Preliminary Results of Ocular Artefacts Identification in EEC Series by Neural Network

Abstract

The human electroencephalogram (EEG), is record of the electrical activity of the brain and contains useful diagnostic information on a variety of neurological disorders. Normal EEG signal are usually registered from electrodes placed on the scalp, and are often very small in amplitude, of 20 µV. The EEG, like all biomedical signals, is very susceptible to a variety of large signal contamination or artefacts (signals of other than brain activity) which reduce its clinical usefulness. For example, blinking or moving eyes produces large electrical potentials around the eyes called the electrooculogram (EOG). The EOG spreads across the scalp to contaminate the EEG, when it is referred to as an ocular artefact (OA). This paper includes method of identification portion of the EEG record where ocular artefact appears and classification its type by neural network.