Extracting Single Trial Visual Evoked Potentials Using Iterative Generalized Eigen Value Decomposition

Abstract

The activity generated in the brain in response to external stimulations which is named the evoked potential (EP) is typically buried in the background EEG. Because of the low signal to noise ratio of EPs, it is difficult to record single trial evoked potentials. The traditional technique which is based on ensemble averaging destroys the dynamic information of single trials. In this paper, a new method has been proposed based on generalized eigen value decomposition to extract single trial EPs from single channel EEG recordings. The extraction of the N75-P100-N135 complex in simulated and actual visual evoked potentials is mainly taken under consideration. To illustrate the effectiveness of the proposed algorithm, it is compared with the iterative ICA method.