A Joint Algorithm for Electroencephalographic Signals in Complex Scenes

Based on the Fast Fourier transform and Support Vector Machine joint algorithm, this paper proposes a new EEG signal processing joint algorithm in the complex scene for more than five kinds of EEG signals. This new algorithm improves the accuracy and comprehensive efficiency of EEG signal processing. Firstly,the EEG data are normalized,then Fast Fourier transform and Principal Component Analysis are applied for feature extraction,the weighted k-nearest neighbor classification algorithm is finally employed to classify the EEG signals of watching digits 0~9. The result demonstrates that accuracy and comprehensive efficiency of the new joint algorithm are 84% and 87% respectively, which indicates that the proposed joint algorithm can be applied in the complex scene for mulit-categories EEG signal processing.