Performance evaluation of nonparametric ICA algorithm for fetal ECG extraction

Fetal electrocardiograms (FECG) contain important indications about the health and condition of the fetus. In this respect, it is crucial to apply a robust algorithm to ECG data for extraction of the FECG signal. Most of the independent component analysis (ICA) algorithms used for this purpose rely on simple statistical models. Such algorithms can fail to separate desired signals when the assumed statistical model is inaccurate. Statistical models can be estimated accurately using kernel density estimation methods. Therefore, the kernel density estimation method was used in this paper for building an ICA algorithm (nonparametric ICA: NpICA) and the algorithm was applied to abdominal recordings to separate the FECG signals, which had not been implemented before. Checking of the separation quality of the NpICA algorithm was applied to synthetic ECG signals and real multichannel ECG recordings obtained from a pregnant woman's skin. The test results showed that the NpICA algorithm outperformed other known ICA algorithms such as FastICA and JADE. The superior performance of the NpICA algorithm was especially evident in recordings with high signal length. This indicates that the NpICA method is more robust than other classical ICA algorithms for FECG extraction.
Anahtar Kelimeler:

ECG, FECG, ICA, JADE, FastICA, BSS

Performance evaluation of nonparametric ICA algorithm for fetal ECG extraction

Fetal electrocardiograms (FECG) contain important indications about the health and condition of the fetus. In this respect, it is crucial to apply a robust algorithm to ECG data for extraction of the FECG signal. Most of the independent component analysis (ICA) algorithms used for this purpose rely on simple statistical models. Such algorithms can fail to separate desired signals when the assumed statistical model is inaccurate. Statistical models can be estimated accurately using kernel density estimation methods. Therefore, the kernel density estimation method was used in this paper for building an ICA algorithm (nonparametric ICA: NpICA) and the algorithm was applied to abdominal recordings to separate the FECG signals, which had not been implemented before. Checking of the separation quality of the NpICA algorithm was applied to synthetic ECG signals and real multichannel ECG recordings obtained from a pregnant woman's skin. The test results showed that the NpICA algorithm outperformed other known ICA algorithms such as FastICA and JADE. The superior performance of the NpICA algorithm was especially evident in recordings with high signal length. This indicates that the NpICA method is more robust than other classical ICA algorithms for FECG extraction.

___

  • M.J. Lewis, “Review of electromagnetic source investigations of the fetal heart”, Med. Eng. Phys., Vol. 25, pp. 801-810, 2003.
  • E.M. Symonds, D. Sahota, A. Chang, Fetal Electrocardiography, London, UK, Imperial College Press, 2001.
  • J.A. Crowe, A. Harrison, B.R. Hayes, “The feasibility of long-term fetal heart rate monitoring in the home environment using maternal abdominal electrodes”, Physiol. Meas., Vol. 16, pp. 195-202, 1995.
  • M. Ungureanu, J.W.M. Bergmans, M. Mischi, S.G. Oei, R. Strungaru, “Improved method for fetal heart rate monitoring”, 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE- EMBS, Shanghai, China, pp. 5916-5919, 2005.
  • E.C. Karvounis, M.G. Tsipouras, D.I. Fotiadis, K.K. Naka, “An automated methodology for fetal heart rate extraction from the abdominal electrocardiogram”, IEEE Trans. Inf. Technol. Biomed., Vol. 11, pp. 628-638, 2007. [6] D. Adam, D. Shaut, “Complete foetal ECG morphology recording by synchronized adaptive Şltration”, Medical & Biological Eng. & Computing, Vol. 28, pp. 287-292, 1990.
  • L. de Lathauwer, B. de Moor, J. Vandewalle, “Fetal electrocardiogram extraction by blind source subspace separa- tion”, IEEE Trans. Biomed. Eng., Vol. 47, pp. 567-572, 2000.
  • T. Oostendorp, Modelling the Fetal ECG, PhD dissertation, K.U. Nijmegen, The Netherlands, 1989.
  • P.P. Kanjilal, S. Palit, G. Saha, “Fetal ECG extraction from single channel maternal ECG using singular value decomposition”, IEEE Trans. Biomed. Eng., Vol. 47, pp. 51-59, 1997.
  • J.F. Cardoso, “Multidimensional independent component analysis”, Proceedings of the IEEE International Confer- ence on Acoustics, Speech, and Sig. Proc. (ICASSP’98), Vol. 4, pp. 1941-1944, 1998.
  • F. Vrins, V. Vigneron, C. Jutten, M. Verleysen, “Abdominal electrodes analysis by statistical processing for fetal electrocardiogram extraction”, in Proc. 2nd IASTED Int. Conf. on Biomedical Eng. (Biomed 2004), Innsbruck, Austria, pp. 244-249, 2004.
  • M. Kotas, “Projective Şltering of time-aligned beats for foetal ECG extraction”, Bulletin of Polish Academy of Sciences, Vol. 55, pp. 331-339, 2007.
  • D.V. Prasad, R. Swarnalatha, “Extraction of fetal ECG from abdominal signal”, BIOSIGNAL 2009, Portugal, pp. 245-248, 2009.
  • P. Gao, E.C. Chang, L. Wyse, “Blind separation of fetal ECG from single mixtures using SVD and ICA”, Proceedings of ICICS-PCM 2003, Singapore, pp. 15-18, 2003.
  • Y. Ye, Z.L. Zhang, J. Chen, “A robust and non-invasive fetal electrocardiogram extraction algorithm in a semi- blind way”, IEICE Trans. on Fundamentals of Electronics, Communications and Computer Sciences, Vol. E91-A, [16] J. Tsao, C.Y. Hsu, M.T. Lo, “A supervised ICA algorithm for fetal ECG extraction”, ISSNIP 2008, Australia, pp. 327-330, 2008.
  • D. Pani, S. Argiolas, L. Raffo, “A DSP algorithm and system for real-time fetal ECG extraction”, Computers in Cardiology, Vol. 35, pp. 1065-1068, 2008.
  • S.I. Amari, T.P. Chen, A. Cichocki, “Stability analysis of learning algorithms for blind source separation”, Neural Networks, Vol. 10, pp. 1345-1351, 1997.
  • S. Amari, S. Cichocki, H. Yang, “A new learning algorithm for blind source separation”, Advances in Neural Information Processing Systems, Vol. 8, pp. 757-763, 1996.
  • A. Hyvarinen, “Survey on independent component analysis”, Neural Computing Surveys, Vol. 2, pp. 94-128, 1999. [21] B.W. Silverman, Density Estimation for Statistics and Data Analysis, New York, Chapman and Hall, 1985.
  • M.C. Jones, The Projection Pursuit Algorithm for Exploratory Data Analysis, PhD dissertation, School of Mathe- matics, Univ. of Bath, 1983.
  • W.L. Martinez, A.R. Martinez, Computational Statistics Handbook with MATLAB 2e, Chapman and Hall, 2008. [24] R. Boscolo, H. Pan, V.P. Roychowdhury, “Non-parametric ICA”, Proceedings of the Third International Symposium on Independent Component Analysis and Blind Signal Separation (ICA2001), San Diego, pp. 13-18, 2001.
  • R. Boscolo, H. Pan, V.P. Roychowdhury, “Independent component analysis based on non-parametric density estimation”, IEEE Transactions on Neural Networks, Vol. 15, pp. 55-65, 2004.
  • A. Bell, T. Sejnowski, “An information maximization approach to blind source separation and blind deconvolution”, Neural Computing, Vol. 7, pp. 1129-1159, 1995.
  • A. Hyvarinen, “Fast and robust Şxed point algorithms for independent component analysis”, IEEE Trans. on Neural Networks, Vol. 10, pp. 626-634, 1999.
  • H.B. Barlow, “Unsupervised learning”, Neural Computation, Vol. 1, pp. 565-608, 1989.
  • T.M. Cover, J.A. Thomas, Elements of Information Theory, John Wiley & Sons, 1991.
  • J.F. Cardoso, “Blind signal separation: statistical principles”, Proceedings of the IEEE, Special Issue on Blind IdentiŞcation and Estimation, Vol. 9, pp. 2009-2025, 1998.
  • D. Donoho, “On minimum entropy deconvolution”, Proceedings of the Second Applied Time Series Symposium, D.F. Findley, Ed., pp. 565-608, 1981.
  • J.F. Cardoso, “Infomax and maximum likelihood for source separation”, IEEE Letters on Signal Processing, Vol. 4, pp. 112-114, 1997.
  • N. Vlassis, Y. Motomura, “Efficient source adaptivity in independent component analysis,” IEEE Trans. Neural Networks, Vol. 12, pp. 559-566, 2001.
  • J. Karvanen, J. Eriksson, V. Koivunen, “Pearson system based method for blind separation”, Proceedings of Second International Workshop on Independent Component Analysis and Blind Signal Separation, pp. 585-590, 2000.
  • E.K.P. Chong, S.H. Zak, An Introduction To Optimization, John Wiley & Sons, 2001.
  • J.F. Cardoso, “High-order contrasts for independent component analysis”, Neural Computation, Vol. 11, pp. 157- 192, 1999.
  • J.F. Cardoso, A. Souloumiac, “Blind beamforming for non-Gaussian signals”, IEEE Proceedings Part F, Vol. 140, [38] C. Salustri, G. Barbati, C. Porcaro, “Fetal magnetocardiographic signals extracted by ‘signal subspace’ blind source separation”, IEEE Transactions on Biomedical Engineering, Vol. 52, pp. 1140-1142, 2005.
  • V. Zarzoso, J.M. Roig, A.K. Nandi, “Fetal ECG extraction from maternal skin electrodes using blind source separation and adaptive noise cancellation techniques”, Computers in Cardiology, Vol. 27, pp. 431-434, 2000.
Turkish Journal of Electrical Engineering and Computer Science-Cover
  • ISSN: 1300-0632
  • Yayın Aralığı: Yılda 6 Sayı
  • Yayıncı: TÜBİTAK