Comparison study of population-based methods for non-invasive fetal electrocardiography extraction

The study compares five population-based optimization algorithms for extracting fetal electrocardiogram (fECG) from abdominal electrocardiogram: artificial bee colony (ABC), gray wolf optimization (GWO), moth flame optimization (MFO), particle swarm optimization (PSO), and whale optimization algorithm (WOA). These algorithms are used with sequential analysis to extract the fECG signal that coexists with other signals, particularly maternal electrocardiogram (mECG), which overlaps with fECG in both time and frequency domains. The systems were tested on two available datasets (Labor and Pregnancy) and their efficiency was evaluated by R-peak detection accuracy. Experiments were conducted 30 times independently. Results showed that systems with GWO, MFO, PSO, and WOA demonstrated similar performance, while the ABC-based system performed poorly and exhibited instability. The authors recommend further investigation of hybrid approaches and modifications to the ABC algorithm.