A Novel Approach & Robust Technique for Fetal ECG Analysis

Authors

M.SHANMUGANAND,E.SIVA SHANMUGANATHAN,R.NAGARAJAN,N.ASHWATHY

B.E BIOMEDICAL ENGINEERING

SRI RAMAKRISHNA ENGINEERING COLLEGE,COIMBATORE

Abstract

In this paper, we propose a new method for FECG analysis in abdominal recordings. A fetal ECG contains important indications about the health conditions of fetus and is a diagnostic tool of particular importance. Our method combines the use of Wavelet Transform, Adaptive signal processing and Independent component analysis to extract various information about the fetal ECG. The fetal ECG is obtained from the mother’s abdomen using multi-lead cutaneous electrodes. The position of the electrodes and the number of electrodes used determines the nature of the signal obtained. The obtained ECG contains a number of contaminants and a strong interference from maternal electrical activity. The de-noising of this signal is done using wavelet transform which removes Power Line Interference, Base Line Wandering and other wide-band noises. The intervention of maternal ECG over the FECG can be removed by using Adaptive Signal Processing (ASP).The required features of the fetal ECG is then extracted using Independent Component Analysis (ICA).The proposed method is more accurate as compared to the earlier methods of Direct Subtraction & Singular Value Decomposition (SVD).The expected result from this method is estimated to have a better balance between Accuracy and Smoothness of the output curve.