SIA OpenIR  > 机器人学研究室
Decoding multiclass motor imagery EEG from the same upper limb by combining Riemannian geometry features and partial least squares regression
Chu YQ(褚亚奇)1,2,3; Zhao XG(赵新刚)1,2; Zou YJ(邹宜君)1,2,3; Xu WL(徐卫良)1,4; Song GL(宋国立)1,2; Han JD(韩建达)1,5; Zhao YW(赵忆文)1,2
Department机器人学研究室
Corresponding AuthorZhao, Xingang(zhaoxingang@sia.cn)
Source PublicationJOURNAL OF NEURAL ENGINEERING
ISSN1741-2560
2020
Volume17Issue:4Pages:1-18
Indexed BySCI ; EI
EI Accession number20203609135409
WOS IDWOS:000561501900001
Contribution Rank1
Funding OrganizationNational Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61573340, 61773369, U1813214] ; Frontier Science research project of the Chinese Academy of Sciences [QYZDY-SSW-JSC005]
Keywordmotor imagery EEG same upper limb Riemannian geometry features partial least squares regression brain-machine interface
Abstract

Objective. Due to low spatial resolution and poor signal-to-noise ratio of electroencephalogram (EEG), high accuracy classifications still suffer from lots of obstacles in the context of motor imagery (MI)-based brain-machine interface (BMI) systems. Particularly, it is extremely challenging to decode multiclass MI EEG from the same upper limb. This research proposes a novel feature learning approach to address the classification problem of 6-class MI tasks, including imaginary elbow flexion/extension, wrist supination/pronation, and hand close/open within the unilateral upper limb.Approach. Instead of the traditional common spatial pattern (CSP) or filter-bank CSP (FBCSP) manner, the Riemannian geometry (RG) framework involving Riemannian distance and Riemannian mean was directly adopted to extract tangent space (TS) features from spatial covariance matrices of the MI EEG trials. Subsequently, to reduce the dimensionality of the TS features, the algorithm of partial least squares regression was applied to obtain more separable and compact feature representations.Main results. The performance of the learned RG feature representations was validated by a linear discriminative analysis and support vector machine classifier, with an average accuracy of 80.50% and 79.70% on EEG dataset collected from 12 participants, respectively.Significance. These results demonstrate that compared with CSP and FBCSP features, the proposed approach can significantly increase the decoding accuracy for multiclass MI tasks from the same upper limb. This approach is promising and could potentially be applied in the context of MI-based BMI control of a robotic arm or a neural prosthesis for motor disabled patients with highly impaired upper limb.

Language英语
WOS SubjectEngineering, Biomedical ; Neurosciences
WOS KeywordBRAIN-COMPUTER INTERFACES ; SENSORIMOTOR RHYTHMS ; CLASSIFICATION ; LEVEL ; TIME
WOS Research AreaEngineering ; Neurosciences & Neurology
Funding ProjectNational Natural Science Foundation of China[61573340] ; National Natural Science Foundation of China[61773369] ; National Natural Science Foundation of China[U1813214] ; Frontier Science research project of the Chinese Academy of Sciences[QYZDY-SSW-JSC005]
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/27565
Collection机器人学研究室
Corresponding AuthorZhao XG(赵新刚)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China
3.University of Chinese Academy of Sciences (UCAS), Beijing, China
4.Department of Mechanical Engineering, University of Auckland, Auckland, New Zealand
5.College of Artificial Intelligence, Nankai University, Tianjin, China
Recommended Citation
GB/T 7714
Chu YQ,Zhao XG,Zou YJ,et al. Decoding multiclass motor imagery EEG from the same upper limb by combining Riemannian geometry features and partial least squares regression[J]. JOURNAL OF NEURAL ENGINEERING,2020,17(4):1-18.
APA Chu YQ.,Zhao XG.,Zou YJ.,Xu WL.,Song GL.,...&Zhao YW.(2020).Decoding multiclass motor imagery EEG from the same upper limb by combining Riemannian geometry features and partial least squares regression.JOURNAL OF NEURAL ENGINEERING,17(4),1-18.
MLA Chu YQ,et al."Decoding multiclass motor imagery EEG from the same upper limb by combining Riemannian geometry features and partial least squares regression".JOURNAL OF NEURAL ENGINEERING 17.4(2020):1-18.
Files in This Item: Download All
File Name/Size DocType Version Access License
Decoding multiclass (1662KB)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
[Chu YQ(褚亚奇)]'s Articles
[Zhao XG(赵新刚)]'s Articles
[Zou YJ(邹宜君)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chu YQ(褚亚奇)]'s Articles
[Zhao XG(赵新刚)]'s Articles
[Zou YJ(邹宜君)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chu YQ(褚亚奇)]'s Articles
[Zhao XG(赵新刚)]'s Articles
[Zou YJ(邹宜君)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Decoding multiclass motor imagery EEG from the same upper limb by combining Riemannian geometry features and partial least squares regression.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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