EEG Signal Recognition and Its Application in the Control of Mechanical Arm
LIU Gang
LI Xiaoou
Abstract：The traditional time-frequency analysis method uses little spatial information and the obtained classification accuracy is very low.To solve this problem,firstly,the common spatial patterns algorithm was applied to extract the feature of EEG,and then the feature was classified by the support vector machine,finally,the classification results was transmitted to the control system of mechani-cal arm by the serial port.The experimental results show that the CSP algorithm can be applied effectively to extract the feature of col-lected EEG signal based on motor imagery,and this algorithm also can effectively overcome the disadvantage of the traditional time-frequency analysis method based on few spatial information.The average classification accuracy is 86.1%.
Keywords：Common spatial patternSupport vector machineSerial portMotor imageryMechanical arm
Publication Date：2016-01-01
Online Publishing Date：2026-09-11(First online date of this platform, not the publication date of the document)
Pages：6( 284-289 )