基于脑电图的三分类前臂运动方向解析
Three Classification Forearm Movement Direction Information Decoding Based on EEG

针对基于非侵入式脑机接口技术的右臂运动方向的判别问题，采用自主运动实验范式，将右臂自主运动脑电图（EEG）划分为规划和执行两阶段分别进行分析，并根据复杂神经活动的特点，采用WPD（小波包）与CSP（共空间模式）融合的方法进行EEG特征提取，进一步利用SVM（支持向量机）对多维持特征进行分类。实验得到三分类（左、右和静止）平均85%的分类正确率。实验结果表明，该组合方法能够较好分析右臂运动方向。
This study aimed to study of forearm movement direction based on non-invasive brain machine interface technology. An autonomic movement expermental paradigm and was desighed, the EEG (electroencephalograph) signal of two stages of autonomous motion planning and execution was anaused. Method that combines the WPD (wavelet packet decomposition) and CSP (common spatial patterns) was used to extract characteristics. The SVM (support vector machine) was further used to classify multidimensional characteristics. Experiment on subjects withness the average 80% accuracy of three classifications (left, right and static) .The results showed that the combined method could effectively resolve direction information of EEG.