HAL : hal-00681534, version 1

Fiche détaillée

Récupérer au format BibTeX - EndNote - TEI - RefWorks -

10th International Conference on Latent Variable Analysis and Source Separation (LVA/ICA 2012), Tel-Aviv : Israel (2012)

Non parametric modelling of ECG: Applications to denoising and single sensor fetal ECG extraction

Bertrand Rivet 1, Mohammad Niknazar 1, Christian Jutten 1

(03/2012)

In this work, we tackle the problem of fetal electrocardio- gram (ECG) extraction from a single sensor. The proposed method is based on non-parametric modelling of the ECG signal described thanks to its second order statistics. Each assumed source in the mixture is thus modelled as a second order process thanks to its covariance function. This modelling allows to reconstruct each source by maximizing the re- lated posterior distribution. The proposed method is tested on synthetic data to evaluate its performance behavior to denoise ECG. It is then ap- plied on real data to extract fetal ECG from a single maternal abdominal sensor.

1 :	Grenoble Images Parole Signal Automatique (GIPSA-lab)
	CNRS : UMR5216 – Université Joseph Fourier - Grenoble I – Université Pierre-Mendès-France - Grenoble II – Université Stendhal - Grenoble III – Institut Polytechnique de Grenoble - Grenoble Institute of Technology

Équipe de recherche : ViBS

Domaine

:

Sciences de l'ingénieur/Traitement du signal et de l'image Informatique/Traitement du signal et de l'image

hal-00681534, version 1

http://hal.archives-ouvertes.fr/hal-00681534

oai:hal.archives-ouvertes.fr:hal-00681534

Contributeur : Bertrand Rivet <>

Soumis le : Mercredi 21 Mars 2012, 17:00:02

Dernière modification le : Vendredi 6 Avril 2012, 10:20:58