SIA OpenIR  > 机器人学研究室
Learning joint space–time–frequency features for EEG decoding on small labeled data
Zhao DY(赵冬晔)1,2,3; Tang FZ(唐凤珍)1,2; Si BL(斯白露)1,2; Feng XS(封锡盛)1,2
Department机器人学研究室
Source PublicationNeural Networks
ISSN0893-6080
2019
Volume114Pages:67-77
Indexed BySCI ; EI
EI Accession number20191206651647
WOS IDWOS:000466610500007
Contribution Rank1
Funding OrganizationNational Key Research and Development Program of China ; Frontier Science research project of the Chinese Academy of Sciences ; CAS Pioneer Hundred Talents Program, China ; State Key Laboratory of Robotics, China
KeywordBrain-computer interfaces Convolutional neural network Joint space–time–frequency feature learning Subject-to-subject weight transfer Small labeled data
AbstractBrain–computer interfaces (BCIs), which control external equipment using cerebral activity, have received considerable attention recently. Translating brain activities measured by electroencephalography (EEG) into correct control commands is a critical problem in this field. Most existing EEG decoding methods separate feature extraction from classification and thus are not robust across different BCI users. In this paper, we propose to learn subject-specific features jointly with the classification rule. We develop a deep convolutional network (ConvNet) to decode EEG signals end-to-end by stacking time–frequency transformation, spatial filtering, and classification together. Our proposed ConvNet implements a joint space–time–frequency feature extraction scheme for EEG decoding. Morlet wavelet-like kernels used in our network significantly reduce the number of parameters compared with classical convolutional kernels and endow the features learned at the corresponding layer with a clear interpretation, i.e. spectral amplitude. We further utilize subject-to-subject weight transfer, which uses parameters of the networks trained for existing subjects to initialize the network for a new subject, to solve the dilemma between a large number of demanded data for training deep ConvNets and small labeled data collected in BCIs. The proposed approach is evaluated on three public data sets, obtaining superior classification performance compared with the state-of-the-art methods.
Language英语
WOS SubjectComputer Science, Artificial Intelligence ; Neurosciences
WOS KeywordBRAIN-COMPUTER INTERFACES ; FEATURE-EXTRACTION ; PATTERNS
WOS Research AreaComputer Science ; Neurosciences & Neurology
Funding ProjectNational Key Research and Development Program of China[2016YFC0801808] ; Frontier Science research project of the Chinese Academy of Sciences[QYZDY-SSW-JSC005] ; CAS Pioneer Hundred Talents Program, China[Y8F1160101] ; State Key Laboratory of Robotics, China[Y7C120E101] ; National Key Research and Development Program of China[2016YFC0801808] ; Frontier Science research project of the Chinese Academy of Sciences[QYZDY-SSW-JSC005] ; CAS Pioneer Hundred Talents Program, China[Y8F1160101] ; State Key Laboratory of Robotics, China[Y7C120E101]
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/24471
Collection机器人学研究室
Corresponding AuthorTang FZ(唐凤珍)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110016, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
Recommended Citation
GB/T 7714
Zhao DY(赵冬晔),Tang FZ(唐凤珍),Si BL(斯白露),等. Learning joint space–time–frequency features for EEG decoding on small labeled data[J]. Neural Networks,2019,114:67-77.
APA Zhao DY,Tang FZ,Si BL,&Feng XS.(2019).Learning joint space–time–frequency features for EEG decoding on small labeled data.Neural Networks,114,67-77.
MLA Zhao DY,et al."Learning joint space–time–frequency features for EEG decoding on small labeled data".Neural Networks 114(2019):67-77.
Files in This Item: Download All
File Name/Size DocType Version Access License
Learning joint space(797KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhao DY(赵冬晔)]'s Articles
[Tang FZ(唐凤珍)]'s Articles
[Si BL(斯白露)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhao DY(赵冬晔)]'s Articles
[Tang FZ(唐凤珍)]'s Articles
[Si BL(斯白露)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhao DY(赵冬晔)]'s Articles
[Tang FZ(唐凤珍)]'s Articles
[Si BL(斯白露)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Learning joint space–time–frequency features for EEG decoding on small labeled data.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.