Clifford wavelets for fetal ECG extraction

TL;DR

This paper introduces a Clifford wavelet-based method for extracting fetal ECG signals from maternal ECG, demonstrating superior performance over classical wavelets in non-invasive fetal heart rate monitoring.

Contribution

It presents a novel Clifford wavelet approach for fetal ECG extraction, improving accuracy and efficiency over traditional wavelet methods.

Findings

Clifford wavelets outperform classical wavelets in fetal ECG extraction.

The proposed method achieves more accurate fetal heart rate monitoring.

Clifford wavelets are the most effective basis for FECG processing.

Abstract

Analysis of the fetal heart rate during pregnancy is essential for monitoring the proper development of the fetus. Current fetal heart monitoring techniques lack the accuracy in fetal heart rate monitoring and features acquisition, resulting in diagnostic medical issues. The challenge lies in the extraction of the fetal ECG from the mother's ECG during pregnancy. This approach has the advantage of being a reliable and non-invasive technique. For this aim, we propose in this paper a wavelet/multi-wavelet method allowing to extract perfectly the feta ECG parameters from the abdominal mother ECG. The method is essentially due to the exploitation of Clifford wavelets as recent variants in the field. We prove that these wavelets are more efficient and performing against classical ones. The experimental results are therefore due to two basic classes of wavelets and multi-wavelets. A first-class is the classical Haar Schauder, and a second one is due to Clifford valued wavelets and multi-wavelets. These results showed that wavelets/multiwavelets are already good bases for the FECG processing, provided that Clifford ones are the best.