Performance comparison of four ICA algorithms applied for fECG extraction from transabdominal recordings

Fetal ECG (fECG) signal offers valuable information about the health state of the fetus during pregnancy that can assist physicians taking timely the appropriate decisions during pregnancy and labor. Thus, the FECG signal extraction from composite abdominal signals (ADS) by powerful and advance signal processing methods is becoming more and more an important requirement for fetal monitoring. This paper presents the evaluation of four Independent Component Analysis (ICA) algorithms, when used for fECG extraction, and their performance comparison when considering the application of the Event Synchronous Canceller (ESC) as a preprocessing step that cancel the maternal ECG (mECG). The algorithms are evaluated when considering two data sets of simulated ADS.