作者: Xiaopei Wu , Zhongfu Ye
DOI: 10.1007/11893295_9
关键词: Kurtosis 、 Speech recognition 、 Artificial neural network 、 Classifier (UML) 、 Electroencephalography 、 Computer science
摘要: In this paper, the kurtosis-based method for classification of mental activities is proposed. The EEG signals were recorded during imagination left or right hand movement. kurtosis and its dynamic properties with respect to time are analyzed. experiment results show that can reflect pattern changes different motor imageries. According analysis results, a based classifier movement designed. This achieves near 90% correct rate. As computationally less demanding also be estimated in on-line way, so new proposed paper has practicability application brain-computer interface.