Comparative study of fetal ECG elicitation using adaptive filtering techniques

Fetal electrocardiogram (f-ECG) elicitation is crucial for cardiac health monitoring of fetus and neonates. This work presents five non-invasive f-ECG elicitation techniques using Least Mean Square (LMS), Normalized Least Mean Square (NLMS), Sign-error Least Mean Square (SELMS), Affine Projection Algorithm (AP), and Recursive Least Square (RLS). The performance of the algorithms is compared on the basis of correlation index between original and recovered signal. Computational complexity per iteration of the algorithms is analyzed on the basis of a parameter, computational cost. RLS out-performed all other algorithms in terms of performance and SELMS is better than LMS and its variants, both in terms of performance and computational complexity.