《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (10): 3297-3308.DOI: 10.11772/j.issn.1001-9081.2022101471

• 前沿与综合应用 • 上一篇    

基于脑电信号的认知功能障碍识别与分类进展综述

张军鹏1, 施玉杰1, 蒋睿1, 董静静2, 邱昌建3()   

  1. 1.四川大学 电气工程学院,成都 610065
    2.中国人民解放军海军特色医学中心 空勤科,上海 200052
    3.四川大学华西医院 心理卫生中心,成都 610041
  • 收稿日期:2022-10-08 修回日期:2023-01-23 接受日期:2023-02-03 发布日期:2023-04-12 出版日期:2023-10-10
  • 通讯作者: 邱昌建
  • 作者简介:张军鹏(1975—),男,陕西韩城人,副教授,博士,主要研究方向:基于脑电(EEG)的认知障碍评估、脑电图个体识别、脑电图辅助精神障碍诊断
    施玉杰(1998—),女,四川泸州人,硕士研究生,主要研究方向:EGG数据分析
    蒋睿(1998—),男,江西南康人,硕士研究生,主要研究方向:脑机接口、目标跟踪
    董静静(1984—),女,陕西大荔人,副主任医师,博士,主要研究方向:特勤人员诊疗、职业性防治及认知评估;
  • 基金资助:
    国家自然科学基金数学天元基金重点专项(12126606);四川省科技厅重点研发项目(2022YFS0345)

Review on advances in recognition and classification of cognitive impairment based on EEG signals

Junpeng ZHANG1, Yujie SHI1, Rui JANG1, Jingjing DONG2, Changjian QIU3()   

  1. 1.College of Electrical Engineering,Sichuan University,Chengdu Sichuan 610065,China
    2.Air Service Department,Naval Medical Center of the People’s Liberation Army,Shanghai 200052,China
    3.Mental Health Center,West China Hospital of Sichuan University,Chengdu Sichuan 610041,China
  • Received:2022-10-08 Revised:2023-01-23 Accepted:2023-02-03 Online:2023-04-12 Published:2023-10-10
  • Contact: Changjian QIU
  • About author:ZHANG Junpeng, born in 1975, Ph. D., associate professor. His research interests include ElectroEncephaloGraphy (EEG) based cognitive impairment assessment, electroencephalogram based individual recognition, electroencephalogram assisted diagnosis of mental disorders.
    SHI Yujie, born in 1998, M. S. candidate. Her research interests include EEG data analysis.
    DONG Jingjing, born in 1984, Ph. D., deputy chief physician. Her research interests include diagnosis and treatment of secret service personnel, occupational prevention and treatment as well as cognitive assessment.
    First author contact:JIANG Rui, born in 1998, M. S. candidate. His research interests include brain-computer interface, target tracking.
  • Supported by:
    Key Project of Mathematics Tianyuan Foundation of National Natural Science Foundation of China(12126606);Key Research and Development Project of Department of Science and Technology of Sichuan Province(2022YFS0345)

摘要:

认知功能障碍的早期检测和及时干预对减缓病情发展至关重要。脑电(EEG)信号具有时间分辨率高、易采集等优点,目前已成为研究认知疾病生物标志物的重要工具。相较于传统的生物标志物识别方法,机器学习方法对于基于EEG信号的认知功能障碍的识别分类的准确率更高,稳定性更好。对于近三年基于EEG信号的认知功能障碍识别分类的相关研究,首先,从认知功能障碍识别分类中常用的时域、频域、时频域结合、非线性动力学、功能连接和脑网络这五类EEG特征出发,寻找更具代表性的EEG特征;其次,总结目前使用较多的支持向量机(SVM)、线性判别分析(LDA)、K-近邻(KNN)和人工神经网络(ANN)等机器学习和深度学习分类方法和这些方法的性能;最后,分析各类研究中目前存在的问题,并展望此领域未来的研究方向,从而为后续基于EEG信号的认知功能障碍识别分类的研究提供参考。

关键词: 脑电信号, 机器学习, 认知功能障碍, 深度学习, 特征提取

Abstract:

Early detection and timely intervention of cognitive impairment are crucial to slow down the progress of the disease. The ElectroEncephaloGraphy (EEG) signal has become an important tool for the investigation of biomarkers of cognitive diseases due to its high temporal resolution and easy acquisition. Compared with the traditional biomarker recognition method, the machine learning method has higher accuracy and better stability for the recognition and classification of cognitive impairment based on EEG signals. Aiming at the relevant research literature on the recognition and classification of cognitive impairment based on EEG signals in the past three years, firstly, from the perspectives of five categories of EEG features commonly used in the recognition and classification of cognitive impairment, including time domain, frequency domain, combination of time and frequency domains, nonlinear dynamics, functional connectivity and brain network, more representative EEG features were found. Then, the currently commonly used classification methods based on machine learning and deep learning, such as Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), K-Nearest Neighbor (KNN) and Artificial Neural Network (ANN), as well as their performance were summarized. Finally, the current problems in different kinds of studies were analyzed, and the future research directions in this field were prospected, thereby providing reference for the follow-up research on the recognition and classification of cognitive impairment based on EEG signals.

Key words: ElectroEncephaloGraphy (EEG) signal, machine learning, cognitive impairment, deep learning, feature extraction

中图分类号: