脑电信号中独立分量特征提取与脑力负荷分类
DOI:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

G202

基金项目:

国家自然科学基金(XLYC1802092)第一作者:曲洪权(1973-),男,汉,黑龙江青冈,博士,教授。研究方向:数据科学。qhqphd@ncut.edu.cn*通信作者:庞丽萍(1973-),女,汉,黑龙江海林,博士,教授。研究方向:人机与环境工程。pangliping@buaa.edu.cn (1. Information College, North China University of Technology, Beijing 100144, China; 2. College of Aviation Science and Engineering, Beihang University, Beijing 100191, China),国家自然科学基金项目(面上项目,重点项目,重大项目)


Extraction of Independent Component Features in EEG Signals and Classification of Mental Workload
Author:
Affiliation:

Fund Project:

The National Natural Science Foundation of China (General Program, Key Program, Major Research Plan)

  • 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:

    脑力负荷过高会造成作业绩效下降和人因事故,过低则会造成人力资源浪费,所以研究操作人员脑力负荷状态非常有意义。现有脑力负荷分类方法利用脑电(electroencephalogram, EEG)信号特征进行分类,准确率较低。所以,本文针对视觉和操作类脑力负荷提出一种基于脑电独立分量特征的分类方法,该方法采用独立分量分析(Independent Component Analysis, ICA)对脑电信号进行分离,直接对得到的独立分量提取四种不同频段的能量特征,最后将特征作为支持向量机(Support Vector Machine, SVM)的输入,对脑力负荷进行分类。由于直接使用脑电独立分量特征,所以分类精度高于现有方法,平均分类精度提高29.14%。本文还进一步发现脑电独立分量中存在的眼电伪迹对分类结果没有明显影响。本文提出的方法可以实现快速、准确、自动的脑力负荷分类。

    Abstract:

    Excessive mental workload will reduce work efficiency, but low mental workload will cause a waste of human resources. It is very significant to study the mental workload status of operators. The existing mental workload classification method use the features of electroencephalogram(EEG) signals, and the accuracy is low. So, this paper proposes a mental workload classification method based on features of EEG independent components for vision and operation. This method is implemented by the following four steps: filtering, obtaining EEG independent components, extracting independent components energy features and classifying. Since this method directly uses independent components energy features for feature extraction. Compared with the existing solution, the proposed method can obtain better classification results, the average accuracy is increased by 29.14%. Further, this paper found that the Ocular Artifacts have no significant effect on the classification of mental workload based on features of EEG independent components. The presented method might provide a way to realize a fast, accurate and automatic mental workload classification.

    参考文献
    相似文献
    引证文献
引用本文

曲洪权,单一平,刘欲哲,等. 脑电信号中独立分量特征提取与脑力负荷分类[J]. 科学技术与工程, 2020, 20(28): 11499-11504.
QU Hong-quan, SHAN Yi-ping, LIU Yu-zhe, et al. Extraction of Independent Component Features in EEG Signals and Classification of Mental Workload[J]. Science Technology and Engineering,2020,20(28):11499-11504.

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:2020-02-23
  • 最后修改日期:2020-06-17
  • 录用日期:2020-04-14
  • 在线发布日期: 2020-11-03
  • 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