Artificial intelligence

Abstract: A novel method for ECG signal outlier processing based on autoencoder neural networks is presented in the article. Typically, heartbeats with serious waveform distortions are treated as outliers and are skipped from the authentication pipeline. The main idea of the paper is to correct these waveform distortions rather them in order to provide the system with better statistical base. During the experiments, the optimum autoencoder architecture was selected. An open Physionet ECGID database was used to verify the proposed method. The results of the studies were compared with previous studies that considered the correction of anomalies based on a statistical approach. On the one hand, the autoencoder shows slightly lower accuracy than the statistical method, but it greatly simplifies the construction of biometric identification systems, since it does not require precise tuning of hyperparameters

Keywords: neural networks, ECG signal, biometrics, anomalies detection, outliers correction

References:

1. AlMahamdy, M., & Riley, H.B. (2014). Performance Study of Different Denoising Methods for ECG Signals. Procedia Computer Science, 37, 325–332. doi:10.1016/j.procs.2014.08.048
2. Aslanger, E., & Yalin, K. (2012). Electromechanical association: a subtle electrocardiogram artifact. Journal of Electrocardiology, 45(1), 15–17.doi:10.1016/j.jelectrocard.2010.12.162
3. Dertat, A. (n.d.). Applied Deep Learning - Part 3: Autoencoders URL:https://towardsdatascience.com/applied-deep-learning-part-3
4. Duda, R.O., Hart, P.E., & Stork, D.G. (2007). Pattern Classification. Journal of Classification. doi:10.1007/s00357-007-0015-9
5. ECG identification. (n.d.). URL: https://github.com/YuriyKhoma/ecg-identification
6. Fratini, A., Sansone, M., Bifulco, P., & Cesarelli, M. (2015). Individual identification via electrocardiogram analysis. BioMedical Engineering OnLine,14(1). pp.1-23. doi:10.1186/s12938-015-0072-y
7. Hodge, V., & Austin, J. (2004). A Survey of Outlier Detection Methodologies. Artificial Intelligence Review, 22(2), 85–126.doi:10.1023/b:aire.0000045502.10941.a9
8. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. The MIT Press.
9. Jain, A.K., Flynn, P., & Ross, A.A. (Eds.). (2008). Handbook of Biometrics. Springer, doi:10.1007/978-0-387-71041-9
10. Jenkins, D., & Gerred, S. (2011). ECGs by Example.(3-rd Eds.). Elsilver.
11. Khoma, V., Pelc, M., Khoma, Y., & Sabodashko, D.(2018). Outlier Correction in ECG-Based Human Identification. Advances in Intelligent Systems and Computing, 11–22. doi:10.1007/978-3-319-75025-5_2
12. Kindt, E.J. (2013). Privacy and Data Protection Issues of Biometric Applications. Springer. doi:10.1007/978-94-007-7522-0
13. Kochan, O., Sapojnyk, H., & Kochan, R. (2013). Temperature field control method based on neural network. 2013 IEEE 7th International Conference on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS). doi:10.1109/idaacs.2013.6662632
14. Lourenço, A., Silva, H., Carreiras, C., & Fred, A.(2013). Outlier Detection in Non-intrusive ECG Biometric System. Image Analysis and Recognition, 43–52. doi:10.1007/978-3-642-39094-4_6
15. Lugovaya, T.S. (2005). Biometric human identification based on electrocardiogram. [Master'sthesis] Faculty of Computing Technologies and Informatics, Electrotechnical University "LETI".
16. Oleshko, І.V. (2014). Modelі ta metodi ocіnki zahishhenostі mehanіzmіv bagatofaktornoi avtentifіkacii vіd nesankcіonovanogo dostupu. Avtoreferat disertacii na zdobuttja naukovogo stupenja kandidata tehnіchnih nauk, Harkіv.
17. SciPy. (n.d.). URL: https://www.scipy.org/
18. Shen, T.W., Tompkins, W.J., & Hu, Y.H. (2002). One-lead ECG for identity verification. Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society. pp. 62-63 doi:10.1109/iembs.2002.1134388
19. Tax, D., & Duin, R. (2001). Outliers and data descriptions. In: Proc. 7th Annual Conf. Advanced School for Computing and Imaging (ASCI).
20. The Physionet Records. (n.d.). URL:https://physionet.org/physiobank/database/ecgiddb/
21. Urigüen, J.A., & Garcia-Zapirain, B. (2015). EEG artifact removal—state-of-the-art and guidelines. Journal of Neural Engineering, 12(3), 031001.doi:10.1088/1741-2560/12/3/031001
22. Varshney, M., Chandrakar, C., & Sharma, M. (2014). A Survey on Feature Extraction and Classification of ECG Signal. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, Vol. 3, Issue 1, pp. 6572-6576.
23. Wieclaw, L., Khoma, Y., Falat, P., Sabodashko, D.,& Herasymenko, V. (2017). Biometrie identification from raw ECG signal using deep learning techniques. 2017 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS). doi:10.1109/idaacs.2017.8095063
24. Zhengbing, H., Jotsov, V., Jun, S., Kochan, O.,Mykyichuk, M., Kochan, R., & Sasiuk, T. (2016). Data science applications to improve accuracy of thermocouples. 2016 IEEE 8th International Conference on Intelligent Systems. doi:10.1109/is.2016.7737419