吉首大学学报(自然科学版) ›› 2022, Vol. 43 ›› Issue (1): 31-37.DOI: 10.13438/j.cnki.jdzk.2022.01.006

• 通信与计算机 • 上一篇    下一篇

基于视觉和操作类脑电信号的脑力负荷分类

曲洪权,刘欲哲,庞丽萍,单一平   

  1. (1.北方工业大学信息学院,北京 100144;2.北京航空航天大学航空科学与工程学院,北京 100191)
  • 出版日期:2022-01-25 发布日期:2022-05-16
  • 通讯作者: 庞丽萍(1973—),女,黑龙江海林人,北京航空航天大学航空科学与工程学院教授,博士,主要从事人机与环境工程研究.
  • 作者简介:曲洪权(1973—),男,黑龙江青冈人,北方工业大学信息学院教授,博士,主要从事数据科学技术研究
  • 基金资助:
    国家自然科学基金资助项目(XLYC1802092)

Mental Workload Classification Based on Visual and Operational EEG Signals

QU Hongquan,LIU Yuzhe,PANG Liping,SHAN Yiping   

  1. (1.School of Information Science and Technology,North China University of Technology,Beijing 100144,China;2.School of Aeronautic Science and Engineering,Beihang University,Beijing 100191,China)
  • Online:2022-01-25 Published:2022-05-16

摘要:针对视觉和操作类任务,提出了一种基于脑电独立分量特征的脑力负荷分类方法.利用独立分量分析法从混合脑电信号中分解获得脑电信号的独立分量,再提取脑电独立分量的4个不同频段的能量特征,并对能量特征进行分类.基于脑电信号特征和脑电独立分量特征分别进行了脑力负荷分类实验,得到平均分类准确率分别为60.52%,86.14%,后者比前者提高了42.33%.

关键词: 脑力负荷, 独立分量, 支持向量机, 脑电信号

Abstract: A classification method is proposed based on EEG independent component features for the mental workload classification of visual and operational task.First,the independent component analysis method is used to decompose the independent components of the EEG signals from the mixed EEG signals;then the energy features of the four different frequency bands of the EEG independent components are extracted;and the energy features are classified.The mental workload classification experiments were carried out based on EEG signal features and EEG independent component features respectively,and the classification accuracy was 60.52% and 86.14%,with the latter increased by 42.33%.

Key words: mental workload, independent component, support vector machine, EEG signal

公众号 电子书橱 超星期刊 手机浏览 在线QQ