摘要
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解析右臂运动方向.
This study aimed to study of forearm movement direction based on non-invasive brain machine interface technology. An autonomic movement experimental 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 withess 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.
引文
[1]李明爱,田晓霞,孙炎珺.基于改进GHSOM的运动想象脑电信号自适应识别方法[J].仪器仪表学报,2015,36(5):1064-1071.
[2] ONOSE G,GROZEA C,ANGHELESCU A,et al. On the feasibility of using motor imagery EEG-based braincomputer interface in chronic tetraplegics for assistive robotic arm control:a clinical test and long-term posttrial follow-up[J]. Spinal cord,2013,50(8):599-608.
[3] WANG D,MIAO D,BLOHM G,et al. Multi-Class motor imagery EEG decoding for brain-computer interfaces[J]. Frontiers in neuroscience,2012,6:151-158.
[4] YANG L,LEUNG H,PLANK M,et al. EEG activity during movement planning encodes upcoming peak speed and acceleration and improves the accuracy in predicting hand kinematics[J]. IEEE journal of biomedical and health informatics, 2015, 19(1):22-28.
[5] EISENBERG M,SHMUELOF L,VAADIA E,et al.Functional organization of human motor cortex:directional selectivity for movement[J]. Journal of neuroscience,2010,30(26):8897-8905.
[6] LACHAUX J P,AXMACHER N,MORMANN F,et al. High-frequency neural activity and human cognition:past,present and possible future of intracranial EEG research[J]. Progress in neurobiology,2012,98(3):279-301.
[7] MECKES M P,SEPULVEDA F,CONWAY B A. 1st order class separability using EEG-based features for classification of wrist movements with direction selectivity[C]∥26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. San Franciso,CA:IEEE,2004:4377-4379.
[8] WANG Y,MAKEIG S. Predicting intended movement direction using EEG from human posterior parietal cortex[C]. San Diego:Lecture Notes In Artificial Intelligence,2009.
[9] KHAN M J,HONG M J,HONG K S,et al. Decoding of four movement directions using hybrid NIRS-EEG brain-computer interface[J]. Frontiers in human neuroscience,2014,8(5):412-432.
[10] TRACY W,ARIAN M,FRANCESCO M,et al. Nicotine effects on brain function during a visual oddball task:a comparison between conventional and EEG-informed FMRI analysis[J]. Journal of cognitive neuroscience,2012,8(24):1682-1694.
[11] GROSBRAS M H,BEATON S,EICKHOFF S B.Brain regions involved in human movement perception:A quantitative voxel-based meta-analysis[J]. Human brain mapping,2012,33(2):431-454.
[12] PUUYA A,STEFAND C,LUCA A. How capable is non-invasive EEG data of predicting the next movement? A mini review[J]. Frontiers in human neuroscience,2013,7(124):124.
[13]张震,张英杰.基于支持向量机与Hamming距离的虹膜识别方法[J].郑州大学学报(工学版),2015,36(363):25-29.
[14]李凌均,陈超,韩捷,等.全矢量支持向量机回归频谱预测方法[J].郑州大学学报(工学版),2016,37(3):78-82.
[15]曹玉珍,张庆学.基于运动相关脑电特征的手运动方向识别[J].天津大学学报,2014(9):836-841.