Classified research on epilepsy electroencephalogram of RBF neutral network based on particle swarm

Epilepsy is a kind of common diseases and frequently-occurring diseases damaging human health, and has a big impact on patient's body and mental health due to its attack at any place and any time, which has been the valued neutral network disease with high incidence in many countries. This paper proposes the mixed feature extraction to extract the feature by mixture of timedomain method and nonlinear analysis method, and then make optimization selection by applying particle swarm optimization, and finally train the epilepsy classifier by utilizing the optimized features through the RBF neutral network algorithm. In the experiment, the accuracies of two-classification problems and three-classification problems respectively reach 99.% and 98.1%, The results of cross-over experiment for many times show that, the method is of effectiveness in the classified feature extraction aiming at epilepsy brain wave.