Efficient Brain Decoding Based on Adaptive EEG Channel Selection and Transformation
文献类型:期刊论文
作者 | Wang, Jiaxing5; Shi, Lei1; Wang, Weiqun5; Hou, Zeng-Guang2,3,4,5 |
刊名 | IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE |
出版日期 | 2022-03-08 |
页码 | 10 |
ISSN号 | 2471-285X |
关键词 | Electroencephalography Decoding Brain modeling Computational modeling Optimized production technology Feature extraction Data models Channel selection channel transformation brain decoding computational cost classification accuracy |
DOI | 10.1109/TETCI.2022.3147225 |
通讯作者 | Hou, Zeng-Guang(zeng-guang.hou@ia.ac.cn) |
英文摘要 | Electroencephalography (EEG) based brain-computer interface (BCI) has a wide range of applications in neuro-rehabilitation and motor assistance. However, brain activities, acquired from a large number of EEG channels, are highly inter-correlated or irrelevant to the brain decoding task, thus reducing the decoding efficiency and accuracy. How to adaptively select the optimal channel number depend on different trials remains a big challenge. To solve this problem, an efficient end-to-end brain decoding model named AdaEEGNet, is proposed in this study. It can reduce the computational cost by adaptively controlling the number of input channels and improve the classification accuracy by reducing over-fitting. Specifically, a lightweight policy module is designed to analyze which channel is needed for decoding current EEG trial. Due to the channel selection process is indifferentiable, we propose to use the Gumbel-Estimator to back-propagate the gradient to train the whole framework. Additionally, a weight coefficient is designed to make a trade-off between brain decoding accuracy and efficiency. To validate the proposed AdaEEGNet feasibility in improving decoding efficiency and accuracy, extensive experiments were conducted on BCI competition IV dataset. The results show that our methods can improve the decoding accuracy by 2% with only 65% computational cost significantly compared with the baseline method. |
WOS关键词 | COMMON SPATIAL-PATTERN ; MOTOR IMAGERY ; COMPUTER-INTERFACE ; CLASSIFICATION ; BCI ; NETWORK ; SYSTEM ; SSVEP |
资助项目 | National Natural Science Foundation of China[61720106012] ; National Natural Science Foundation of China[U1913601] ; National Key R&D Program of China[2018YFC2001700] ; Beijing Natural Science Foundation[4202074] ; Beijing Science and Technology Project[Z211100007921021] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32000000] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000767853500001 |
资助机构 | National Natural Science Foundation of China ; National Key R&D Program of China ; Beijing Natural Science Foundation ; Beijing Science and Technology Project ; Strategic Priority Research Program of Chinese Academy of Science |
源URL | [http://ir.ia.ac.cn/handle/173211/47990] |
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.Meituan Inc, Beijing 100102, Peoples R China 2.Macau Univ Sci & Technol, Inst Syst Engn, MUST CASIA Joint Lab Intelligence Sci & Technol, Macau, Peoples R China 3.CAS Ctr Excellence Brain Sci & Intelligence Tech, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 5.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Wang, Jiaxing,Shi, Lei,Wang, Weiqun,et al. Efficient Brain Decoding Based on Adaptive EEG Channel Selection and Transformation[J]. IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE,2022:10. |
APA | Wang, Jiaxing,Shi, Lei,Wang, Weiqun,&Hou, Zeng-Guang.(2022).Efficient Brain Decoding Based on Adaptive EEG Channel Selection and Transformation.IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE,10. |
MLA | Wang, Jiaxing,et al."Efficient Brain Decoding Based on Adaptive EEG Channel Selection and Transformation".IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE (2022):10. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。