Removal of ocular artifacts from EEG using an efficient neural network based adaptive filtering technique

The electroencephalogram (EEG) is susceptible to various large signal conta minations or artifacts. Ocular artifacts act as major source of noise, maki ng it difficult to distinguish normal brain activities from the abnormal on es. In this letter, an efficient technique that combines two popular adapti ve filtering techniques, namely adaptive noise cancellation and adaptive si gnal enhancement, in a single recurrent neural network is proposed for the adaptive removal of ocular artifacts from EEG, Real time recurrent learning algorithm is employed for training the proposed neural network which conve rges faster to a lower mean squared error. This technique is suitable for r eal-time processing.