Fetal ECG extraction using wiener, SVD and ICA algorithms

Abstract

Fetal Electrocardiogram (FECG) signal recording is one of the best techniques for Heart signal monitoring of fetus. It is also used to monitor health condition of fetus in pregnancy period continuously. Fetal electrocardiogram is nothing but wave form which shows electrical activity of fetus’s heart. FECG is extracted from a signal recorded on the mother’s abdomen, which is an indirect method (non-invasive method). Abdomen signal includes mother electrocardiogram (MECG) signal, FECG signal and noise signal. Different indirect methods to extract the Fetal Electrocardiogram (FECG) signal from an ECG recorded on the mother’s abdomen have been proposed. In this thesis, three methods are used, which are as follows: Singular Value Decomposition (SVD) method, Independent Component Analysis (ICA) method, and Weiner Filtering method. Wiener filter uses the linear least square estimation; SVD uses the variance as measure which is similar to Eigen value decomposition and ICA uses the fourth order moment, kurtosis. SVD and ICA are comes under statistical domain and also blind source separation, whereas Wiener filter comes under Fourier domain. The mentioned methods use signal processing techniques for extracting FECG from Abdominal Electrocardiogram (AECG) and uses a multi-channel data/signal. The advantages and disadvantages of each method are discussed. The methods have applied on synthetic ECG signals of 10 seconds with a sampling rate of 256Hz. Efficiencies of all the methods are compared together based on the few important criterions, which are output waveform, PSD, and SNR. The results are stated and best method based on the criterions is selected.