Classifying Mental Tasks Using Local Mean Decomposition of Electroencephalogram and Support Vector Machine

摘要：

　　We present a new combination classification algorithm and test it on the EEG of right and left motor imagery experiment.First,the original EEGs signals are decomposed by Local Mean Decomposition (LMD) and then determine that the first three PFs include the main mental task features.After determining the optimal kernel parameters for support vector machine (SVM),the energy values of the first three PFs of the EEG signals from three electrodes were extracted as the input vectors of SVM.The outputs of SVM were the classification results for different mental task EEG signals.Result shows that mean accuracy of the proposed algorithm is 92.25%,and the best accuracy is 95.00%,which is much better than the present traditional algorithms.

关键词： brain computer interface motor imagery electroencephalogram local mean decomposition support vector machine

作者: Liyu Huang Jie Niu Jianing Zheng Yingju Du

作者单位: School of Life Sciences and Technology, Xidian University, Xi-an, China

会议类型: 国际会议

会议名称: 2nd International Conference on Materials Engineering and Automatic Control (第二届材料工程与自动化控制国际会议)(ICMEAC2013)

会议地点: 济南

会议语种:英文

页码: 973-976

在线出版日期: 2013-05-18（万方平台首次上网日期，不代表论文的发表时间）