Bilinear neural network with 3-D attention for brain decoding of motor imagery movements from the human EEG

doi:10.1007/s11571-020-09649-8

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进机器人控制团队

	Bilinear neural network with 3-D attention for brain decoding of motor imagery movements from the human EEG
	Fan, Chen-Chen 1,3; Yang, Hongjun 1; Hou, Zeng-Guang 1,2,3; Ni, Zhen-Liang 1,3; Chen, Sheng 1,3; Fang, Zhijie 1,3
刊名	COGNITIVE NEURODYNAMICS
	2020-11-10
页码	9
关键词	EEG Motor imagery Convolutional neural network Bilinear vectors Attention mechanism
ISSN号	1871-4080
DOI	10.1007/s11571-020-09649-8
通讯作者	Hou, Zeng-Guang(zengguang.hou@ia.ac.cn)
英文摘要	Deep learning has achieved great success in areas such as computer vision and natural language processing. In the past, some work used convolutional networks to process EEG signals and reached or exceeded traditional machine learning methods. We propose a novel network structure and call it QNet. It contains a newly designed attention module: 3D-AM, which is used to learn the attention weights of EEG channels, time points, and feature maps. It provides a way to automatically learn the electrode and time selection. QNet uses a dual branch structure to fuse bilinear vectors for classification. It performs four, three, and two classes on the EEG Motor Movement/Imagery Dataset. The average cross-validation accuracy of 65.82%, 74.75%, and 82.88% was obtained, which are 7.24%, 4.93%, and 2.45% outperforms than the state-of-the-art, respectively. The article also visualizes the attention weights learned by QNet and shows its possible application for electrode channel selection.
资助项目	National Key R&D Program of China[2018YFC2001700] ; National Natural Science Foundation of China[61720106012] ; National Natural Science Foundation of China[U1913601] ; Beijing Natural Science Foundation[L172050] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32040000]
WOS关键词	SINGLE-TRIAL EEG ; CLASSIFICATION
WOS研究方向	Neurosciences & Neurology
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000588280200001
资助机构	National Key R&D Program of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Strategic Priority Research Program of Chinese Academy of Science
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/41758]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进机器人控制团队
通讯作者	Hou, Zeng-Guang
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Fan, Chen-Chen,Yang, Hongjun,Hou, Zeng-Guang,et al. Bilinear neural network with 3-D attention for brain decoding of motor imagery movements from the human EEG[J]. COGNITIVE NEURODYNAMICS,2020:9.
APA	Fan, Chen-Chen,Yang, Hongjun,Hou, Zeng-Guang,Ni, Zhen-Liang,Chen, Sheng,&Fang, Zhijie.(2020).Bilinear neural network with 3-D attention for brain decoding of motor imagery movements from the human EEG.COGNITIVE NEURODYNAMICS,9.
MLA	Fan, Chen-Chen,et al."Bilinear neural network with 3-D attention for brain decoding of motor imagery movements from the human EEG".COGNITIVE NEURODYNAMICS (2020):9.