计算机应用 ›› 2014, Vol. 34 ›› Issue (3): 771-774.DOI: 10.11772/j.issn.1001-9081.2014.03.0771

• 人工智能 • 上一篇    下一篇

模拟阅读脑-机接口异步化研究

曹巧玲1,2,官金安1,2   

  1. 1. 中南民族大学 认知科学国家民委重点实验室，武汉430074
    2. 中南民族大学 生物医学工程学院，武汉430074
  • 收稿日期:2013-09-22 修回日期:2013-11-13 发布日期:2014-04-01 出版日期:2014-03-01
  • 通讯作者: 曹巧玲
  • 作者简介:曹巧玲(1986-)，女，河北邯郸人，硕士研究生，主要研究方向：生物信号处理、模式识别、脑-计算机接口；官金安(1965-)，男，湖北武汉人，教授，博士，主要研究方向：生物信息处理、模式识别。
  • 基金资助:

    国家自然科学基金资助项目;中央高校基本科研业务费资助项目;武汉市科技计划项目

Research of asynchronous reading imitating of brain-computer interface

CAO Qiaoling1,2,GUAN Jinan1,2   

  1. 1. College of Biomedical Engineering, South-Central University for Nationalities, Wuhan Hubei 430074, China;
    2. Key Laboratory of Cognitive Science of State Ethnic Affairs Commission, South-Central University for Nationalities, Wuhan Hubei 430074, China
  • Received:2013-09-22 Revised:2013-11-13 Online:2014-04-01 Published:2014-03-01
  • Contact: CAO Qiaoling
  • Supported by:

    National Natural Science Foundation

PDF

摘要：

“模拟阅读”脑机接口(BCI)工作在同步模式，而实际中使用者希望能在“工作/非工作”状态间自由切换，即异步化，针对该问题提出了利用闭眼固定时间的脑电信号作为两种状态间转换开关的方法。首先设计了实验方案；然后对采集的脑电图(EEG)信号分别在时域和频域进行特征提取，对时域特征利用支持向量机(SVM)和K-means分类器进行分类，对频域特征用SVM分类。时域最高识别率分别为91.25%和89.17%，平均分类所需时间分别为1.89s和0.11s，频域最高识别率和平均识别率分别为86.25%和81.875%。实验结果表明该实验模式能实现两种状态自由切换的目的。

关键词: 异步, 脑机接口, 支持向量机, 特征提取, 模式识别

Abstract:

Reading imitating of Brain-Computer Interface (BCI) works on synchronous mode, but in practice users want to switch between "work" state and "idle" state freely, namely asynchrony. Therefore, a closing-eyes fixed time as the switch between the two states was proposed to solve the problem. Firstly, an experimental scheme was put forward, then the features of Electroencephalography (EEG) signal were extracted in time and frequency domains respectively, features of time domain were classified by Support Vector Machine (SVM) and the K-means algorithm, and features of frequency domain were classified by SVM. The highest recognition rates of time domain were 95% and 89.17%, the average time needed for classification were 1.89s and 0.11s respectively. The highest and the average recognition of frequency domain rate were 86.25% and 81.875% respectively. The experimental results show that this scheme can achieve the goal of switching the two states freely.

Key words: asynchrony, Brain-Computer Interface (BCI), Support Vector Machine (SVM), feature extraction, pattern recognition

中图分类号: 

版权所有 © 2021 四川计算机应用杂志社有限公司
蜀ICP备 05010208 号-3　新出网证(川)字026号
技术支持：北京玛格泰克科技发展有限公司
访问总数：
今日访问：