The human electroencephalogram (EEG) is often corrupted by ocular artefacts (OAs) caused by the movement of the eyes and/or the eyelids, making the recognition of abnormal EEG signals more difficult. The removal of OAs using conventional signal processing is complicated by the similarity between abnormal EEGs and OAs, which can lead to corruption of the EEG signal. The paper describes the development of a novel approach that uses expert system techniques to differentiate OAs from genuine EEG signals, enabling OA removal to be applied only where appropriate, and ensuring that clinically relevant EEG information is left unaffected.
Read full abstract