A hybrid nonlinear adaptive noise canceller for fetal ECG extraction

In this paper, a hybrid nonlinear adaptive noise canceller (ANC) with single-or multi-reference channels is proposed to perform the task of extracting fetal electrocardiogram (FECG). A Volterra filter and a functional link artificial neural network (FLANN) are equipped in parallel in each reference channel to approximate the linearity and nonlinearity between the maternal ECG (MECG) and its distorted version within the abdominal ECG (AECG). Two (2) real ECG datasets are utilized to demonstrate the improved effectiveness of the proposed ANC as compared with other three (3) existing ANCs using FIR filter, Volterra filter, and FLANN alone.