System identification of the brain dynamics by EEG analysis using neural networks

We have constructed a multilayered neural network system that identifies brain dynamics from electroencephalogram (EEG) data by error backpropagation (BP) learning. EEG data in the normal state and in the state when the cerebral blood flow is blockaded during the surgical operation were measured. The electrodes were placed by the international 10-20 system. The brain dynamics are embedded in the neural networks. We analyzed the temporal change of the dynamics by examining the coupling weights in the networks which learned the EEG data for different periods. The developed system captures the temporal change in cerebral dynamics under an operation.