运动意图诱发脑电预备响应信号的特征识别  

Feature Identification of EEG Preparatory ResponseSignals Evoked by Motor Intention

作　　者：付荣荣[1,2] 梁海峰 米瑞甫 FU Rong-rong;LIANG Hai-feng;MI Rui-fu(School of Electrical Engineering,Yanshan University,Qinhuangdao,Hebei 066004,China;Jiangxi new energy technology institute,Xinyu,Jiangxi 338004,China)

机构地区：[1]燕山大学电气工程学院,河北秦皇岛066004 [2]江西新能源科技职业学院,江西新余338004

出　　处：《计量学报》2023年第10期1597-1601,共5页Acta Metrologica Sinica

基　　金：国家自然科学基金面上项目(62073282);河北省中央引导地方科技发展资金项目(206Z0301G);河北省自然科学基金面上项目(F2022203092);河北省教育厅在读研究生创新能力培养资助项目(CXZZSS2021060)。

摘　　要：针对预备响应脑电信号(EEG)所包含的运动意图进行提取与识别,对于真实运动前准备电位进行解码。利用共空间模式(CSP)和极限学习机(ELM)解决大脑运动准备诱发特征识别。实验结果表明:该方法能够高效区分左右手真实运动前的准备电位,对脑机接口(BCI)大赛运动执行前的准备诱发脑电数据平均识别正确率可达85.7%。在解码问题上,预备电位与运动想象(MI)脑电信号相比,节省了意识产生到动作执行这一段时间,提高操作任务执行的响应效率,为实现基于运动意图的高效脑机交互提供理论依据和技术支持。The motor intention contained in the preparation response to electroencephalogram(EEG)signals is extracted and recognized,and the pre-movement EEG patterns is decoded.The experimental results show that using the common spatial pattern(CSP)and extreme learning machines(ELM)can efficiently distinguish the preparation potential of the left and right hands before real movement,and the average recognition accuracy rate of EEG data induced by the preparation before the execution of the brain computer interface(BCI)competition can reach 85.7%.On the decoding problem,compared with motor imagery(MI)EEG signals,the preparatory potential saves the time from consciousness generation to action execution,improves the response efficiency of operational task execution,and provides theoretical basis and technical support for efficient BCI based on motor intention.

关 键 词：计量学 脑电信号 准备电位 共空间模式 极限学习机 运动意图 特征识别 

分 类 号：TB99[一般工业技术—计量学] TB973[机械工程—测试计量技术及仪器]