Neural Computing & Applications

, Volume 15, Issue 2, pp 105–116 | Cite as

Application of independent component analysis in removing artefacts from the electrocardiogram

  • Taigang He
  • Gari Clifford
  • Lionel TarassenkoEmail author
Original Article


Routinely recorded electrocardiograms (ECGs) are often corrupted by different types of artefacts and many efforts have been made to enhance their quality by reducing the noise or artefacts. This paper addresses the problem of removing noise and artefacts from ECGs using independent component analysis (ICA). An ICA algorithm is tested on three-channel ECG recordings taken from human subjects, mostly in the coronary care unit. Results are presented that show that ICA can detect and remove a variety of noise and artefact sources in these ECGs. One difficulty with the application of ICA is the determination of the order of the independent components. A new technique based on simple statistical parameters is proposed to solve this problem in this application. The developed technique is successfully applied to the ECG data and offers potential for online processing of ECG using ICA.


Independent component analysis Artefacts Noise removal ECG Permutation 



Dr. Taigang He was supported by an EPSRC post-doctoral Research Assistantship (GR/M05614) and Gari Clifford was funded by Oxford BioSignals Ltd.


  1. 1.
    Paul JS, Reddy MR, Kumar VJ (2000) A transform domain SVD filter for suppression of muscle noise artefacts in exercise ECG’s. IEEE Trans Biomed Eng 3:654–663CrossRefGoogle Scholar
  2. 2.
    Talmon TL, Kors JA, Von JH (1986) Adaptive Gaussian filtering in routine ECG/VCG analysis. IEEE Trans Acoust Speech Signal Process ASSP-34:527–534CrossRefGoogle Scholar
  3. 3.
    Thakor NV, Zhu VS (1991) Application of adaptive filtering to ECG analysis: noise cancellation and arrhythmia detection. IEEE Trans Biomed Eng 38:785–793CrossRefGoogle Scholar
  4. 4.
    Bensadoun Y, Novakov E, Raoof K (1995) Multidimensional adaptive method for canceling EMG signals from the ECG signal. In: Roberge FA, Kearney RE (eds) 17th IEEE Ann Int Conf on Engng in Med and Biol Soc. Montreal, pp 299–300Google Scholar
  5. 5.
    Barros AK, Ohnishi N (1997) MSE behavior of biomedical event-related filters. IEEE Trans Biomed Eng 44:848–855CrossRefGoogle Scholar
  6. 6.
    Laguna P, Janè R, Meste O et’al (1992) Adaptive filter for event-related bioelectric signals using an impulse correlated reference input: comparison with signal averaging techniques. IEEE Trans Biomed Eng 39:1032–1043CrossRefGoogle Scholar
  7. 7.
    Vaz C, Kong X, Thakor NV (1994) An adaptive estimation of periodic signals using a Fourier linear combiner. IEEE Trans Signal Process 42:1–10CrossRefGoogle Scholar
  8. 8.
    Kanjilal PP, Palit S (1995) On multiple pattern extraction using singular value decomposition. IEEE Trans Signal Process 43:1536–1540CrossRefGoogle Scholar
  9. 9.
    Wisbeck JO, Garcia RO (1998) Application of neural networks to separate interferences and ECG signals. In: Proceedings of IEEE international Caracas conference on devices, circuits and systems, pp 291–294Google Scholar
  10. 10.
    Speirs CA, Soraghan JJ, Stewart RW et’al (1994) Ventricular late potential detection from bispectral analysis of ST-segments. In: Proceedings of EUSIPCO–94, September 1994, pp 1129–1132Google Scholar
  11. 11.
    Jung T-P, Makeig S, Lee T-W et’al (2000) The 2nd international workshop on independent component analysis and signal separation, pp 633–644Google Scholar
  12. 12.
    Cardoso JF (1998) Multidimensional independent component analysis. In: Proceedings of ICASSP ’98, Seattle, pp 1941–1944Google Scholar
  13. 13.
    Wisbeck JO, Barros AK, Ojeda R (1998) Application of ICA in the separation of breathing artefacts in ECG signals. International conference on neural information processing, (ICONIP’98), Kyushu, JapanGoogle Scholar
  14. 14.
    Barros AK, Mansour A, Ohnishi N (1998) Removing artefacts from electrocardiographic signals using independent component analysis. Neurocomputing 22:173–186zbMATHCrossRefGoogle Scholar
  15. 15.
    Tong S, Bezerianos A, Paul J et’al (2001) Removal of ECG interference from the EEG recordings in small animals using independent component analysis. J Neurosci Meth 108:11–17CrossRefGoogle Scholar
  16. 16.
    Jung TP, Makeig S, Humphries C et’al (2000) Removing electroencephalographic artefacts by blind source separation. Psychophysiology 37:163–178CrossRefGoogle Scholar
  17. 17.
    Hyvarinen A (1999) Survey on independent component analysis. Neural Comput Survey 2:94–128Google Scholar
  18. 18.
    Cardoso JF (1999) High-order contrasts for independent component analysis. Neural Comput 11:157–192CrossRefGoogle Scholar
  19. 19.
    Huber PJ (1985) Projection pursuit. Ann Stat 13(2):435–475zbMATHCrossRefMathSciNetGoogle Scholar
  20. 20.
    Tarassenko L, Townsend N, Clifford G et’al (2001) Medical signal processing using the software monitor. In: Proceedings of IEE/DERA workshop on intelligent signal processing, Birmingham, February, pp 3/1–3/4Google Scholar
  21. 21.
    Anderson ST, Downs WG, Lander P et’al (1995) Advanced electrocardiography. Spacelabs medical biophysical measurement, SpaceLabs Medical Inc., WashingtonGoogle Scholar
  22. 22.
    ANSI/AAMI EC38–1994, Ambulatory electrocardiographs. American National Standard, August 1994Google Scholar
  23. 23.
    McClellan P (1979) Algorithm 5.1. Programs for digital signal processing. IEEE Press, Wiley, New YorkGoogle Scholar
  24. 24.
    Clifford G (1999) The software monitor project—novelty detection and classification in electrocardiograms. DPhil transfer report, Department of Engineering Science, University of OxfordGoogle Scholar
  25. 25.
    Houghton A, Gray D (1997) Making sense of the ECG. Oxford University Press, OxfordGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2005

Authors and Affiliations

  1. 1.Signal Processing and Neural Networks Research Group, Department of Engineering ScienceUniversity of OxfordOxfordUK

Personalised recommendations