BCI establishs a direct communication and control channel between human and computer or other electronic device.P300-based speller paradigm is an common method for BCI.Genetic algorithm and support vector machines(SVM) are used for classification of EEG.Principal Component Analysis(PCA) and Fisher discriminant criterion are emloied to implement the feature extraction.After using PCA to reduce dimension,Fisher discriminant Criterion can further extract effective features and improve the accuracy of classfication.SVM is emploied to classify electroencephalogram.