Artificial Neural Networks (ANNs) for EEG Purging using Wavelet Analysis

The Electroencephalogram (EEG) is a biological signal that represents the electrical activity of the brain. Artifacts in EEG signals are caused by various factors, like line interference, EOG (electro-oculogram) and ECG (electrocardiogram). The removal of artifact from scalp EEGs is of considerable importance for analysis of underlying brainwave activity. The presence of artifacts such as muscle activity, eye blinks, pulse signals and line noise in electroencephalographic (EEG) recordings obscures the underlying processes. These artifacts sources increase the difficulty in analyzing the EEG. For this reason, it is necessary to design a procedure to decrease such artifacts in EEG. A commonly encountered problem in artifact removal is the ‘blanking’ of the EEG signal due to blinking of the patient’s eyes. In biomedical analysis, EEG signal consists of artifacts. The fundamental basis of the paper here is to address the elimination of ocular artifact called Electroculogram (EOG) from Electroencephalogram (EEG) signal using wavelet method. An algorithm using wavelet analysis is implemented to eliminate the eye blink artifact without compromising the integrity of the primary EEG data.