中国组织工程研究

中国组织工程研究 ›› 2011, Vol. 15 ›› Issue (48): 9003-9006.doi: 10.3969/j.issn.1673-8225.2011.48.018

• 数字化骨科 digital orthopedics • 上一篇    下一篇

基于四类运动想象任务的脑电信号识别

李丽君，熊冬生，吴效明   

  1. 华南理工大学生物医学工程系，广东省广州市510006
  • 收稿日期:2011-06-14 修回日期:2011-07-20 出版日期:2011-11-26 发布日期:2011-11-26
  • 通讯作者: 熊冬生，副教授，华南理工大学生物医学工程系，广东省广州市 510006 btlxiong@scut.edu.cn
  • 作者简介:李丽君★，女，1986年生，河南省平顶山人，汉族，华南理工大学在读硕士，主要从事生物医学信号检测与处理研究。 lljkd@163.com
  • 基金资助:

    广东省科技计划项目(2009B030801004)，课题名称：面向社区家庭的医疗服务与检测仪器。

Classification of four-class imaginary movements in electroencephalogram

Li Li-jun, Xiong Dong-sheng, Wu Xiao-ming   

  1. Biomedical Engineering, South China University of Technology, Guangzhou  510006, Guangdong Province, China
  • Received:2011-06-14 Revised:2011-07-20 Online:2011-11-26 Published:2011-11-26
  • Contact: Xiong Dong-sheng, Associate professor, Biomedical Engineering, South China University of Technology, Guangzhou 510006, Guangdong Province, China btlxiong@scut.edu.cn
  • About author:Li Li-jun★, Studying for master’s degree, Biomedical Engineering, South China University of Technology, Guangzhou 510006, Guangdong Province, China lljkd@163.com
  • Supported by:

    Guangdong Science and Technology Program, No. 2009B030801004*

PDF

496

被引次数

10

摘要：

背景：脑-机接口是在大脑与外部设备之间建立的直接的交流通路，基于运动想象的脑-机接口研究已经从两类运动想象任务的识别发展到多类任务的识别。
目的：探寻准确有效的对多任务运动想象脑电信号进行特征提取及模式识别的方法。
方法：首先采用公共平均参考法减小多通道中各导联间的相关性，提高脑电信号的信噪比。并对公共空间模式算法进行扩展，采用“一对多”的策略，对4类任务的脑电信号进行特征提取，在模式识别过程中，采用基于决策树法的支持向量机进行分类。对于实验对象样本不充足，结合支持向量机和贝叶斯分类器，将分类结果中具有大概率的测试样本扩充到训练集，最后再次运用支持向量机进行分类。
结果与结论：最佳正确率达到92.78%，“一对多”的公共空间模式和基于决策树的支持向量机可以有效地进行多任务脑电信号识别，扩充样本可以提高分类正确率。

关键词: 脑-机接口, 事件相关去同步化/同步化, 公共空间模式, 支持向量机, 样本扩充

Abstract:

BACKGROUND: Brain-computer interface (BCI) has provided a direct communication pathway between brain and external devices. The BCI based on motor imagery research has developed from classification of the two types to classification of multi-class.
OBJECTIVE: To investigate accurate and effective method for extracting and classifying electroencephalogram (EEG) for multi-class imagery movement.
METHODS: First, the common average reference method was used to reduce the correlation among leads and improve the signal to noise ratio of EEG signal. The one versus the rest common spatial patterns (OVR-CSP) was used to extract the feature of EEG data, then use support vector machine of decision tree to classify the feature data. For the insufficient sample, combined with support vector machines and Bayesian classifier, expanded to the training set form the test set with a high probability of classification results, and finally re-classified by using support vector machines.
RESULTS AND CONCLUSION: The best accuracy was 92.78%. The OVR-CSP and the decision tree based on support vector machine could effectively identify multi-class EEG signal, and the expansion of the sample could improve classification accuracy.

中图分类号: