fetal electrocardiogram extraction based on non-stationary ica and wavelet denoising

Vincent Vigneron (1) , Anisoara Paraschiv-Ionescu (2) , Annabelle Azancot (3) , Christian Jutten (4) , Olivier Sibony (3)

1 LSC - Laboratoire Systèmes Complexes
2 LMAM - Laboratory of Movement Analysis and Measurement
3 Service d'Obstétrique Gynécologique
4 LIS - Laboratoire des images et des signaux

Fetal electrocardiogram (fECG) monitoring is a technique for obtaining important information about the condition of the fetus during pregnancy and labour by measuring electrical signals generated by the fetal heart as measured from multi-channel potential recordings on the mother body surface. It is shown in this paper that the fetal ECG can be reconstructed by means of higher order statistical tools exploiting ECG non-stationarity associated with post-denoising with wavelets. The method is illustrated on real fetal ECG data.

Domaines: Traitement du signal et de l'image [eess.SP]

Vincent Vigneron, Anisoara Paraschiv-Ionescu, Annabelle Azancot, Christian Jutten, Olivier Sibony. fetal electrocardiogram extraction based on non-stationary ica and wavelet denoising. 7th IEEE International Symposium on Signal Processing and its applications, Jul 2003, Paris, France. pp.00. ⟨hal-00232989⟩