Enhancing Fetal ECG Using Gaussian Process

Saman Noorzadeh (1) , Bertrand Rivet (1) , Pierre-Yves Guméry (2)

1 GIPSA-VIBS - GIPSA - Vision and Brain Signal Processing
2 TIMC-IMAG - Techniques de l'Ingénierie Médicale et de la Complexité - Informatique, Mathématiques et Applications, Grenoble - UMR 5525

This paper investigates the problem of the extraction of fetal ECG from the noisy abdominal channel. The method which is presented here is a multi-channel one which uses two data channels: one is the abdominal channel and the other is the reference channel. The reference channel, which is recorded from the chest of the mother, can well define the covariance function to model the maternal ECG contribution in the abdominal channel. The maternal ECG can then be extracted using this model which proposes a non-linear extraction. The reference signal is also proposed to be replaced with a 1-bit thoracic signal which can be cheaply recorded and has less time complexity to be processed.

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

Saman Noorzadeh, Bertrand Rivet, Pierre-Yves Guméry. Enhancing Fetal ECG Using Gaussian Process. IMA International Conference on Mathematics in Signal Processing, Dec 2014, Birmingham, United Kingdom. ⟨hal-01133615⟩