采用平滑伪Wigner-Ville分布的SSVEP脑机接口系统
|
摘要
提出基于多频率刺激源诱发SSVEP的脑机接口(BCI)系统.针对脑电信号的微弱性和非平稳性特点,在对其进行预处理和空间滤波的基础上,采用平滑伪Wigner-Ville分布的时频分析方法将时间窗口长度内的脑电信号转换为时间-频率分布的信号.分类汇总视觉刺激时间内的脑电频率,并提取脑电信号中的最大频率成分作为目标频率.实验结果表明:随着分析时间窗的增大,平滑伪Wigner-Ville时频分析方法具有一定的优势.当时间窗为4s时,其分类准确率达98.29%,信息传输率达28.01bits/min,超过经典的典型相关分析(CCA)和功率谱密度分析(PSDA)的结果.
The multi-frequencies stimulus brain-computer interface(BCI)system based on SSVEP was proposed.Electroencephalography(EEG)is preprocessed and spatial filtered firstly due to its weakness and non-stationary characteristics.The time-frequency analysis method of smoothed pseudo Wigner-Ville distribution was used to extract the maximum frequency components of the EEG signal as the target frequency,while the EEG signal in the length of time window was converted into a time-frequency distribution signal and the visual stimuli EEG frequency time was classified and summarized.As results,the time-frequency analysis method of SPWVD shows advantages with the increase of the length of time windows.When the length of time window reaches 4s,the classification accuracy of SPWVD reaches 98.29%and the information transmission rate reaches 28.01bit/min,which is superior to the results by the classic methods of canonical correlation analysis(CCA)and power spectral-density analysis(PSDA),respectively.
The multi-frequencies stimulus brain-computer interface(BCI)system based on SSVEP was proposed.Electroencephalography(EEG)is preprocessed and spatial filtered firstly due to its weakness and non-stationary characteristics.The time-frequency analysis method of smoothed pseudo Wigner-Ville distribution was used to extract the maximum frequency components of the EEG signal as the target frequency,while the EEG signal in the length of time window was converted into a time-frequency distribution signal and the visual stimuli EEG frequency time was classified and summarized.As results,the time-frequency analysis method of SPWVD shows advantages with the increase of the length of time windows.When the length of time window reaches 4s,the classification accuracy of SPWVD reaches 98.29%and the information transmission rate reaches 28.01bit/min,which is superior to the results by the classic methods of canonical correlation analysis(CCA)and power spectral-density analysis(PSDA),respectively.
引文
[1]WOLPAW J R,BIRBAUMER N,MCFARLAND D J,et al.Brain-computer interfaces for communication and control[J].Clinical Neurophysiology,2002,113(6):767-791.
[2]WANG Y,GAO X,HONG B,et al.Brain-computer interfaces based on visual evoked potentials[J].Engineering in Medicine and Biology Magazine,IEEE,2008,27(5):64-71.
[3]HE B,BAIRD R,BUTERA R,et al.Grand challenges in interfacing engineering with life sciences and medicine[J].IEEE Transactions on Biomedical Engineering,2013,60(3):589-598.
[4]FAN X,BI L,TENG T,et al.A brain-computer interface-based vehicle destination selection system using P300and SSVEP signals[J].Intelligent Transportation Systems Transactions on IEEE,2015,16(1):274-283.
[5]VIALATTE F,MAURICE M,DAUWELS J,et al.Steady-state visually evoked potentials:focus on essential paradigms and future perspectives[J].Progress in Neurobiology,2010,90(4):418-438.
[6]ZHANG Y,XU P,LIU T,et al.Multiple frequencies sequential coding for SSVEP-based brain-computer interface[J].PloSone,2012,7(3):e29519.
[7]YIN E,ZHOU Z,JIANG J,et al.A novel hybrid BCI speller based on the incorporation of SSVEP into the P300paradigm[J].Journal of neural engineering,2013,10(2):026012.
[8]XU M,QI H,WAN B,et al.A hybrid BCI speller paradigm combining P300potential and the SSVEP blocking feature[J].Journal of neural engineering,2013,10(2):026001.
[9]CHENG M,GAO X,GAO S,et al.Design and implementation of a brain-computer interface with high transfer rates[J].IEEE Transactions on Biomedical Engineering,2002,49(10):1181-1186.
[10]FRIMAN O,CEDEFAMN J,LUNDBERG P,et al.Detection of neural activity in functional MRI using canonical correlation analysis[J].Magnetic Resonance in Medicine,2001,45(2):323-330.
[11]LIN Z,ZHANG C,WU W,et al.Frequency recognition based on canonical correlation analysis for SSVEPbased BCIs[J].IEEE Transactions on Biomedical Engineering,2006,53(12):2610-2614.
[12]ZHANG Y,ZHOU G,ZHAO Q,et al.Multiway canonical correlation analysis for frequency components recognition in SSVEP-based BCIs[C]∥19th International Conference of Neural Information Processing.ICONIP 2012.Doha:Springer Berlin Heidelberg,2011:287-295.
[13]TIBSHIRANI R.Regression shrinkage and selection via the lasso[J].Journal of the Royal Statistical Society:Series B(Methodological),1996(6):267-288.
[14]张宇.基于视觉诱发电位的脑—机接口分析算法优化及实时控制系统构建[D].上海:华东理工大学,2013.ZHANG Yu.Analysis algorithm optimization and realtime control system establishment for brain-computer interface based on visual evoked potentials[D].Shanghai:East China University of Science and Technology,2013.
[15]FRIMAN O,VOLOSYAK I,GRSER A.Multiple channel detection of steady-state visual evoked potentials for brain-computer interfaces[J].IEEE Transactions on Biomedical Engineering,2007,54(4):742-750.
[16]何庆华,彭承琳,吴宝明.脑-机接口技术研究方法[J].重庆大学学报:自然科学版,2002,25(12):106-109.HE Qing-hua,PENG Cheng-lin,WU Bao-ming.Research methods of brain-computer interface technology[J].Journal of Chongqing University:Natural Science Edition,2002,25(12):106-109.
[17]GARCIA-MOLINA G,ZHU D.Optimal spatial filtering for the steady state visual evoked potential:BCI application[C]∥2011 5th International IEEE/EMBS Conference on Neural Engineering(NER).Cancun:IEEE.2011:156-160.
[18]MLLER-PUTZ G R,SCHERER R,BRAUNEIS C,et al.Steady-state visual evoked potential(SSVEP)-based communication:impact of harmonic frequency components[J].Journal of Neural Engineering,2005,2(4):123.
[19]张杨松.基于稳态视觉诱发电位的脑机制及脑-机接口研究[D].成都:电子科技大学,2013.ZHANGYang-song.Research on steady state visual evoked potential of its brain mechanisms and application in brain-computer interface[D].Chengdu:University of Electronic Science and Technology of China,2013.
[20]HART E P,DUMAS E M,REIJNTJES R,et al.Deficient sustained attention to response task and P300characteristics in early Huntington’s disease[J].Journal of Neurology,2012,259(6):1191-1198.
[2]WANG Y,GAO X,HONG B,et al.Brain-computer interfaces based on visual evoked potentials[J].Engineering in Medicine and Biology Magazine,IEEE,2008,27(5):64-71.
[3]HE B,BAIRD R,BUTERA R,et al.Grand challenges in interfacing engineering with life sciences and medicine[J].IEEE Transactions on Biomedical Engineering,2013,60(3):589-598.
[4]FAN X,BI L,TENG T,et al.A brain-computer interface-based vehicle destination selection system using P300and SSVEP signals[J].Intelligent Transportation Systems Transactions on IEEE,2015,16(1):274-283.
[5]VIALATTE F,MAURICE M,DAUWELS J,et al.Steady-state visually evoked potentials:focus on essential paradigms and future perspectives[J].Progress in Neurobiology,2010,90(4):418-438.
[6]ZHANG Y,XU P,LIU T,et al.Multiple frequencies sequential coding for SSVEP-based brain-computer interface[J].PloSone,2012,7(3):e29519.
[7]YIN E,ZHOU Z,JIANG J,et al.A novel hybrid BCI speller based on the incorporation of SSVEP into the P300paradigm[J].Journal of neural engineering,2013,10(2):026012.
[8]XU M,QI H,WAN B,et al.A hybrid BCI speller paradigm combining P300potential and the SSVEP blocking feature[J].Journal of neural engineering,2013,10(2):026001.
[9]CHENG M,GAO X,GAO S,et al.Design and implementation of a brain-computer interface with high transfer rates[J].IEEE Transactions on Biomedical Engineering,2002,49(10):1181-1186.
[10]FRIMAN O,CEDEFAMN J,LUNDBERG P,et al.Detection of neural activity in functional MRI using canonical correlation analysis[J].Magnetic Resonance in Medicine,2001,45(2):323-330.
[11]LIN Z,ZHANG C,WU W,et al.Frequency recognition based on canonical correlation analysis for SSVEPbased BCIs[J].IEEE Transactions on Biomedical Engineering,2006,53(12):2610-2614.
[12]ZHANG Y,ZHOU G,ZHAO Q,et al.Multiway canonical correlation analysis for frequency components recognition in SSVEP-based BCIs[C]∥19th International Conference of Neural Information Processing.ICONIP 2012.Doha:Springer Berlin Heidelberg,2011:287-295.
[13]TIBSHIRANI R.Regression shrinkage and selection via the lasso[J].Journal of the Royal Statistical Society:Series B(Methodological),1996(6):267-288.
[14]张宇.基于视觉诱发电位的脑—机接口分析算法优化及实时控制系统构建[D].上海:华东理工大学,2013.ZHANG Yu.Analysis algorithm optimization and realtime control system establishment for brain-computer interface based on visual evoked potentials[D].Shanghai:East China University of Science and Technology,2013.
[15]FRIMAN O,VOLOSYAK I,GRSER A.Multiple channel detection of steady-state visual evoked potentials for brain-computer interfaces[J].IEEE Transactions on Biomedical Engineering,2007,54(4):742-750.
[16]何庆华,彭承琳,吴宝明.脑-机接口技术研究方法[J].重庆大学学报:自然科学版,2002,25(12):106-109.HE Qing-hua,PENG Cheng-lin,WU Bao-ming.Research methods of brain-computer interface technology[J].Journal of Chongqing University:Natural Science Edition,2002,25(12):106-109.
[17]GARCIA-MOLINA G,ZHU D.Optimal spatial filtering for the steady state visual evoked potential:BCI application[C]∥2011 5th International IEEE/EMBS Conference on Neural Engineering(NER).Cancun:IEEE.2011:156-160.
[18]MLLER-PUTZ G R,SCHERER R,BRAUNEIS C,et al.Steady-state visual evoked potential(SSVEP)-based communication:impact of harmonic frequency components[J].Journal of Neural Engineering,2005,2(4):123.
[19]张杨松.基于稳态视觉诱发电位的脑机制及脑-机接口研究[D].成都:电子科技大学,2013.ZHANGYang-song.Research on steady state visual evoked potential of its brain mechanisms and application in brain-computer interface[D].Chengdu:University of Electronic Science and Technology of China,2013.
[20]HART E P,DUMAS E M,REIJNTJES R,et al.Deficient sustained attention to response task and P300characteristics in early Huntington’s disease[J].Journal of Neurology,2012,259(6):1191-1198.