基于多模式EEG的脑-机接口虚拟键鼠系统设计

发布时间：2018-05-26 12:20

本文选题：脑电信号 + 脑-机接口　；参考：《西北工业大学学报》2016年02期

【摘要】：现有的脑-机接口系统大都只基于单模式的脑电特征,系统能实现的功能非常有限,从而制约了脑-机接口系统的应用。采用基于多种模式脑电信号(electroencephalogram,EEG)的脑-机接口技术来实现虚拟键鼠系统,使得被试可以利用自身的脑电信号控制鼠标和键盘的操作。研究了脑-机接口中常用的3种脑电信号,分别是P300波、alpha波以及稳态视觉诱发电位(steady state visual evoked potential,SSVEP),通过设计实验成功的诱发出了被试相应的特征脑电信号。利用SSVEP的脑电特征设计6频率LED闪烁刺激的虚拟鼠标系统,实现控制鼠标光标移动、单击左键和单击右键的任务;利用P300波的脑电特征设计6×6的字符矩阵虚拟键盘系统,实现字符输入的任务;利用被试自主闭眼增强alpha波的脑电特征,实现鼠标和键盘应用切换的任务。研究了适宜这3种脑电特征的最佳测量电极组合及模式识别算法,使得对3种脑电信号的识别正确率均达到了85%以上。测试结果显示,文中设计的基于多模式EEG的脑-机接口虚拟键鼠系统能有效地实现鼠标控制以及键盘输入的任务。
[Abstract]:Most of the existing brain-computer interface systems are based on single-mode EEG features, and the functions of the system are very limited, which restricts the application of brain-computer interface system. The brain-computer interface technology based on multi-mode EEG electroencephalogrammogram (EGG) is used to realize the virtual mouse keying system, which enables the subjects to control the mouse and keyboard operation by using their own EEG signals. Three kinds of EEG signals commonly used in brain-computer interface, namely P300 wave alpha wave and steady-state visual evoked potential (SVEP), were studied. The corresponding characteristic EEG signals were sent out by designing experiments successfully. A virtual mouse system with 6 frequency LED flickering stimuli is designed by using the EEG features of SSVEP. The task of controlling mouse cursor movement, clicking left button and right click is realized, and the 6 脳 6 character matrix virtual keyboard system is designed by using P300 wave EEG feature. The task of character input is realized, and the task of mouse and keyboard application switching is realized by using the self-closing eyes of the subjects to enhance the EEG characteristics of the alpha wave. The optimal measurement electrode combination and pattern recognition algorithm suitable for these three EEG features are studied. The recognition accuracy of the three EEG signals is more than 85%. The test results show that the designed brain-computer interface virtual keyboard and mouse system based on multi-mode EEG can effectively realize the task of mouse control and keyboard input.
【作者单位】：西北工业大学电子信息学院;
【基金】：国家自然科学基金(61273250) 陕西省工业攻关项目(2015GY003) 西北工业大学研究生创业种子基金(Z2015112)资助
【分类号】：R338;TN911.7

【相似文献】