Proceedings of the Conference on Electronics, Telecommunications and Computers – CETC, pp. 265–272 (2013)Google Scholar
  12. 12.
    Lugovaya, T.S.: Biometric human identification based on electrocardiogram. [Master’s thesis] Faculty of Computing Technologies and Informatics, Electrotechnical University “LETI”, Saint-Petersburg, Russian Federation, June 2005Google Scholar
  13. 13.
    AlMahamdy, M., Bryan Riley, H.: Performance study of different denoising methods for ECG signals. In: Proceedings of the 4th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare (ICTH-2014), pp. 325–332 (2014)Google Scholar
  14. 14.
    Varshney, M., Chandrakar, C., Sharma, M.: A survey on feature extraction and classification of ECG signal. Int. J. Adv. Res. Electr. Electron. Instrum. Eng. 3(1), 6572–6576 (2014)Google Scholar
  15. 15.
  16. 16.
    Pan, J., Tompkins, W.J.: A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. 32(3), 230–236 (1985)CrossRefGoogle Scholar
  17. 17.
    Duda, R.O., Hart, P.E., Stork, D.H.: Pattern Classification, 2nd edn. Wiley Interscience (2000)Google Scholar
  18. 18.
    Jolliffe, I.T.: Principal Component Analysis. Springer Series in Statistics, 2nd edn., 487 p. Springer, New York (2002)Google Scholar
  19. 19.
    Python-based ecosystem of open-source software. Accessed 12 Apr 2017
  20. 20.
    BioSPPy - Biosignal Processing in Python. A toolbox for biosignal processing written in Python. Accessed 12 Apr 2017
  21. 21.
    ecg-identification: Package to process common ECG signals for human identification purposes. Acceseed 14 Apr 2017
  22. 22.
    Scikit-Learn Machine Learning in Python. Accessed 21 Apr 2017

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Volodymyr Khoma
    • 1
    • 2
  • Mariusz Pelc
    • 1
  • Yuriy Khoma
    • 2
  • Dmytro Sabodashko
    • 2
  1. 1.Opole University of TechnologyOpolePoland
  2. 2.Lviv Polytechnic National UniversityLvivUkraine

Personalised recommendations