基于少量导联的脑-机接口实现方法研究
|
摘要
针对少量导联脑电信号在脑-机接口实现中的可靠性和适用性问题,提出了一种基于独立分量分析的运动想象脑-机接口实现方法,系统输入为运动皮层三导联脑电信号。为了保证在少量导联情况下的算法稳定性和可靠性,提出采用自测试方法对空域滤波器进行优化设计。基于脑-机接口国际竞赛数据集对所提方法进行验证,所得运动想象分类结果优于竞赛优胜者的分类结果。
Aiming at the realizability and applicability of brain-computer interface(BCI) system with few-channel electroencephalogram(EEG), an implementation method of motor imagery BCI system based on independent component analysis(ICA) was proposed in this paper. Three channel EEG signals from the motor cortex were employed as input of the MI-BCI system. In order to ensure the stability and reliability of BCI system,the ICA spatial filter was optimized with self-test technique. The proposed method was validated on the public benchmark dataset(BCI competition IV-2 b). The experiment results indicated that the proposed method outperformed that used by the winner in BCI competition in terms of classification accuracies.
Aiming at the realizability and applicability of brain-computer interface(BCI) system with few-channel electroencephalogram(EEG), an implementation method of motor imagery BCI system based on independent component analysis(ICA) was proposed in this paper. Three channel EEG signals from the motor cortex were employed as input of the MI-BCI system. In order to ensure the stability and reliability of BCI system,the ICA spatial filter was optimized with self-test technique. The proposed method was validated on the public benchmark dataset(BCI competition IV-2 b). The experiment results indicated that the proposed method outperformed that used by the winner in BCI competition in terms of classification accuracies.
引文
[1]He B,Baxter B,Edelman B J.Noninvasive Brain-Computer Interfaces Based on Sensorimotor Rhythms[J].Proceedings of the IEEE,2015,103(6):1-19.
[2]Ramoser,H,Muller-Gerking,J,Pfurtscheller,G.Optimal Spatial Filtering of Single Trial EEG During Imagined Hand Movement[J].IEEE Transactions on Rehabilitation Engineering,2000,8(4):441.
[3]Wang Y.,Wang Y.T.,Jung T.P.Translation of EEG Spatial Filters from Resting to Motor Imagery using Independent Component Analysis[J].PloS One,2012,5(7):e37665.
[4]A.Kachenoura,L.Albera,L.Senhadji,P.Comon,ICA:a Potential Tool for BCI Systems[J].IEEE Signal Processing Magazine,2008,25(1):57-68.
[5]Rejer I,Górski P,Benefits of ICA in the Case of a Few Channel EEG[C].37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).IEEE,2015:7434-7437.
[6]BCI Competition IV[DB/OL].http://www.bbci.de/com- petition/ iv/index.html,2018-12-20.
[7]Lee T W,Girolami M,Sejnowski T J.Independent Component Analysis Using an Extended Infomax Algorithm for Mixed Subgaussian and Supergaussian Sources[J].Neural Computation,1999,11(2):417-441.
[8]Hyvarinen,A.Fast and Robust Fixed-Point Algorithms for Independent Component Analysis[J].IEEE Transactions on Neural Networks,1999,10 (3):626-634.
[9]Comon P.Independent Component Analysis,A New Concept?[J].Signal Processing,1994,36(3):287-314.
[10]Belouchrani A,Abed-Meraim K,Cardoso J F.A Blind Source Separation Technique Using Second-Order Statistics[J].IEEE Transactions on Signal Processing,1997,45(2):434-444.
[11]吴小培,周蚌艳,张磊.运动想象脑-机接口中的ICA滤波器设计[J].生物物理学报,2014,30(7):540-554.
[12]Zhou B ,Wu X ,Lv Z.A Fully Automated Trial Selection Method for Optimization of Motor Imagery Based Brain-Computer Interface[J].Plos One,2016,11(9):e0162657.
[13]吴小培,周蚌艳,张磊.脑-机接口中空域滤波技术现状与进展[J].安徽大学学报(自然科学版),2017,41(2):14-31.
[14]Ang K K,Chin Z-Y,Zhang H,et al.Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface[C].in Proc.IEEE Int.Joint Conf.Neural Netw.,2008:2390-2397.
[15]Naoki T,Toshihisa T.Active Data Selection for Motor Imagery EEG Classification[J].IEEE Transactions on Biomedical Engineering,2015,62 (2):458-467.
[16]Vinay J,Morteza A,Yasemin A,et al.Transfer Learning in Brain-Computer Interfaces[J].IEEE Computational Intelligence Magazine,2016:20-31.
[2]Ramoser,H,Muller-Gerking,J,Pfurtscheller,G.Optimal Spatial Filtering of Single Trial EEG During Imagined Hand Movement[J].IEEE Transactions on Rehabilitation Engineering,2000,8(4):441.
[3]Wang Y.,Wang Y.T.,Jung T.P.Translation of EEG Spatial Filters from Resting to Motor Imagery using Independent Component Analysis[J].PloS One,2012,5(7):e37665.
[4]A.Kachenoura,L.Albera,L.Senhadji,P.Comon,ICA:a Potential Tool for BCI Systems[J].IEEE Signal Processing Magazine,2008,25(1):57-68.
[5]Rejer I,Górski P,Benefits of ICA in the Case of a Few Channel EEG[C].37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).IEEE,2015:7434-7437.
[6]BCI Competition IV[DB/OL].http://www.bbci.de/com- petition/ iv/index.html,2018-12-20.
[7]Lee T W,Girolami M,Sejnowski T J.Independent Component Analysis Using an Extended Infomax Algorithm for Mixed Subgaussian and Supergaussian Sources[J].Neural Computation,1999,11(2):417-441.
[8]Hyvarinen,A.Fast and Robust Fixed-Point Algorithms for Independent Component Analysis[J].IEEE Transactions on Neural Networks,1999,10 (3):626-634.
[9]Comon P.Independent Component Analysis,A New Concept?[J].Signal Processing,1994,36(3):287-314.
[10]Belouchrani A,Abed-Meraim K,Cardoso J F.A Blind Source Separation Technique Using Second-Order Statistics[J].IEEE Transactions on Signal Processing,1997,45(2):434-444.
[11]吴小培,周蚌艳,张磊.运动想象脑-机接口中的ICA滤波器设计[J].生物物理学报,2014,30(7):540-554.
[12]Zhou B ,Wu X ,Lv Z.A Fully Automated Trial Selection Method for Optimization of Motor Imagery Based Brain-Computer Interface[J].Plos One,2016,11(9):e0162657.
[13]吴小培,周蚌艳,张磊.脑-机接口中空域滤波技术现状与进展[J].安徽大学学报(自然科学版),2017,41(2):14-31.
[14]Ang K K,Chin Z-Y,Zhang H,et al.Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface[C].in Proc.IEEE Int.Joint Conf.Neural Netw.,2008:2390-2397.
[15]Naoki T,Toshihisa T.Active Data Selection for Motor Imagery EEG Classification[J].IEEE Transactions on Biomedical Engineering,2015,62 (2):458-467.
[16]Vinay J,Morteza A,Yasemin A,et al.Transfer Learning in Brain-Computer Interfaces[J].IEEE Computational Intelligence Magazine,2016:20-31.