EEG Signal Classification Using Neural Networks

Abstract

The application of Artificial Neural Networks (ANN) to electroencephalographic (EEG) signal classification is presented. Initially, the power spectrum and coherence ``reactivity'' parameters are extracted from the EEG signals in order to provide the inputs to the ANNs. In addition, traditional statistical and classification methods are utilized to improve the accuracy of the ANN classifiers. Various ANN experiments are performed and their results are discussed.