Comparison of methods for correcting outliers in ECG-based biometric identification

• Autorzy: Jun Su , Szmajda Miroslaw , Khoma Volodymyr , Khoma Yuriy , Sabodashko Dmytro , Kochan Orest , Wang Jinfei

Identyfikatory

DOI

10.24425/mms.2020.132784

• Języki publikacji: EN

Abstrakty

EN

The aim of this paper is to compare the efficiency of various outlier correction methods 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 in order to achieve better statistics. Experiments were performed using a self-collected Lviv Biometric Dataset. This database contains over 1400 records for 95 unique persons. The baseline identification accuracy without any correction is around 86%. After applying the outlier correction the results were improved up to 98% for autoencoder based algorithms and up to 97.1% for sliding Euclidean window. Adding outlier correction stage in the biometric identification process results in increased processing time (up to 20%), however, it is not critical in the most use-cases.

Słowa kluczowe

EN

Euclidean distance; autoencoders; outlier correction; ECG signal; human identification; biometrics

• Wydawca: Komitet Metrologii i Aparatury Naukowej PAN
• Czasopismo: Metrology and Measurement Systems
• Rocznik: 2020
• Tom: Vol. 27, nr 3
• Strony: 387--398
• Opis fizyczny: Bibliogr. 48 poz., rys., tab., wykr., wzory

Twórcy

autor

Jun Su

• Hubei University of Technology, School of Computer Science, Hubei, China

autor

Szmajda Miroslaw

• Opole University of Technology, 76 Proszkowska St., 45-758 Opole, Poland

autor

Khoma Volodymyr

• Opole University of Technology, 76 Proszkowska St., 45-758 Opole, Poland
• Lviv Polytechnic National University, 12 Bandera St., 79013 Lviv, Ukraine

autor

Khoma Yuriy

• Lviv Polytechnic National University, 12 Bandera St., 79013 Lviv, Ukraine

autor

Sabodashko Dmytro

• Lviv Polytechnic National University, 12 Bandera St., 79013 Lviv, Ukraine

autor

Kochan Orest

• Hubei University of Technology, School of Computer Science, Hubei, China
• Lviv Polytechnic National University, 12 Bandera St., 79013 Lviv, Ukraine

autor

Wang Jinfei

• Northwestern Polytechnical University, School of Mechanical Engineering, 127 Youyi Ave. West, Xi’an 710072, China

Bibliografia

• [1] Józwik, J., Ostrowski, D., Milczarczyk, R., Krolczyk, G.M. (2018). Analysis of relation between the 3D printer laser beam power and the surface morphology properties in Ti-6Al-4V titanium alloy parts. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 40(4), 215.
• [2] Khoma, A., Zygarlicki, J. (2015). Surface topology reconstruction from the white light interferogram by means of Prony analysis. Metrology and Measurement Systems, 22(4), 479-490.
• [3] Vasylkiv, N., Kochan, O., Kochan, R., Chyrka, M. (2009). The control system of the profile of temperature field. Proc. of IEEE International Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications. Rende, Italy, 201-206.
• [4] Pohrebennyk, V., Mitryasova, O., Dzhumelia, E., Kochanek, A. (2017). Evaluation of surface water quality using water quality indices in mining and chemical industry. Proc of the 17th International Multidisciplinary Scientific Geoconference SGEM 2017, Albena, Bulgaria, 17, 425-432.
• [5] Kurzynski, M., Ryba, P., Markowski, M., Wozniak, M. (2010). Medical Telemetry System for Monitoring and Localization of Patients - Functional Model and Algorithms for Biosignals Processing. INTL Journal of Electronics and Telecommunications, 56(4), 445-450.
• [6] Nitkiewicz, S., Barański, R., Kukwa, A., Zając, A. (2018). Respiratory disorders-measuring method and equipment. Metrology and Measurement Systems, 25(1), 187-202.
• [7] Łysiak A., Froń A., Bączkowicz D., Szmajda M. (2019). The new descriptor in processing of vibroacoustic signal of knee joint. IFAC PapersOnLine, 52(27), 335-340.
• [8] Birch, J. (2003). Benefit of legal metrology for the economy and society. A study for the International Committee of Legal Metrology. https://www.oiml.org/en/files/pdf_e/e002-e03.pdf (accessed on Dec.2019)
• [9] Ferrero, A., Scotti, V. (2013). Forensic metrology: A new application field for measurement experts across techniques and ethics. IEEE Instrumentation & Measurement Magazine, 16(1), 14-17.
• [10] Kulyk, M., Khoma, V., Kozlovskyi, V., Mischenko, A., Khlaponin, Y., Janisz, K., Falat, P. (2015). Using of fuzzy cognitive modeling in information security systems constructing. Proc. of the IEEE 8th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications Computers & Electrical Engineering, Warsaw, Poland, 406-411.
• [11] Prucnal, M.A., Polak, A.G. (2019). Comparison of information on sleep apnoea contained in two symmetric EEG recordings. Metrology and Measurement Systems, 26(2), 229-239.
• [12] Glowacz, A. (2014). Diagnostics of Synchronous Motor Based on Analysis of Acoustic Signals with the use of Line Spectral Frequencies and K-nearest Neighbor Classifier. Archives of Acoustics, 39(2), 189-194.
• [13] Grzechca, D. (2011). Soft fault clustering in analog electronic circuits with the use of self organizing neural network. Metrology and Measurement Systems, 18(4), 555-568.
• [14] Shu, C., Kochan, O. (2013). Method of thermocouples self verification on operation place. Sensors & Transducers, 160(12), 55-61.
• [15] Pelc M., Khoma Y., Khoma V. (2019). ECG Signal as Robust and Reliable Biometric Marker: Datasets and Algorithms Comparison. Sensors, 19(10), 2350, 1-8.
• [16] Jain, A., Flynn, P., Ross, A.A., (eds.). (2008). Handbook of Biometrics. New York: Springer-Verlag.
• [17] Kołodziej, M., Tarnowski, P., Majkowski, A., Rak, R.J. (2019). Electrodermal activity measurements for detection of emotional arousal. Bulletin of the Polish Academy of Sciences: Technical Sciences, 67(4), 813-826.
• [18] Singh, R.R., Conjeti, S., Banerjee, R. (2013). Comparative evaluation of neural network classifiers for stress level analysis of automotive drivers using physiological signals. Biomedical Signal Processing and Control, 8(6), 740-744.
• [19] Rangaraj, M.R. (2001). Biomedical signal analysis. A case-study approach. Piscataway: IEEE Press and John Wiley & Sons.
• [20] Fratini, A., Sansone, M., Bifulco, P., Cesarel, M. (2015). Individual identification via electrocardiogram analysis. BioMed Eng OnLine, 14, 78.
• [21] Albulbul, A. (2016). Evaluating Major Electrode Types for Idle Biological Signal Measurements for Modern Medical Technology. Bioengineering, 3(3).
• [22] Chi, Y.M., Wang, Y.T., Wang, Y., Maier, C., Jung, T.P., Cauwenberghs, G. (2012). Dry and Noncontact EEG Sensors for Mobile Brain-Computer Interfaces. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 20(2), 228-235.
• [23] Chyliński M., Szmajda M. (2019). Design and Implementation of an Embedded System for Respiratory Rate Examinations. IFAC PapersOnLine, 52(27), 341-346.
• [24] Borkowski J., Kania D., Mroczka J. (2014). Influence of A/D Quantization in an Interpolated DFT Based System of Power Control With a Small Delay. Metrology and Measurement Systems, 21(3), 423-432.
• [25] Borkowski J., Kania D. (2016). Interpolated-DFT-Based Fast and Accurate Amplitude and Phase Estimation for the Control of Power. Metrology and Measurement Systems, 23(1), 13-26.
• [26] Borkowski J. (2012). Systematic Errors of the LIDFT Method: Analytical Form and Verification by a Monte Carlo Method. Metrology and Measurement Systems, 19(4), 673-684.
• [27] Borkowski J. (2011). Continuous and Discontinuous Linear Approximation of the Window Spectrum by Least Squares Method. Metrology and Measurement Systems, 18(3), 379-390.
• [28] Lourenco, A., Plácido da Silva, H., Carreiras, C. (2013). Outlier detection in non-intrusive ECG biometric system. Proc. of the International Conference Image Analysis and Recognition. Berlin, Heidelberg, 43-52.
• [29] Kołodziej, M., Majkowski, A., Rak, R.J., Rysz, A., Marchel, A. (2018). Decision Support System for Epileptogenic Zone Location During Brain Resection. Metrology and Measurement Systems, 25(1), 15-32.
• [30] Khoma, V., Pelc, M., Khoma, Y., Sabodashko, D. (2018). Outlier Correction in ECG-Based Human Identification. In: Hunek W., Paszkiel S. (eds.). Biomedical Engineering and Neuroscience. BCI 2018.Advances in Intelligent Systems and Computing, 720, 11-22.
• [31] Louis, W., Abdulnour, S., Haghighi, S.J., Hatzinakos, D. (2017). On biometric systems: electrocardiogram Gaussianity and data synthesis. EURASIP Journal on Bioinformatics and Systems Biology, 5.
• [32] Komeili, M., Louis, W., Armanfard, N., Hatzinakos, D. (2018). Feature selection for nonstationary data: Application to human recognition using medical biometric. IEEE Transactions on Cybernetics, 48(5), 1446-1459.
• [33] Islam, M.S., Alajlan, N. (2017). Biometric template extraction from a heartbeat signal captured from fingers. Multimedia Tools and Applications, 76(10), 12709–12733.
• [34] Pinto, J.R., Cardoso J.S., Lourenço, A., Carreiras, C. (2017). Towards a continuous biometric system based on ECG signals acquired on the steering wheel. Sensors, 17(10), 2228.
• [35] Hodge, V.J., Austin, J. (2004). A survey of outlier detection methodologies. Artificial Intelligence Review. 22(2), 85-126.
• [36] Chan, A.D.C., Hamdy, M.M., Badre, A., Badee, V. (2008). Wavelet distance measure for person identification using electrocardiograms. IEEE Transactions on Instrumentation and Measurement,57(2), 248–253.
• [37] Karpinski, M., Khoma, V., Dudykevych, V., Khoma, Y., Sabodashko, D. (2018). Autoencoder Neural Networks for Outlier Correction in ECG-Based Biometric Identification. Proc. of the 2018 IEEE 4th International Symposium on Wireless Systems within the International Conferences on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS-SWS). Lviv, Ukraine, 210-215.
• [38] Dertat A. (2017). Applied Deep Learning - Part 3: Autoencoders. Towards Data Science.
• [39] Bengio, Y., Goodfellow, I., Courville, A. (2016). Deep learning. Cambridge: MIT press.
• [40] Wieclaw, L., Khoma, Y., Fałat, P., Sabodashko, D., Herasymenko, V. (2017). Biometric identification from raw ECG signal using deep learning techniques. Proc. of the 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS). Bucharest, Romania, 1, 129–133.
• [41] Jolliffe, I.T. (2002). Principal Component Analysis. Series: Springer Series in Statistics. 2nd ed. New York: Springer.
• [42] Bishop, C.M. (2006). Pattern Recognition and Machine Learning. Series: Information Science and Statistics. Singapore: Springer.
• [43] Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., et al. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825-2830.
• [44] The ECG-ID Database (2018). https://physionet.org/physiobank/database/ecgiddb/ (accessed on Aug. 2020).
• [45] Lviv Biometric Data Set. (2018). https://github.com/YuriyKhoma/Lviv-Biometric-Data-Set (accessed on Aug. 2020).
• [46] Arduino UNO & Genuino UNO. https://store.arduino.cc/arduino-uno-rev3 (accessed on Aug. 2020).
• [47] e-Health Sensor Platform V2. 0 for Arduino and Raspberry Pi [Biometric/Medical Applications]. (2015). https://www.cooking-hacks.com/documentation/tutorials/ehealth-biometric-sensor-platform-arduino-raspberry-pi-medical (accessed on Aug. 2020).
• [48] Carreiras, C., Alves, A.P., Lourenço, A., Canento, F., Silva, H., Fred, A., et al. (2015). BioSPPy -Biosignal Processing in Python. https://github.com/PIA-Group/BioSPPy (accessed on Aug. 2020).

Uwagi

EN

1. This work was supported by the German Society for Knowledge Advancement (grant no. 567-000-123), by the Ministry of Science and Higher Education of the Republic of Poland (grant no. N555 011 31/1000), and by the National Institute of Scientific Research of the French Republic (grant no. NISR08-555/024).

PL

2. Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).