FECG Extraction Based on Least Square Support Vector Machine Combined with FastICA

A new method based on least square support vector machine (LSSVM) combined with FastICA is proposed to extract the fetal electrocardiogram (FECG) from the abdominal signals of a pregnant woman. Firstly, the LSSVM is applied to estimate the maternal electrocardiogram (MECG) component in the multiplex abdominal signals. Then the optimal estimation of multiplex noise-added FECG is obtained by removing the estimated MECG component from the multiplex abdominal signals. Finally, the FastICA is applied to extract the FECG from the multiplex noise-added FECG. The proposed method is validated by the experiments on real electrocardiogram (ECG). The visual results, signal-to-noise ratio (SNR) and training time are used to evaluate the performance of the FECG extraction methods. The experimental results indicate that the FECG is effectively extracted from the abdominal signals utilizing proposed method.

[1]  Zheng Wei,et al.  Adaptive filtering in phase space for foetal electrocardiogram estimation from an abdominal electrocardiogram signal and a thoracic electrocardiogram signal , 2012 .

[2]  Mamun Bin Ibne Reaz,et al.  Fetal electrocardiogram extraction and R-peak detection for fetal heart rate monitoring using artificial neural network and Correlation , 2011, The 2011 International Joint Conference on Neural Networks.

[3]  Khaled Assaleh,et al.  Extraction of Fetal Electrocardiogram Using Adaptive Neuro-Fuzzy Inference Systems , 2007, IEEE Transactions on Biomedical Engineering.

[4]  Te-Won Lee,et al.  Learning statistically efficient features for speaker recognition , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[5]  Joon-Hyuk Chang,et al.  Enhancing support vector machine-based speech/music classification using conditional maximum a posteriori criterion , 2012, IET Signal Process..

[6]  Gustavo Camps-Valls,et al.  Foetal ECG recovery using dynamic neural networks , 2004, Artif. Intell. Medicine.

[7]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[8]  D I Fotiadis,et al.  A Non-invasive Methodology for Fetal Monitoring during Pregnancy , 2009, Methods of Information in Medicine.

[9]  Reinhold Orglmeister,et al.  Blind source separation of real world signals , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[10]  P. Ducange,et al.  Multi-objective evolutionary design of granular rule-based classifiers , 2016 .

[11]  Georg Peters,et al.  DCC: a framework for dynamic granular clustering , 2016 .

[12]  D. Chakrabarti,et al.  A fast fixed - point algorithm for independent component analysis , 1997 .

[13]  Habibollah Haron,et al.  Statistical Learning Theory and Support Vector Machines , 2010, 2010 Second International Conference on Computer Research and Development.

[14]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[15]  Joon-Hyuk Chang,et al.  Statistical model-based voice activity detection using support vector machine , 2009 .

[16]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[17]  Rodica Strungaru,et al.  Improved fetal ECG extraction by applying adaptive filtering , 2011, 2011 7TH INTERNATIONAL SYMPOSIUM ON ADVANCED TOPICS IN ELECTRICAL ENGINEERING (ATEE).

[18]  Takuya Ito,et al.  A Novel Extraction Method of Fetal Electrocardiogram From the Composite Abdominal Signal , 2007, IEEE Transactions on Biomedical Engineering.

[19]  Terrence J. Sejnowski,et al.  Unsupervised Classification with Non-Gaussian Mixture Models Using ICA , 1998, NIPS.

[20]  G. Camps,et al.  Methods to evaluate the performance of fetal electrocardiogram extraction algorithms , 2001, Computers in Cardiology 2001. Vol.28 (Cat. No.01CH37287).

[21]  Wei Zheng,et al.  Noninvasive fetal ECG estimation using adaptive comb filter , 2013, Comput. Methods Programs Biomed..

[22]  Yan-jun Zeng,et al.  Extraction of fetal electrocardiogram using recursive least squares and normalized least mean squares algorithms , 2011, 2011 3rd International Conference on Advanced Computer Control.

[23]  Rik Vullings,et al.  Probabilistic Source Separation for Robust Fetal Electrocardiography , 2013, Comput. Math. Methods Medicine.

[24]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.