SMALS: A SVD Multi-Stage Adaptive Least Square Approach for FECG Signal Extraction in Multichannel System

In this paper the abdominal signal is de-noised and the Fetal ECG is extracted for obtaining the important information about the fetus during pregnancy. Noise analysis and removal is done using different signal processing techniques. The results are been compared. To cancel out a Maternal ECG and noise from the Abdominal ECG, different types of filtering techniques are used. A Multistage adaptive filtering along with the SVD denoising techniques to extract the FECG from the abdominal signal is proposed. The proposed architecture is a combination of Singular Value Decomposition (SVD) filtering method and Multistage Adaptive filter model. This method leads to enhancement of fetal ECG by canceling maternal ECG and noises in the first stage using SVD. The FECG extraction is done using multistage multichannel adaptive filter from 4 channels simulated and 5 real time channel signals recorded at the thoracic and abdominal areas of the mother?s skin. The thoracic ECG simulated is assumed to be almost completely maternal while the abdominal ECG (AECG) is considered to be composite as it contains both the mother?s, fetus ECG signals and the noise. The proposed method is applied to simulated and real time ECG signals to demonstrate its superior effectiveness.