基于稳态视觉诱发电位在线脑机接口研究.pdf

154 2017 ，53（3 ） Computer Engineering and Applications 计算机工程与应用 基于稳态视觉诱发电位的在线脑机接口研究 董恩增，郭光瑞，陈 超 DONG Enzeng, GUO Guangrui, CHEN Chao 天津理工大学 自动化学院 复杂系统控制理论及应用重点实验室，天津 300384 Complex System Control Theory and Application Key Laboratory, School of Electrical Engineering, Tianjin University of Technology, Tianjin 300384, China DONG Enzeng, GUO Guangrui, CHEN Chao. Research of steady-state visual evoked potential based online brain- computer interface. Computer Engineering and Applications, 2017, 53 （3 ）：154-159. Abstract: The most brain-computer interface systems perform badly in resisting the noise and seem complicated for oper- ation. This paper proposes a steady-state visual evoked potential based online brain computer interface system employing the portable EEG collecting device Emotiv EPOC and the NAO robot, which has a good ability of anti-noise. This system utilizes canonical correlation analysis to detect the frequency of steady-state visual evoked potential. In online experiment, the NAO robot is controlled by the EEG signals collected from Emotiv EPOC, the average classification accuracy rate of 4 types of tasks achieves 87. 50%. The online experiment doesn ’t suffer from the surrounding noise, which shows the sys- tem has a good ability to resist the noise. Key words: steady-state visual evoked potential; brain computer interface; Emotiv EPOC; NAO robot; canonical correla- tion analysis 摘 要：针对脑机接口中存在的抗噪声能力差、操作复杂的问题，利用便携式脑电采集设备Emotiv EPOC 以及NAO 机器人，搭建了一个抗噪能力较好的稳态视觉诱发在线脑机接口系统。该系统采用典型相关性分析进行稳态视觉 诱发电位的频率识别。在线实验中受试者通过Emotiv 控制NAO 机器人运动，四类任务的准确率达到87.50% 。在线 实验没有回避周围的噪声，表明该系统具有较好的抗噪能力。 关键词：稳态视觉诱发电位；脑机接口；Emotiv EPOC ；NAO 机器人；典型相关性分析 文献标志码：A 中图分类号：TP391 doi ：10.3778/j.issn. 1002-8331.1504-0257 1 引言 于SSVEP 的脑机接口越来越受到研究者的重视，该类 脑机接口（Brain-Computer Interface ，BCI ）可以识 脑机接口具有信噪比高、通讯速率快、