摘要
脑机融合控制的典型控制信号源是脑电,然而脑电信号具有低信噪比、低空间分辨率、极易受到伪迹的污染,这给该类控制系统中脑电信号的处理带来了巨大的挑战.针对脑电中存在的各种伪迹,分析总结了各种伪迹处理方法并比较它们的优缺点,最后针对脑机融合控制的实用化需求,指出该领域脑电伪迹处理方法未来的研究方向——在线实时、自适应/机器学习、免伪迹参考、少通道/单通道、优化融合多种有效方法综合去除EEG中的主要伪迹.
Electroencephalogram(EEG)is the typical control signal source of Brain-Machine Integration Control(BMIC).However,EEG signals low signal-to-noise ratio,low spatial resolution and susceptibility to artifact contamination poses great challenge to deal with EEG signal in this kind of control system.In this paper,aiming at various artifacts existing in EEG,the authors analyzed and summarizes the methods of EEG artifacts processing and compared their advantages and disadvantages.Finally,in view of the practical needs of BMIC,the future research direction of EEG artifacts processing methods in this field was we pointed out——online,real time,adaptive/machine learning,without reference channel,few/single channel,combined algorithm to remove artifacts in EEG signal.
作者
熊馨
杨秋红
周建华
徐保磊
李永程
尹旭贤
伏云发
XIONG Xin;YANG Qiuhong;ZHOU Jianhua;XU Baolei;LI Yongcheng;YIN Xuxian;FU Yunfa(Faculty of Automation and Information Engineering,Kunming University of Science and Technology,Kunming 650500,China;State Key Laboratory of Robotics,Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China)
出处
《昆明理工大学学报（自然科学版）》
北大核心
2021年第3期56-70,共15页
Journal of Kunming University of Science and Technology(Natural Science)
基金
国家自然科学基金项目(82060329,81470084,81771926,61463024,61763022)
云南省教育厅基金项目(2020J0052)。
关键词
脑电
伪迹
脑机融合控制
独立成分分析
共同空间模式
Electroencephalogram(EEG)
artifact
Brain-Machine Integration Control(BMIC)
Independent Component Analysis(ICA)
Common Spatial Pattern(CSP)
