Blind Extraction for Noisy Fetal Electrocardiogram by Using Gaussian Moments

Non-invasive fetal electrocardiogram (FECG) extraction is a vital issue in biomedical signal processing and analysis. A promising approach is blind source extraction and many algorithms have been proposed in recent years. In this paper, we consider the blind extraction when Gaussian noise is present and the source signals combine the non-Gaussianity and the autocorrelations. According to the useful properties of Gaussian moments, a simple gradient algorithm is developed for noisy blind extraction. Validity and performance of the described algorithm are demonstrated by computer simulations.