Sub-band target alignment common spatial pattern in brain-computer interface

被引:30
作者
Zhang, Xianxiong [1 ]
She, Qingshan [1 ]
Chen, Yun [1 ]
Kong, Wanzeng [2 ]
Mei, Congli [3 ]
机构
[1] Hangzhou DianZi Univ, Sch Automat, Hangzhou 310018, Peoples R China
[2] Key Lab Brain Machine Collaborat Intelligence Zhe, Hangzhou 310018, Peoples R China
[3] Zhejiang Univ Water Resources & Elect Power, Coll Elect Engn, Hangzhou 310018, Peoples R China
基金
中国国家自然科学基金;
关键词
Brain-computer interface; Transfer learning; Sub-band filtering; Target alignment; Cross-subject classification; SINGLE-TRIAL EEG; MUTUAL INFORMATION; ADAPTATION; SELECTION; MANIFOLD;
D O I
10.1016/j.cmpb.2021.106150
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Background and objective: In the brain computer interface (BCI) field, using sub-band common spatial pattern (SBCSP) and filter bank common spatial pattern (FBCSP) can improve the accuracy of classification by selection a specific frequency band. However, in the cross-subject classification, due to the individual differences between different subjects, the performance is limited. Methods: This paper introduces the idea of transfer learning and presents the sub-band target alignment common spatial pattern (SBTACSP) method and applies it to the cross-subject classification of motor imagery (MI) EEG signals. First, the EEG signals are bandpass-filtered into multiple frequency bands (sub band filtering). Subsequently, the source domain trails are aligned into the target domain space in each frequency band. The CSP algorithm is then employed to extract features among which more representative features are selected by the minimum redundancy maximum relevance (mRMR) approach from each sub-band. Then the features of all sub-bands are fused. Finally, conventional linear discriminant analysis (LDA) algorithm is used for MI classification. Results: Our method is evaluated on Datasets IIa and IIb of the BCI Competition IV . Compared with six state-of-the-art algorithms, the proposed SBTACSP method performed relatively the best and achieved a mean classification accuracy of 75.15% and 66.85% in cross-subject classification of Datasets IIa and IIb respectively. Conclusion: Therefore, the combination of sub-band filtering and transfer learning achieves superior classification performance compared to either one. The proposed algorithms will greatly promote the practical application of MI based BCIs. (c) 2021 Elsevier B.V. All rights reserved.
引用
收藏
页数:8
相关论文
共 36 条
[31]   Probabilistic Common Spatial Patterns for Multichannel EEG Analysis [J].
Wu, Wei ;
Chen, Zhe ;
Gao, Xiaorong ;
Li, Yuanqing ;
Brown, Emery N. ;
Gao, Shangkai .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (03) :639-653
[32]   Parallel Transport on the Cone Manifold of SPD Matrices for Domain Adaptation [J].
Yair, Or ;
Ben-Chen, Mirela ;
Talmon, Ronen .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2019, 67 (07) :1797-1811
[33]   Riemannian Approaches in Brain-Computer Interfaces: A Review [J].
Yger, Florian ;
Berar, Maxime ;
Lotte, Fabien .
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2017, 25 (10) :1753-1762
[34]   Transfer Learning: A Riemannian Geometry Framework With Applications to Brain-Computer Interfaces [J].
Zanini, Paolo ;
Congedo, Marco ;
Jutten, Christian ;
Said, Salem ;
Berthoumieu, Yannick .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2018, 65 (05) :1107-1116
[35]   Joint Geometrical and Statistical Alignment for Visual Domain Adaptation [J].
Zhang, Jing ;
Li, Wanqing ;
Ogunbona, Philip .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :5150-5158
[36]   Manifold Embedded Knowledge Transfer for Brain-Computer Interfaces [J].
Zhang, Wen ;
Wu, Dongrui .
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2020, 28 (05) :1117-1127