微弱脑信号专注度特征提取与识别
DOI:
作者:
作者单位:

同济大学信息与通信工程系 上海201804,同济大学信息与通信工程系 上海201804

作者简介:

通讯作者:

中图分类号:

TN911.7

基金项目:

国家自然科学基金;国家自然科学基金项目(61201225),上海市浦江人才计划资助(13PJD030);上海市科学技术委员会的资助,资助课题编号为12ZR1450800;同济大学青年优秀人才培养行动计划资助(2013KJ007);中央高校基本科研业务费专项资金资助(20140767); 上海市教育委员会和上海市教育发展基金会“晨光计划”资助(13CG18)。


The Feature Extraction and Recognition of Weak Attention EEG Signals
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    目前基于脑机接口的脑电信号研究得到越来越广泛的关注,然而传统脑电信号采集需要使用电极帽并涂抹胶泥膏而不被大多数用户所接受。因此,本文将研究使用无需涂抹胶泥膏的独立电极采集脑电信号,然而使用独立电极采集脑电信号容易出现干扰大、信号不稳定等缺陷。为了快速有效提取脑电信号特征并克服独立电极采集脑电信号的缺陷,本文将采用低通滤波方法进行工频干扰的滤除,利用独立成分分析(ICA)实现脑电信号中的眼电伪迹分离,并在此基础上通过设置水平眼电和垂直眼电阈值以及各个独立成分在脑部位置的空间分布特性实现眼电伪迹的识别。最后,分别利用β波能量以及样本熵来衡量人脑专注度的高低,仿真结果表明两者均与专注度成正相关,实验以Neuroscan专注度为基准,将两种算法分别与其进行对照。此外,样本熵与Neuroscan算法的相关度比β波能量法提高了26%,说明样本熵专注度提取算法更能精确跟踪人脑注意力的变化,对脑电信号专注度的衡量与实际更加吻合。

    Abstract:

    The study of electroencephalogram signals based on brain-computer interface gets more and more attention, but the acquisition of the electroencephalogram signals by using traditional electrode cap cannot be accepted by most users because of the use of electrode cap and cement. So we acquire electroencephalogram signals by using independent electrode. However using independent electrode to acquire electroencephalogram signals makes big interference, and the signal is not stable. In order to quickly and efficiently extract brain signal characteristics, low pass filtering is used to remove power frequency interference, and we use independent component analysis (ICA) to realize the separation of eye artifact and electroencephalogram signals. Then we achieve the identification of eye artifact through the horizontal eye electrical threshold settings, vertical eye electrical threshold settings and spatial distribution characteristics of individual components in the location of the brain. Then we can use the energy of β-band and sample entropy to measure the concentration in this paper. Simulation results show that both the energy and entropy are positively related with the concentration. Experimental measurement is on the basis of patented algorithm of Neuroscan. Compare the two algorithms with the algorithm of Neuroscan respectively, the results show that the correlation coefficient between the entropy and the value of attention of Neuroscan increases 26% comparing with the correlation coefficient between the energy and the value of attention of Neuroscan, which indicates that sample entropy can accurately track the change of attention and has a better effect in the feature extraction.

    参考文献
    相似文献
    引证文献
引用本文

郇小宁,黄新林. 微弱脑信号专注度特征提取与识别[J]. 科学技术与工程, 2015, 15(13): .
Xiaoning Huan and. The Feature Extraction and Recognition of Weak Attention EEG Signals[J]. Science Technology and Engineering,2015,15(13).

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2014-12-28
  • 最后修改日期:2015-04-13
  • 录用日期:2015-02-05
  • 在线发布日期: 2015-05-05
  • 出版日期:
×
律回春渐,新元肇启|《科学技术与工程》编辑部恭祝新岁!
亟待确认版面费归属稿件,敬请作者关注