Fetal ECG Signal Enhancement using Polynomial Classifiers and Wavelet Denoising

This paper addresses the enhancements achievable by the application of wavelet transform to fetal ECG (FECG) signals extracted by polynomial networks. The polynomial networks technique has been exploited to isolate fetal electrocardiogram (FECG) from the undesired mapped maternal electrocardiogram (mapped MECG). In this paper wavelet transform is used to enhance the extracted FECG. Processing of both real and synthetic ECG data are examined with proposed pre and post wavelet denoising algorithms. Results show improved extraction performance and successful removal of baseline wandering. Numerical results of signal-to-noise ratio for synthetic data attest considerable enhancement. The characteristics of the FECG signal were shown to be preserved and a relatively clean FECG signal is obtained.