Fetal Electrocardiogram Extraction Using Adaptive Neuro-fuzzy Inference Systems and Undecimated Wavelet Transform

摘要

The Fetal electrocardiogram (FECG) signal reflects the electrical activity of the fetal heart. Fetal heart monitoring yields vital information about the fetus health and can support medical decision making in critical situations. In this paper, FECG is extracted from the maternal electrocardiogram using adaptive neuro-fuzzy inference systems and undecimated wavelet transform (UWT) is proposed. The performance of the proposed system is compared with the standard discrete wavelet transform (DWT). For numerical evaluation, the mean square error (MSE) between de-noised FECG signal and original FECG signal is used. Experimental results show that the UWT produce better results than DWT, as the MSE of DWT is higher than the UWT.