Abstract: One of the most important things in diagnosis of epilepsy is to find the exact location of the epileptogenic point. EEG is a tool commonly used at epilepsy diagnosis centers for diagnosis purposes. . In this paper, the modified particle swarm optimization (MPSO) method used to solve the EEG source localization problem. The attempt has been done here to estimate the brain activity on the basis of spectrum analysis. EEG classification can be very useful in predicting the action or the intention of action performed on the basis of EEG which leads to more development in brain computer interface. The brain waves a, ß, ?, d, ? were extracted using frequency filtering and estimating the level of disease is done by the clinical experts based on the amplitudes of the brain waves. The EEG data has been referred from a website MIT-BIH and the mathematical tool for EEG analysis called EEGLAB has been used to perform work in this paper.

Keywords: Electroencephalogram (EEG), particle swarm optimization (PSO).