PSYCH OpenIR
Common Spatial Pattern with L21-Norm
Gu, Jingyu1; Wei, Mengting2; Guo, Yiyun3; Wang, Haixian1
First AuthorGu, Jingyu
Correspondent Emailhxwang@seu.edu.cn
Contribution Rank3
Abstract

As one of the most commonly used algorithms in the field of feature extraction, common spatial pattern (CSP) has a good effect on multichannel electroencephalogram (EEG) signal classification, especially for motor imagery-based signals. However, the formulation of the conventional CSP based on the L2-norm is sensitive to outliers. Whereas the L1-norm-based common spatial pattern (CSP-L1) proposed in recent years can seek robust spatial filters to effectively alleviate the impact of outliers, the L1-norm is unable to characterize the geometric structure of the data well. To further improve the robustness of CSP, in this paper, we propose a new extension to CSP called the L21-norm-based common spatial pattern (CSP-L21), which is formulated by using the L21-norm rather than the L2-norm. Moreover, CSP-L21 has the advantages of rotational invariance and geometric structure characterization. We provide a non-greedy iterative algorithm to maximize the objective function of CSP-L21. Experiments on a toy example and three popular data sets of BCI competitions illustrate that the proposed method can efficiently extract discriminative features.

KeywordBrain-computer interfaces (BCI) Common spatial pattern (CSP) L21-norm Robust feature extraction
2021-07
Language英语
DOI10.1007/s11063-021-10567-x
Source PublicationNEURAL PROCESSING LETTERS
ISSN1370-4621
Subtype综述
Indexed ByEI
Citation statistics
Document Type期刊论文
Identifierhttp://ir.psych.ac.cn/handle/311026/39589
Collection中国科学院心理研究所
Affiliation1.Southeast Univ, Sch Biol Sci & Med Engn, Key Lab Child Dev & Learning Sci, Minist Educ, Nanjing 210096, Jiangsu, Peoples R China
2.Qingdao Port Int Co Ltd, Qingdao 266011, Shandong, Peoples R China
3.Chinese Acad Sci, Inst Psychol, Beijing 100101, Peoples R China
Recommended Citation
GB/T 7714
Gu, Jingyu,Wei, Mengting,Guo, Yiyun,et al. Common Spatial Pattern with L21-Norm[J]. NEURAL PROCESSING LETTERS,2021.
APA Gu, Jingyu,Wei, Mengting,Guo, Yiyun,&Wang, Haixian.(2021).Common Spatial Pattern with L21-Norm.NEURAL PROCESSING LETTERS.
MLA Gu, Jingyu,et al."Common Spatial Pattern with L21-Norm".NEURAL PROCESSING LETTERS (2021).
Files in This Item:
File Name/Size DocType Version Access License
Common Spatial Patte(3461KB)期刊论文出版稿限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Gu, Jingyu]'s Articles
[Wei, Mengting]'s Articles
[Guo, Yiyun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Gu, Jingyu]'s Articles
[Wei, Mengting]'s Articles
[Guo, Yiyun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Gu, Jingyu]'s Articles
[Wei, Mengting]'s Articles
[Guo, Yiyun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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