FECG Extraction Based on Least Square Support Vector Machine Combined with FastICA

A new method based on least square support vector machine (LSSVM) combined with FastICA is proposed to extract the fetal electrocardiogram (FECG) from the abdominal signals of a pregnant woman. Firstly, the LSSVM is applied to estimate the maternal electrocardiogram (MECG) component in the multiplex abdominal signals. Then the optimal estimation of multiplex noise-added FECG is obtained by removing the estimated MECG component from the multiplex abdominal signals. Finally, the FastICA is applied to extract the FECG from the multiplex noise-added FECG. The proposed method is validated by the experiments on real electrocardiogram (ECG). The visual results, signal-to-noise ratio (SNR) and training time are used to evaluate the performance of the FECG extraction methods. The experimental results indicate that the FECG is effectively extracted from the abdominal signals utilizing proposed method.