Medical & Biological Engineering & Computing

, Volume 46, Issue 3, pp 251–261 | Cite as

Independent component analysis applied to the removal of motion artifacts from electrocardiographic signals

  • M. MilanesiEmail author
  • N. Martini
  • N. Vanello
  • V. Positano
  • M. F. Santarelli
  • L. Landini
Original Article


Electrocardiographic (ECG) signals are affected by several kinds of artifacts that may hide vital signs of interest. In this study we apply independent component analysis (ICA) to isolate motion artifacts. Standard or instantaneous ICA, which is currently the most addressed ICA model within the context of artifact removal, is compared to two other ICA techniques. The first technique is a frequency domain approach to convolutive mixture separation. The second is based on temporally constrained ICA, which enables the estimation of only one component close to a particular reference signal. Performance indexes evaluate ECG complex enhancement and relevant heart rate errors. Our results show that both convolutive and constrained ICA implementations perform better than standard ICA, thus opening up a new field of application for these two methods. Moreover, statistical analysis reveals that constrained ICA and convolutive ICA do not significantly differ concerning heart rate estimation, even though the latter overcomes the former in ECG morphology recovery.


Independent component analysis Frequency domain Temporal constraint Motion artifacts Electrocardiographic signals 


  1. 1.
    Anemüller J, Sejnowski TJ, Makeig S (2003) Complex independent component analysis of frequency-domain electroencephalographic data. Neural Netw 16(9):1311–1323CrossRefGoogle Scholar
  2. 2.
    Anemüller J, Duann JR, Sejnowski TJ, Makeig S (2006) Spatio-temporal dynamics in fMRI recordings revealed with complex independent component analysis. Neurocomputing 69:1502–1512CrossRefGoogle Scholar
  3. 3.
    Barros AK, Mansour A, Ohnishi N (1998) Removing artifacts from electrocardiographic signals using independent components analysis. Neurocomputing 22:173–186zbMATHCrossRefGoogle Scholar
  4. 4.
    Bronzino JD (2000) The biomedical engineering handbook, 2nd edn. CRC, LLC Boca RatonGoogle Scholar
  5. 5.
    Burbank DP, Webster JG (1978) Reducing skin potential motion artifacts by skin abrasion. Med Biol Eng Comput 16:31–38CrossRefGoogle Scholar
  6. 6.
    He T, Clifford G, Tarassenko L (2006) Application of independent component analysis in removing artefacts from the electrocardiogram. Neural Comput Appl 5:105–116Google Scholar
  7. 7.
    Hyvärinen A, Oja E (1997) A fast fixed-point algorithm for independent component analysis. Neural Comput 9(7):1483–1492CrossRefGoogle Scholar
  8. 8.
    Hyvärinen A, Karhunen J, Oja E (2001) Independent component analysis. Wiley, LondonGoogle Scholar
  9. 9.
    James CJ, Gibson OJ (2003) Temporally constrained ICA: an application to artifact rejection in electromagnetic brain signal analysis. IEEE Trans Biomed Eng 50(9):1108–1116CrossRefGoogle Scholar
  10. 10.
    James,CJ, Hesse CW (2005) Independent component analysis for biomedical signals. Physiol Meas 26:R15–R39CrossRefGoogle Scholar
  11. 11.
    Jung TP, Makeig S, Humphries C, Lee TW, McKeown MJ, Iragui V, Sejnowski TJ (2000) Removing electroencephalographic artifacts by blind source separation. Psychophysiology 37(2):163–178CrossRefGoogle Scholar
  12. 12.
    Lee J, Park KL, Lee KJ (2005) Temporally constrained ICA-based foetal ecg separation. Electron Lett 41:1158–1160CrossRefGoogle Scholar
  13. 13.
    Lu W, Rajapakse JC (2001) ICA with reference. In: Proceedings of 3rd international conference independent component analysis and blind signal separation: ICA 2001, pp 120–125Google Scholar
  14. 14.
    Makeig S, Bell AJ, Jung TP, Sejnowski TJ (1996) Independent component analysis of electroencephalographic data. Adv Neural Inf Process Syst 8:145–151Google Scholar
  15. 15.
    Mckeown M, Makeig S, Brown G, Jung T, Kindermann S, Bell A, Sejnowski, TJ (1998) Analysis of fMRI data by blind separation into independent spatial components. Human Brain Map 6:160–188CrossRefGoogle Scholar
  16. 16.
    Milanesi M, Vanello N, Positano V, Santarelli M, Paradiso R, De Rossi D, Landini L (2005) Frequency domain approach to blind source separation in ecg monitoring by wearable system. Proc Comp Cardiol IEEE 32:767–770Google Scholar
  17. 17.
    Milanesi M, Vanello N, Positano V, Santarelli MF, Landini L. (2005) Separation and identification of biomedical signals based on frequency domain independent component analysis. WSEAS Trans Syst 10:1752–1761Google Scholar
  18. 18.
    Milanesi M, Martini N, Vanello N, Positano V, Santarelli MF, Paradiso R, De Rossi D, Landini L (2006) Multichannel techniques for motion artifacts removal from electrocardiographic signals. In: Proceedings of the 28th annual intern conference of the IEEE Eng Med and Biol Soc (EMBS), New York, USA, pp 3391–3394Google Scholar
  19. 19.
    Murata N, Ikeda S, Ziehe A (2001) An approach to blind source separation based on temporal structure of speech signals. Neurocomputing 41:1–24zbMATHCrossRefGoogle Scholar
  20. 20.
    Opie LH (2004) Heart physiology. Lippincott Williams & Wilkins, PhiladelphiaGoogle Scholar
  21. 21.
    Pan J, Tompkins WJ (1985) A real-time QRS detection algorithm. IEEE Trans Biomed Eng 32(3):230–236CrossRefGoogle Scholar
  22. 22.
    Paradiso R, Loriga G, Taccini N (2005) A wearable health care system based on knitted integrated sensors. IEEE Trans Inf Technol Biomed 9(3):337–344CrossRefGoogle Scholar
  23. 23.
    Peng C, Qian X, Ye D (2007) Electrogastrogram extraction using independent component analysis with references. Neural Comp Appl 16:581–587CrossRefGoogle Scholar
  24. 24.
    Raya MAD, Sison LG (2002) Adaptive noise cancelling of motion artifact in stress ECG signals using accelerometer. In: Proceedings of 2nd joint EMBS/BMES Conference, Huston, pp 1756–1757Google Scholar
  25. 25.
    Rompelman O, Ros HH (1986) Coherent averaging technique: a tutorial review. Part 1: noise reduction and the equivalent filter. J Biomed Eng 8(1):30–35CrossRefGoogle Scholar
  26. 26.
    Smaragdis P (1998) Blind separation of convolved mixtures in the frequency domain. Neurocomputing 22:21–34zbMATHCrossRefGoogle Scholar
  27. 27.
    Tam HW, Webster JG (1977) Minimizing electrode motion artifact by skin abrasion. IEEE Trans Biomed Eng 24(2):134–139CrossRefGoogle Scholar
  28. 28.
    Vayá C, Rieta JJ, Sánchez C, Moratal D (2006) Performance study of convolutive BSS algorithms applied to the electrocardiogram of atrial fibrillation. In: Proceedings of 6th international conference independent component analysis and blind signal separation: ICA 2006, pp 495–502Google Scholar
  29. 29.
    Vanello N, Positano V, Ricciardi E, Santarelli MF, Guazzelli A, Pietrini P, Landini L (2003) Independent component analysis of fMRI data: a model based approach for artifacts separation. In: Proceedings of 1st International IEEE EMBS Conference on Neural Engineering, pp 529–532Google Scholar
  30. 30.
    Webster JG (1984) Reducing motion artifacts and interference in biopotential recording. IEEE Trans Biomed Eng 31(12):823–826CrossRefGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2007

Authors and Affiliations

  • M. Milanesi
    • 1
    • 2
    Email author
  • N. Martini
    • 2
  • N. Vanello
    • 2
  • V. Positano
    • 3
  • M. F. Santarelli
    • 3
  • L. Landini
    • 4
  1. 1.Department of Electrical Systems and AutomationUniversity of PisaPisaItaly
  2. 2.Interdepartmental Research Center “E. Piaggio”University of PisaPisaItaly
  3. 3.Institute of Clinical PhysiologyNational Research CouncilPisaItaly
  4. 4.Department of Information EngineeringUniversity of PisaPisaItaly

Personalised recommendations