Temporally Nonstationary Component Analysis; Application to Noninvasive Fetal Electrocardiogram Extraction

Objective: Mixtures of temporally nonstationary signals are very common in biomedical applications. The nonstationarity of the source signals can be used as a discriminative property for signal separation. Herein, a semi-blind source separation algorithm is proposed for the extraction of temporally nonstationary components from linear multichannel mixtures of signals and noises. Methods: A hypothesis test is proposed for the detection and fusion of temporally nonstationary events, by using ad hoc indexes for monitoring the first and second order statistics of the innovation process. As proof of concept, the general framework is customized and tested over noninvasive fetal cardiac recordings acquired from the maternal abdomen, over publicly available datasets, using two types of nonstationarity detectors: 1) a local power variations detector, and 2) a model-deviations detector using the innovation process properties of an extended Kalman filter. Results: The performance of the proposed method is assessed in presence of white and colored noise, in different signal-to-noise ratios. Conclusion and Significance: The proposed scheme is general and it can be used for the extraction of nonstationary events and sample deviations from a presumed model in multivariate data, which is a recurrent problem in many machine learning applications.

[1]  Joos Vandewalle,et al.  Fetal electrocardiogram extraction by blind source subspace separation , 2000, IEEE Transactions on Biomedical Engineering.

[2]  Jean-François Cardoso,et al.  Equivariant adaptive source separation , 1996, IEEE Trans. Signal Process..

[3]  A. Gacek,et al.  Computationally effective algorithm for robust weighted averaging , 2004, IEEE Transactions on Biomedical Engineering.

[4]  Andrzej Cichocki,et al.  Second Order Nonstationary Source Separation , 2002, J. VLSI Signal Process..

[5]  R. Sameni,et al.  An iterative subspace denoising algorithm for removing electroencephalogram ocular artifacts , 2014, Journal of Neuroscience Methods.

[6]  Gholam-Ali Hossein-Zadeh,et al.  MR artifact reduction in the simultaneous acquisition of EEG and FMRI of epileptic patients , 2008, 2008 16th European Signal Processing Conference.

[7]  Allan Kardec Barros,et al.  Extraction of Specific Signals with Temporal Structure , 2001, Neural Computation.

[8]  Christian Jutten,et al.  A Deflation Procedure for Subspace Decomposition , 2010, IEEE Transactions on Signal Processing.

[9]  J. Cardoso,et al.  Blind beamforming for non-gaussian signals , 1993 .

[10]  Patrick E. McSharry,et al.  A dynamical model for generating synthetic electrocardiogram signals , 2003, IEEE Transactions on Biomedical Engineering.

[11]  Mohinder S. Grewal,et al.  Kalman Filtering: Theory and Practice Using MATLAB , 2001 .

[12]  Jean-Francois Cardoso,et al.  THE THREE EASY ROUTES TO INDEPENDENT COMPONENT ANALYSIS; CONTRASTS AND GEOMETRY , 2001 .

[13]  Dinh Tuan Pham,et al.  Joint Approximate Diagonalization of Positive Definite Hermitian Matrices , 2000, SIAM J. Matrix Anal. Appl..

[14]  Xianda Zhang,et al.  Sequential Blind Extraction Adopting Second-Order Statistics , 2007, IEEE Signal Processing Letters.

[15]  Dinh-Tuan Pham,et al.  Blind separation of instantaneous mixtures of nonstationary sources , 2001, IEEE Trans. Signal Process..

[16]  Reza Sameni,et al.  Extraction of Fetal Cardiac Signals from an Array of Maternal Abdominal Recordings , 2008 .

[17]  C. Jutten,et al.  Identification of brain regions involved in epilepsy using common spatial pattern , 2011, 2011 IEEE Statistical Signal Processing Workshop (SSP).

[18]  Arie Yeredor,et al.  Second-order methods based on color , 2010 .

[19]  Reza Sameni,et al.  Fetal ECG extraction from time-varying and low-rank noninvasive maternal abdominal recordings , 2018, Physiological measurement.

[20]  Jérôme Bobin,et al.  Robust Sparse Blind Source Separation , 2015, IEEE Signal Processing Letters.

[21]  Arie Yeredor.  Performance Analysis of GEVD-Based Source Separation With Second-Order Statistics , 2011, IEEE Transactions on Signal Processing.

[22]  Christian Jutten,et al.  A Nonlinear Bayesian Filtering Framework for ECG Denoising , 2007, IEEE Transactions on Biomedical Engineering.

[23]  Arie Yeredor.  On Optimal Selection of Correlation Matrices for Matrix-Pencil-Based Separation , 2009, ICA.

[24]  P. Tichavsky,et al.  Fast Approximate Joint Diagonalization Incorporating Weight Matrices , 2009, IEEE Transactions on Signal Processing.

[25]  Pierre Comon,et al.  Handbook of Blind Source Separation: Independent Component Analysis and Applications , 2010 .

[26]  Audra E. Kosh,et al.  Linear Algebra and its Applications , 1992 .

[27]  Gari D Clifford,et al.  A practical guide to non-invasive foetal electrocardiogram extraction and analysis , 2016, Physiological measurement.

[28]  Christian Jutten,et al.  Multichannel Electrocardiogram Decomposition Using Periodic Component Analysis , 2008, IEEE Transactions on Biomedical Engineering.

[29]  Robert F. Engle,et al.  Large Dynamic Covariance Matrices , 2017 .

[30]  C Jutten,et al.  Model-based Bayesian filtering of cardiac contaminants from biomedical recordings , 2008, Physiological measurement.

[31]  Michel Verleysen,et al.  Abdominal electrodes analysis by statistical processing for fetal eletrocardiogram extraction , 2004 .

[32]  Jean-François Cardoso,et al.  Multidimensional independent component analysis , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[33]  Joachim Behar,et al.  A Comparison of Single Channel Fetal ECG Extraction Methods , 2014, Annals of Biomedical Engineering.

[34]  G. Clifford,et al.  A Review of Fetal ECG Signal Processing; Issues and Promising Directions. , 2010, The open pacing, electrophysiology & therapy journal.

[35]  Kiyotoshi Matsuoka,et al.  A neural net for blind separation of nonstationary signals , 1995, Neural Networks.