Fetal ECG extraction based on different kernel functions of SVM

In this paper, we have applied the support vector machine (SVM) in the fetal ECG extraction. The fetal ECG is obtained by subtracting the estimated maternal ECG from the abdominal signal. We evaluate the performance of three types of kernel function in the SVM: linear kernel, polynomial kernel and RBF kernel. The visual quality of the extracted fetal ECG shows that linear kernel fails to suppress the maternal component completely. The RBF kernel achieves a better extent than polynomial kernel but takes longer time to complete the calculation. Also, the polynomial method is implemented much conveniently as it contains less parameter than the RBF method.