Advertisement

ECG-Based Personal Identification Using Empirical Mode Decomposition and Hilbert Transform

  • R. Boostani
  • M. Sabeti
  • S. Omranian
  • S. Kouchaki
Research Paper
  • 35 Downloads

Abstract

It is evident that biological signals of each subject (e.g., electrocardiogram signal) carry his/her unique signature; consequently, several attempts have been made to extract subject-dependent features from these signals with application to human verification. Despite numerous efforts to characterize electrocardiogram (ECG) signals and provide promising results for low population of subjects, the performance of state-of-the-art methods mostly fail in the presence of noise or arrhythmia. This paper presented an efficient and fast-to-compute ECG feature by applying empirical mode decomposition (EMD) to ECG signals, and then, instantaneous frequency, instantaneous phase, amplitude, and entropy features were extracted from the analytical form of the last EMD component. Finally, the k-nearest neighbor (kNN) classifier was utilized to classify the individuals’ features. The proposed method was compared to the conventional features such as fiducial points, correlation, wavelet coefficients, and principal component analysis (PCA). These methods were all applied to ECG signals of 34 healthy subjects derived from the Physikalisch-Technische Bundesanstalt (PTB) database. The results implied the effectiveness of the proposed method, providing 95% verification accuracy, which was not the best among the competitors but provided much lower dimensional feature space compared to the top-rank counterparts.

Keywords

ECG Empirical mode decomposition (EMD) Hilbert transform Verification 

References

  1. Abbaspour H, Razavi SM, Mehrshad N (2015) Electrocardiogram based identification using a new effective intelligent selection of fused features. J Med Signals Sens 5(1):30–39Google Scholar
  2. Akhbari M, Shamsollahi MB, Jutten C (2013) ECG Fiducial points extraction by extended Kalman filtering. In: 36th International conference on telecommunications and signal processing (TSP), Rome, ItalyGoogle Scholar
  3. Biel L, Pettersson O, Lennart P, Peter W (2001) ECG analysis: a new approach in human identification. IEEE Trans Instrum Meas 50(3):808–812CrossRefGoogle Scholar
  4. Bilato R, Maj O, Brambilla M (2014) An algorithm for fast Hilbert transform of real functions. Adv Comput Math 40(5–6):1159–1168MathSciNetCrossRefzbMATHGoogle Scholar
  5. Boashash B (1992) Estimating and interpreting the instantaneous frequency of a signal. II. Algorithms and applications. Proc IEEE 80(4):540–568CrossRefGoogle Scholar
  6. Boumbarov O, Velchev Y, Sokolov S (2008) Personal biometric identification based on ECG features. Inf Technol Control 3(4):2–9Google Scholar
  7. Burrus S (1998) Introduction to wavelet and wavelet transforms. Prentice Hall, Upper Saddle River, NJGoogle Scholar
  8. Castells F, Laguna P, Sörnmo L, Bollmann A, Roig JM (2007) Principal component analysis in ECG signal processing. EURASIP J Adv Signal Process 2007:074580.  https://doi.org/10.1155/2007/74580 CrossRefzbMATHGoogle Scholar
  9. Cheang Loong JL, Subari KS, Besar R, Abdullah MK (2010) A new approach to ECG biometric systems: a comparative study between LPC and WPD systems. World Acad Sci Eng Technol 68:759–764Google Scholar
  10. Daubechies I (1992) Ten lectures on wavelets. Society for Industrial and Applied Mathematics (SIAM), Philadelphia, PACrossRefzbMATHGoogle Scholar
  11. Fatemi M, Sameni R (2017) An online subspace denoising algorithm for maternal ECG removal from fetal ECG signals. Iran J Sci Technol Trans Electr Eng 41(1):65–79CrossRefGoogle Scholar
  12. Fix E, Hodges JL Jr (1989) Discriminatory analysis, non-parametric discrimination, and consistency properties. Int Stat Rev 57(3):238–247CrossRefzbMATHGoogle Scholar
  13. Fonseca P, Aarts RM, Foussier J, Long X (2014) A novel low-complexity post-processing algorithm for precise QRS localization. SpringerPlus 3:376–389CrossRefGoogle Scholar
  14. Fratini A, Sansone M, Bifulco P, Cesarelli M (2015) Individual identification via electrocardiogram analysis. Biomed Eng Online 14:78CrossRefGoogle Scholar
  15. Ghofrani N, Boostani R (2010) Reliable features for an ECG-based biometric system. In: 17th Iranian conference of biomedical engineering (ICBME), Isfahan, IranGoogle Scholar
  16. Hoekema R, Uijen GJ, Oosterom AV (2001) Geometrical aspect of the inter-individual variability of multi-lead ECG recordings. IEEE Trans Biomed Eng 48:551–559CrossRefGoogle Scholar
  17. Huang NE, Shen Z, Long SR, Wu ML, Shih HH, Zheng Q, Yen NC, Tung CC, Liu HH (1998) The empirical mode decomposition and Hilbert spectrum for nonlinear and nonstationary time series analysis. Proc R Soc Lond A 454:903–995MathSciNetCrossRefzbMATHGoogle Scholar
  18. Huang NE, Wu MC, Long SR, Shen SSP, Qu W, Gloersen P, Fan KL (2003) A confidence limit for the empirical mode decomposition and Hilbert spectral analysis. Proc R Soc Lond A 459:2317–2345MathSciNetCrossRefzbMATHGoogle Scholar
  19. Jain AK, Ross A, Prabhakar S (2004) An introduction to biometric recognition. IEEE Trans Circuits Syst Video Technol 14(1):4–20CrossRefGoogle Scholar
  20. Kang W, Byun K, Kang HG (2015) Detection of fiducial points in ECG waves using iteration based adaptive thresholds. In: 37th annual international conference of the IEEE engineering in medicine and biology society, Milan, ItalyGoogle Scholar
  21. Khelil B, Kachouri A, Messaoud MB, Ghariani H (2007) P wave analysis in ECG signals using correlation for arrhythmias detection. In: 4th International multi-conference on systems, signals & devices, vol III, Hammamet, TunisiaGoogle Scholar
  22. Kligfield P (2002) The centennial of the Einthoven electrocardiogram. J Electrocardiol 35:123–129CrossRefGoogle Scholar
  23. Kouchaki S, Dehghani A, Omranian S, Boostani R (2012) ECG-based personal identification using empirical mode decomposition and Hilbert transform. In: Artificial intelligence and signal processing (AISP), Shiraz, Iran, pp 569–573Google Scholar
  24. Oeff M, Koch H, Bousseljot R, Kreiseler D (2012) The PTB diagnostic ECG database. National Metrology Institute of Germany. http://www.physionet.org/physiobank/database/ptbdb/. 24 Feb 2012
  25. Pan J, Tompkins WJ (1985) A real-time QRS detection algorithm. IEEE Trans Biomed Eng 3:230–236CrossRefGoogle Scholar
  26. Plesnik E, Malgina O, Tasic JF, Zajc M (2011) Detection of the electrocardiogram fiducial points in the phase space using area calculation. Elektrotehniski Vestnik 78(5):257–262Google Scholar
  27. Rahbi E, Lachiri Z (2013) Biometric personal identification system using the ECG signal. Comput Cardiol 40:507–510Google Scholar
  28. Roweis S (1998) EM algorithms for PCA and SPCA. Adv Neural Inf Process Syst 10:626–632Google Scholar
  29. Rujirakul K, So-In C, Arnonkijpanich B (2014) PEM-PCA: a parallel expectation-maximization PCA face recognition architecture. Sci World J 2014:468176.  https://doi.org/10.1155/2014/468176 CrossRefGoogle Scholar
  30. Sabeti M, Boostani R (2017) Separation P300 event-related potential using time varying time-lag blind source separation algorithm. Comput Methods Progr Biomed 145:95–102CrossRefGoogle Scholar
  31. Ting CM. Salleh SH (2010) ECG based personal identification using extended Kalman filter. In: IEEE international conference on information science, signal processing and their applications. pp 774–777Google Scholar
  32. Shen TW, Tompkins WJ, Hu YH (2002) On lead ECG for identity verification. In: IEEE joint conference in medicine and biology society and the biomedical engineering society. pp 62–63Google Scholar
  33. Souza Neto EP, Custaud MA, Cejka CJ, Abry P, Frutoso J, Gharib C, Flandrin P (2002) Assessment of cardiovascular autonomic control by the Empirical Mode Decomposition. In: 4th international workshop on biosignal interpretation, Como (I), pp 123–126Google Scholar
  34. Stoica P, Moses RL (1997) Introduction to spectral analysis. Prentice Hall, USAzbMATHGoogle Scholar
  35. Tadejko P, Waldemar Rakowski W (2007) Mathematical morphology based ECG feature extraction for the purpose of heartbeat classification. In: 6th International conference on computer information systems and industrial management applications, Minneapolis, USAGoogle Scholar
  36. Taouli SA, Bereksi-Reguig F (2013) ECG signal denoising by morphological top-hat transform. Glob J Comput Sci Technol Softw Data Eng 13(5):1–10Google Scholar
  37. Vos K (2013) A fast implementation of Burg’s method. Creat Commons Attrib 1–3Google Scholar
  38. Wang Y, Plataniotis KN, Hatzinakos D (2006) Integrating analytic and appearance attributes for human identification from ECG signals. In: Biometrics symposium: special session on research at the biometric consortium conference, MarylandGoogle Scholar
  39. Wang Y, Agrafioti F, Hatzinakos D, Plataniotis KN (2008) Analysis of human electrocardiogram for biometric recognition. EURASIP J Adv Signal Process 1:1–6CrossRefzbMATHGoogle Scholar
  40. Wang YH, Yeh CH, Young HW, Hu K, Lo MT (2014) On the computational complexity of the empirical mode decomposition algorithm. Phys A 400:159–167CrossRefGoogle Scholar
  41. Yazdani S, Vesin JM (2016) Extraction of QRS fiducial points from the ECG using adaptive mathematical morphology. Digit Signal Process 56:100–109MathSciNetCrossRefGoogle Scholar

Copyright information

© Shiraz University 2018

Authors and Affiliations

  • R. Boostani
    • 1
  • M. Sabeti
    • 2
  • S. Omranian
    • 1
  • S. Kouchaki
    • 1
  1. 1.CSE and IT Department, Faculty of Electrical and Computer EngineeringShiraz UniversityShirazIran
  2. 2.Computer Engineering Department, School of Engineering, Shiraz BranchIslamic Azad UniversityShirazIran

Personalised recommendations