A Decoding Scheme for Incomplete Motor Imagery EEG With Deep Belief Network | |
Chu, Yaqi1,2,3; Zhao, Xingang1,2; Zou, Yijun1,2,3; Xu, Weiliang1,4; Han, Jianda1,2; Zhao, Yiwen1,2 | |
刊名 | FRONTIERS IN NEUROSCIENCE |
2018-09-28 | |
卷号 | 12页码:17 |
关键词 | brain-computer interface decoding scheme incomplete motor imagery EEG power spectral density deep belief network |
ISSN号 | 1662-453X |
DOI | 10.3389/fnins.2018.00680 |
通讯作者 | Zhao, Xingang(zhaoxingang@sia.cn) |
英文摘要 | High accuracy decoding of electroencephalogram (EEG) signal is still a major challenge that can hardly be solved in the design of an effective motor imagery-based brain-computer interface (BCI), especially when the signal contains various extreme artifacts and outliers arose from data loss. The conventional process to avoid such cases is to directly reject the entire severely contaminated EEG segments, which leads to a drawback that the BCI has no decoding results during that certain period. In this study, a novel decoding scheme based on the combination of Lomb-Scargle periodogram (LSP) and deep belief network (DBN) was proposed to recognize the incomplete motor imagery EEG. Particularly, instead of discarding the entire segment, two forms of data removal were adopted to eliminate the EEG portions with extreme artifacts and data loss. The LSP was utilized to steadily extract the power spectral density (PSD) features from the incomplete EEG constructed by the remaining portions. A DBN structure based on the restricted Boltzmann machine (RBM) was exploited and optimized to perform the classification task. Various comparative experiments were conducted and evaluated on simulated signal and real incomplete motor imagery EEG, including the comparison of three PSD extraction methods (fast Fourier transform,Welch and LSP) and two classifiers (DBN and support vector machine, SVM). The results demonstrate that the LSP can estimate relative robust PSD features and the proposed scheme can significantly improve the decoding performance for the incomplete motor imagery EEG. This scheme can provide an alternative decoding solution for the motor imagery EEG contaminated by extreme artifacts and data loss. It can be beneficial to promote the stability, smoothness and maintain consecutive outputs without interruption for a BCI system that is suitable for the online and long-term application. |
资助项目 | National Nature Science Foundation of China[61503374] ; National Nature Science Foundation of China[61573340] ; Chinese Academy of Sciences[QYZDY-SSW-JSC005] ; Liaoning Provincial Doctoral Starting Foundation of China[201501032] |
WOS研究方向 | Neurosciences & Neurology |
语种 | 英语 |
出版者 | FRONTIERS MEDIA SA |
WOS记录号 | WOS:000445928200001 |
资助机构 | National Nature Science Foundation of China ; Chinese Academy of Sciences ; Liaoning Provincial Doctoral Starting Foundation of China |
内容类型 | 期刊论文 |
源URL | [http://ir.imr.ac.cn/handle/321006/129609] |
专题 | 金属研究所_中国科学院金属研究所 |
通讯作者 | Zhao, Xingang |
作者单位 | 1.Chinese Acad Sci, Shenyang Inst Automat, State Key Lab Robot, Shenyang, Liaoning, Peoples R China 2.Chinese Acad Sci, Inst Robot & Intelligent Mfg, Shenyang, Liaoning, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Univ Auckland, Dept Mech Engn, Auckland, New Zealand |
推荐引用方式 GB/T 7714 | Chu, Yaqi,Zhao, Xingang,Zou, Yijun,et al. A Decoding Scheme for Incomplete Motor Imagery EEG With Deep Belief Network[J]. FRONTIERS IN NEUROSCIENCE,2018,12:17. |
APA | Chu, Yaqi,Zhao, Xingang,Zou, Yijun,Xu, Weiliang,Han, Jianda,&Zhao, Yiwen.(2018).A Decoding Scheme for Incomplete Motor Imagery EEG With Deep Belief Network.FRONTIERS IN NEUROSCIENCE,12,17. |
MLA | Chu, Yaqi,et al."A Decoding Scheme for Incomplete Motor Imagery EEG With Deep Belief Network".FRONTIERS IN NEUROSCIENCE 12(2018):17. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论