Performance Analysis of ECG Signal by Wavelet Transform, Independent Component Analysis and Fast Fourier Transform

Authors(1) :-Mayank Kumar Gautam

ECG plays a vital role in the analysis of various heart diseases as the shape of the ECG waveform consist of vital information about heart conditions such as its electrical conduction or muscle activity. Inspite of the conventional method the extraction of ECG features is of major significance and benefit for the diagnosis of numerous harmful or even critical cardiac diseases. The feature extraction plays a vital role in diagnosis of the various cardiac diseases. Each cycle of an ECG signal contains of the P-QRS-T waves. This scheme of feature extraction describes and provides the amplitudes and intervals in the ECG signal for further investigation. The amplitudes and intervals value of P-QRS-T segment shows the operation of heart. Recently, various techniques have been evolved for analysis of the ECG signal. This paper discusses three most widely used methods used to extract the different features of Electrocardiograph (ECG) signals namely Wavelet Transform (WT), Fast Fourier Transform (FFT), Independent Component Analysis (ICA). The study conveys the information that the Fast Fourier Transform method gives better performance in frequency domain for the ECG feature extraction. Accuracy of Wavelet Transform is 92.20%, of the Fast Fourier Transform is 92.47%, and of the Independent Component Analysis is 90.13%. It has been observed that FFT shows better performance regarding the ECG signal analysis. Moreover, provides efficient estimation of the PSD from noise corrupted signals. But the limitation of this method is the leakage decreases the ability of FFT to resolve two frequencies of close space. But by the use of a window function will reduce this leakage.

Authors and Affiliations

Mayank Kumar Gautam
Electrical Engineering Department, R.E.C. Ambedkar Nagar, Uttar Pradesh, India

ECG feature extraction, Wavelet Transform, ICA, FFT.

  1. D. Clifford, et al., Advanced methods and tools for ECG data analysis: Artech House, 2006.
  2. gen Zhang, et al., "Pattern recognition of cardiac arrhythmias using scalar autoregressive modeling," 2004, pp. 5545-5548 Vol. 6.
  3. Li and P. Li, "A Switching Method Based on FD and WTMM for ECG Signal Real-Time Feature Extraction," 2009, pp. 828-830.
  4. Mallat, "Zero-crossings of a wavelet transform, "Information Theory, IEEE Transactions on, vol. 37, pp.1019-1033, 1991.
  5. Ubeyli, et al., "Eigenvector methods for analysis of human PPG, ECG and EEG signals ," 2007, pp. 3304-3307.
  6. D. Übeyli and _. Güler, "Improving medical diagnostic accuracy of ultrasound Doppler signals by combining neural network models," Computers in Biology and Medicine, vol. 35, pp. 533-554, 2005.
  7. Maniewski, et al., "Time-frequency methods for high resolution ECG analysis," 1993, pp. 1266-1267 vol. 3.
  8. B. Tayel and M. E. El-Bouridy, "ECG images classification using artificial neural network based on several feature extraction methods," 2008, pp. 113-115.
  9. Challis and R. Kitney, "Biomedical signal processing (in four parts)," Medical and Biological Engineering and Computing, vol. 28, pp. 509-524, 1990.
  10. Challis and R. Kitney, "Biomedical signal processing (in four parts)," Medical and Biological Engineering and Computing, vol. 29, pp. 1-17, 1991.
  11. M. Kay and S. L. Marple Jr, "Spectrum analysis—a modern perspective," Proceedings of the IEEE, vol. 69, pp. 1380-1419, 1981.
  12. Noponen, et al., "Electrocardiogram Quality Classification based on Robust Best Subsets Linear Prediction Error."
  13. Hyvarinen, "Fast and robust fixed-point algorithms for independent component analysis," Neural Networks, IEEE Transactions on, vol. 10, pp. 626-634, 1999.
  14. Wang, et al., "Blind EGG separation using ICA neural networks," 1997, pp. 1351-1354 vol. 3.
  15. De Lathauwer, et al., "Fetal electrocardiogram extraction by blind source subspace separation, "Biomedical Engineering, IEEE Transactions on, vol. 47, pp. 567-572, 2000.
  16. Vigário, et al., "Independent component approach to the analysis of EEG and MEG recordings," Biomedical Engineering, IEEE Transactions on, vol. 47, pp. 589-593, 2000.
  17. Owis, et al., "Characterization of electrocardiogram signals based on blind source separation," Medical and Biological Engineering and Computing, vol. 40, pp. 557- 564, 2002.
  18. G. Herrero, et al., "Feature extraction for heartbeat classification using independent component analysis and matching pursuits," 2005, pp. iv/725-iv/728 Vol. 4.
  19. Hyvärinen, et al., Independent component analysis vol.26: Wiley-interscience, 2001.
  20. J. Bell and T. J. Sejnowski, "An information maximization approach to blind separation and blind deconvolution," Neural computation, vol. 7, pp. 1129-1159, 1995.
  21. F. Cardoso and B. H. Laheld, "Equivariant adaptive source separation," Signal Processing, IEEE Transactions on, vol.44, pp. 3017-3030, 1996.
  22. Hyvärinen and E. Oja, "A fast fixed-point algorithm for independent component analysis," Neural computation, vol. 9, pp. 1483-1492, 1997.
  23. N. Yu and K. T. Chou, "Selection of significant independent components for ECG beat classification," Expert Systems with Applications, vol. 36, pp. 2088-2096, 2009.
  24. F. GE, et al., "Study of Feature Extraction Based on Autoregressive Modeling in EGG Automatic Diagnosis," Acta Automática Sinica, vol. 33, pp. 462-466, 2007.
  25. R. H. Sandercock, et al., "The reliability of short-term measurements of heart rate variability," International journal of cardiology, vol. 103, pp. 238-247, 2005.
  26. Chemla, et al., "Comparison of fast Fourier transform and autoregressive spectral analysis for the study of heart rate variability in diabetic patients," International journal of cardiology, vol. 104, pp. 307-313, 2005.
  27. V. Pitzalis, et al., "Short-and long-term reproducibility of time and frequency domain heart rate variability measurements in normal subjects," Cardiovascular research, vol. 32, p. 226, 1996
  28. F. Cardoso and A. Souloumiac, "Blind beam forming for non-Gaussian signals," 1993, pp. 362-370.

Publication Details

Published in : Volume 1 | Issue 2 | September-October 2016
Date of Publication : 2016-10-30
License:  This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 95-98
Manuscript Number : CSEIT161214
Publisher : Technoscience Academy

ISSN : 2456-3307

Cite This Article :

Mayank Kumar Gautam, "Performance Analysis of ECG Signal by Wavelet Transform, Independent Component Analysis and Fast Fourier Transform ", International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT), ISSN : 2456-3307, Volume 1, Issue 2, pp.95-98, September-October-2016.
Journal URL :

Article Preview