A novel adaptive filtering technique for the processing of abdominal fetal electrocardiogram using neural network

The abdominal fetal signal recorded non-invasively by placing the electrodes on the mother's abdomen, consists of a weak fetal signal, a relatively strong maternal heart signal and considerable noise contributed by the electrical potential from the maternal abdominal muscles and random electrical noise. In this paper an efficient technique which combines two popular adaptive filtering techniques, namely adaptive noise cancellation and adaptive signal enhancement, in a single recurrent neural network is proposed for processing the abdominal fetal electrocardiogram. Real time recurrent learning algorithm is employed for training the proposed neural network which converges faster to a lower mean squared error. This technique is suitable for real-time processing.