Fetal electrocardiogram extraction using blind source separation and empirical mode decomposition
When fetal electrocardiogram (FECG) is acquired with non-invasive method, it is overwhelmed by the mother electrocardiogram (MECG) and other contaminated noises, thus, FECG is difficult to be extracted. In order to obtain more clearer FECG, a FECG extraction method that combines a blind source separation with empirical mode decomposition is proposed in this paper. Firstly, FECG is extracted from maternal abdominal ECG, the mixed signal using the RLS blind source separation algorithm based natural gradient, then, the noisy FECG signal is decomposed by empirical mode decomposition and its intrinsic mode functions (IMF) is adjusted, finally, the clear FECG signal is obtained after some IMF are reconstructed. Experimental results show that the algorithm can rapidly and efficiently extract FECG and greatly suppress noise, it is a efficient FECG extraction method.