Denoising Phonocardiogram signals with Non-negative Matrix Factorization informed by synchronous Electrocardiogram

The phonocardiographic signals (PCG) are of interest for the analysis of the cardiac mechanical function. However, they are not always directly exploitable because of ambient interference (gastric noises, breathing noises, etc.). We aim to denoise PCG signals using another cardiac modality, the electrocardiographic (ECG) signal. In this paper, we investigate an informed non-negative matrix factorization to extract signal components out of the noisy PCG signal, considering synchronous ECG information. Our approach is applied and evaluated on a database consisting of real and artificially noisy PCG signals.

[1]  Derek Abbott,et al.  Optimal wavelet denoising for phonocardiograms , 2001 .

[2]  R. O'Rourke.  Gallop rhythm. , 1972, The Medical annals of the District of Columbia.

[3]  Rémi Gribonval,et al.  Performance measurement in blind audio source separation , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[4]  M.R. Azimi-Sadjadi,et al.  Reduced order Kalman filtering for the enhancement of respiratory sounds , 1996, IEEE Transactions on Biomedical Engineering.

[5]  Pierre-Yves Gumery,et al.  A multi-modal approach using a non-parametric model to extract fetal ECG , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Andrzej Cichocki,et al.  Nonnegative Matrix and Tensor Factorization T , 2007 .

[7]  Mohammed Abo-Zahhad,et al.  Biometric authentication based on PCG and ECG signals: present status and future directions , 2013, Signal, Image and Video Processing.

[8]  Emmanuel Vincent,et al.  Multi-Channel Audio Source Separation Using Multiple Deformed References , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[9]  Antoine Liutkus,et al.  The 2016 Signal Separation Evaluation Campaign , 2017, LVA/ICA.

[10]  Christian Jutten,et al.  Multimodal Data Fusion: An Overview of Methods, Challenges, and Prospects , 2015, Proceedings of the IEEE.

[11]  Miroslav Zivanovic,et al.  ECG-EMG separation by using enhanced non-negative matrix factorization , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[12]  Christian Jutten,et al.  Multimodal Soft Nonnegative Matrix Co-Factorization for Convolutive Source Separation , 2017, IEEE Transactions on Signal Processing.

[13]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[14]  Olivier Cappé,et al.  Soft nonnegative matrix co-factorizationwith application to multimodal speaker diarization , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[15]  Jérôme Idier,et al.  Algorithms for Nonnegative Matrix Factorization with the β-Divergence , 2010, Neural Computation.