Separation Of Maternal And Fetal ECG Signals From The Mixed Source Signal Using FASTICA

In this paper it is proposed to separate the ECG signal taken from skin electrodes located on a pregnant woman's body into Maternal Electro Cardiogram signal and Fetal Electro Cardiogram signal. Blind Source Separation is the technique used for separating these source signals. ICA is applied on the mixed signals and the separated signals are reconstructed using wavelet reconstruction. Comparison results show that Lifting Wavelet Transformation and FASTICA algorithm produces the best SNR value of 11.39 for maternal and 10.10 for fetal Electro Cardio Gram signals.