Fetal ECG Extraction Using ANFIS Trained With Genetic Algorithm

Nowadays, ICA based methods are widely used. However, ICA needs multiples channels for collecting electrocardiogram signals. One of the most significant advantages of utilizing ANFIS networks in FECG extraction is that the methods require only two record signals, one thoracic signal and one abdominal ECG signal. In the present work, ANFIS network is apply to extract the FECG signal from both ECG signals recorded at the thoracic and abdominal areas of the mother’s skin. This can be performing using ANFIS to identify the nonlinear relationship between the maternal component in the abdominal ECG and the thoracic MECG which is assumed to include no fetal component in it. The Technique on both real and synthetic ECG signals will be validated with experiment result. In generating the synthetic abdominal ECG signals, multipath and nonlinear effects apply to the thoracic signal for simulate the transformation and it travels from the heart to the abdomen. Finally, noise can be suppressed by post processing methods such as wavelet de-noising that has proven useful with other FECG extraction methods.