|
|
论文:2016,Vol:34,Issue(2):245-249 |
|
|
引用本文： |
|
|
谢松云, 刘畅, 吴悠, 张娟丽, 段绪. 基于多模式EEG的脑-机接口虚拟键鼠系统设计[J]. 西北工业大学学报 |
|
|
Xie Songyun, Liu Chang, Wu You, Zhang Juanli, Duan Xu. A Hybrid BCI (Brain-Computer Interface) Based on Multi-Mode EEG for Words Typing and Mouse Control[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于多模式EEG的脑-机接口虚拟键鼠系统设计 |
|
| 谢松云, 刘畅, 吴悠, 张娟丽, 段绪 |
|
| 西北工业大学 电子信息学院, 陕西 西安 710072 |
| 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。 |
| 关键词:
脑电信号
脑-机接口
虚拟键/鼠系统
机器学习
模式识别
|
|
| A Hybrid BCI (Brain-Computer Interface) Based on Multi-Mode EEG for Words Typing and Mouse Control |
|
| Xie Songyun, Liu Chang, Wu You, Zhang Juanli, Duan Xu |
|
| Department of Electronics and Engineering, Northwestern Polytechnical University, Xi'an, 710072, China |
| Abstract: |
| The existing BCI systems are mostly based on single EEG (Electroencephalogram) feature; thus, the functions of these systems are very limited. A hybrid BCI system based on multi-mode EEG for words typing and mouse control has been designed in this paper .This paper studies three commonly used EEG features in BCIs, namely, P300, alpha waves and SSVEP. Three experiments are designed using software E-Prime to evoke the features. According to the different evoking experiments and signal processing methods, SSVEP is used to design 6 flashing LED virtual mouse to move the mouse cursor and click left key and right-click, P300 is used to design a virtual keyboard of 6x6 character matrix to input the characters. The switch of the mouse and keyboard application is controlled by the enhancement of the alpha wave through closing the eyes. The real-time processing method of the three EEG features that include data segment, signal preprocessing, feature extraction and pattern recognition has also been studied; this study makes the average accuracies of the recognition of these three EEGs attain more than 85%. Test results and their analysis showed preliminarily that the BCI system designed in this paper can effectively implement the mouse and keyboard input tasks. |
| Key words:
back propagation
computer simulation
computer software
control
data acquisition
design
efficiency
feature extraction
field programmable gate arrays (FPGA)
light emitting diodes
MATLAB
matrix algebra
mean square error
neural networks
pattern recognition
real time systems
signal processing
support vector machines
BCI (Brain-Computer Interface)
EEG(electroencephalogram)
virtual keyboard
virtual mouse
|
|
| 收稿日期: 2015-10-12
修回日期:
|
| DOI: |
| 基金项目: 国家自然科学基金(61273250)、陕西省工业攻关项目(2015GY003)及西北工业大学研究生创业种子基金(Z2015112)资助 |
| 通讯作者:
Email： |
| 作者简介: 谢松云(1968-) ,女,西北工业大学教授、博士生导师,主要从事神经信息处理与脑认知及动态目标识别与跟踪研究。
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 谢松云 在本刊中的所有文章 |
| 刘畅 在本刊中的所有文章 |
| 吴悠 在本刊中的所有文章 |
| 张娟丽 在本刊中的所有文章 |
| 段绪 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Wang Y, Chen S, Lin C. An EEG-Based Brain-Computer Interface for Dual Task Driving Detection[J]. Neurocomputing, 2014, 129:85-93
[2] Farwell L A, Donchin E. Talking off the Top of Your Head:Toward a Mental Prosthesis Utilizing Event-Related brain Potentials[J]. Electroencephalography and Clinical Neurophysiology, 1988, 70(6):510-523
[3] Marchetti M, Priftis K. Effectiveness of the P3-Speller in Brain-Computer Interfaces for Amyotrophic Lateral Sclerosis Patients:A Systematic Review and Meta-Analysis[J]. Frontiers in Neuroengineering, 2014, 7:12-14
[4] Long J, Li Y, Yu T, et al. Target Selection with Hybrid Feature for BCI-Based 2-D Cursor Control[J]. IEEE Transactions on Biomedical Engineering, 2012, 59(1):132-140
[5] Huang G, Zhu Q, Siew C. Extreme Learning Machine:Theory and Applications[J]. Neurocomputing. 2006, 70(1/2/3):489-501
[6] Lin Z, Zhang C, Wu W, et al. Frequency Recognition Based on Canonical Correlation Analysis for SSVEP-Based BCIs[J]. IEEE Trans on Biomedical Engineering, 2007, 54(62):1172-1176 |
|
|
|
相关文献: |
|
|
1．赵金, 谢松云, 郭正, 于海勋.基于HOC-SVM的运动状态下脑电的特征提取与分类[J]. 西北工业大学学报, 2012,30(3): 435-439 |
|
|
|
|
|
|
