整合贝叶斯动态停止策略对SSVEP-BCIs的性能提升研究
|
摘要
由于大脑的状态处于不断变化中,因此提取自脑电图中的特征,其质量并不总是足够高以保证脑-机接口(BCI)的可靠输出。提出了基于贝叶斯估计的动态停止(DS)策略,并将其整合到基于稳态视觉诱发电位(SSVEP)的BCI系统中,以进一步优化和提升SSVEP-BCIs的性能。10人次的实验结果表明,相比于传统的静态停止(FS)策略,DS策略能有效提升信息传输率(ITR),尤其是使用扩展的典型相关分析的DS策略相比FS策略提升了7.85%。另外,使用总体任务相关成分分析的DS策略得到的平均和最高ITR分别是352.3和435.7 bits/min。因此,证明了通过整合DS策略可以进一步提升SSVEP-BCIs的性能,并有希望推广到实际应用。
As the brain state is always changing,the quality of features extracted from electroencephalography(EEG) is not high enough to guarantee the reliable output of brain-computer interface(BCI) all the time. In this study,we propose a Bayes-based dynamic stopping(DS) strategy and incorporate it into the steady-state visual evoked potential(SSVEP)-based BCI,to further optimize and enhance the performance of SSVEP-BCIs. Experimental results of ten subjects suggest that the Bayes-based DS strategy effectively improves information transfer rate(ITR),and especially,the DS strategy using extended canonical correlation analysis(CCA) improves 7. 85% compared with the conventional fixed stopping(FS) strategy. In addition,the average and highest ITR achieved by the DS strategy using ensemble taskrelated component analysis(TRCA) is 352. 3 bits/min and 435. 7 bits/min,respectively. This study demonstrates that the performance of SSVEP-based BCIs can be further improved by incorporating the DS strategy,which is promising for practical applications.
As the brain state is always changing,the quality of features extracted from electroencephalography(EEG) is not high enough to guarantee the reliable output of brain-computer interface(BCI) all the time. In this study,we propose a Bayes-based dynamic stopping(DS) strategy and incorporate it into the steady-state visual evoked potential(SSVEP)-based BCI,to further optimize and enhance the performance of SSVEP-BCIs. Experimental results of ten subjects suggest that the Bayes-based DS strategy effectively improves information transfer rate(ITR),and especially,the DS strategy using extended canonical correlation analysis(CCA) improves 7. 85% compared with the conventional fixed stopping(FS) strategy. In addition,the average and highest ITR achieved by the DS strategy using ensemble taskrelated component analysis(TRCA) is 352. 3 bits/min and 435. 7 bits/min,respectively. This study demonstrates that the performance of SSVEP-based BCIs can be further improved by incorporating the DS strategy,which is promising for practical applications.
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]YIN E,ZEYL T,SAAB R,et al.An auditory-tactile visual saccade-independent P300 brain-computer[J].International Journal of Neural Systems,2016,26(1):1650001.
[3]李佳宁,蒲江波,崔红岩,等.基于体感电刺激诱发P300的脑机接口[J].仪器仪表学报,2017,38(6):1353-1360.LI J N,PU J B,CUI H Y,et al.Electrical somatosensory based P300 for a brain computer interface system[J].Chinese Journal of Scientific Instrument,2017,38(6):1353-1360.
[4]刘晶,白艳茹,许敏鹏,等.基于Farwell范式诱发ERP的身份识别研究[J].电子测量与仪器学报,2015,29(2):221-226.LIU J,BAI Y G,XU M P,et al.Research of person identi-fication using ERP based on Farwell paradigm[J].Journal of Electronic Measurement and Instrumentation,2015,29(2):221-226.
[5]PICHIORRI F,DE V F F,CINCOTTI F,et al.Sensorimotor rhythm-based brain-computer interface training:the impact on motor cortical responsiveness[J].Journal of Neural Engineering,2011,8(2):025020.
[6]ZHANG Y,ZHOU G,JIN J,et al.Frequency recognition in SSVEP-based BCI using multiset canonical correlation analysis[J].International Journal of Neural Systems,2014,24(4):1450013.
[7]李鹏海,许敏鹏,万柏坤,等.视觉诱发电位脑-机接口实验范式研究进展[J].仪器仪表学报,2016,37(10):2340-2351.LI P H,XU M P,WAN B K,et al.Review of experimental paradigms in brain-computer interface based on visual evoked potential[J].Chinese Journal of Scientific Instrument,2016,37(10):2340-2351.
[8]安兴伟,曹勇,焦学军,等.基于视听交互刺激的认知机理与脑机接口范式研究进展[J].电子测量与仪器学报,2017,31(7):983-993.AN X W,CAO Y,JIAO X J,et al.Research on cognitive mechanism and brain computer interface application in visual auditory crossmodal stimuli[J].Journal of Electronic Measurement and Instrumentation,2017,31(7):983-993.
[9]XU M,QI H,WAN B,et al.A hybrid BCI speller paradigm combining P300 potential and the SSVEP blocking feature[J].Journal of Neural Engineering,2013,10(2):026001.
[10]VIALATTE F B,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.
[11]JIA C,GAO X,HPNG B,et al.Frequency and phase mixed coding in SSVEP-based brain-computer interface[J].IEEE Transactions on Biomedical Engineering,2011,58(1):200-206.
[12]CHEN X,WANG Y,NAKANISHI M,et al.High-speed spelling with a noninvasive brain-computer interface[J].Proceedings of the National Academy of Sciences of the United States of America,2015,112(44):e6058.
[13]ZHANG Y,PENG X,LIU T,et al.Multiple frequencies sequential coding for SSVEP-based brain-computer interface[J].Plos One,2012,7(3):e29519.
[14]BIN G,GAO X,YAN Z,et al.An online multi-channel SSVEP-based brain-computer interface using a canonical correlation analysis method[J].Journal of Neural Engineering,2009,6(4):046002.
[15]WANG Y,NAKANISHI M,WANG Y T,et al.Enhancing detection of steady-state visual evoked potentials using individual training data[C].36th Annual International Conf.of the IEEE Engineering in Medicine and Biology Society,2014:3037-3040.
[16]NAKANISHI M,WANG Y,CHEN X,et al.Enhancing detection of SSVEPs for a high-speed brain speller using task-related component analysis[J].IEEE Transactions on Biomedical Engineering,2017,65(1):104-112.
[17]SCHREUDER M,HOHNE J,BLANKERTZ B,et al.Optimizing event-related potential based brain-computer interfaces:A systematic evaluation of dynamic stopping methods[J].Journal of Neural Engineering,2013,10(3):036025.
[18]LENHARDT A,KAPER M,RITTER H J.An adaptive P300-based online brain-computer interface[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2008,16(2):121-130.
[19]JIN J,ALLISON B Z,SELLERS E W,et al.An adaptive P300-based control system[J].Journal of Neural Engineering,2011,8(3):036006.
[20]THROCKMORTON C S,COLWELL K A,RYAN D B,et al.Bayesian approach to dynamically controlling data collection in P300 spellers[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2013,21(3):508-517.
[21]YUAN P,GAO X,ALLISON B,et al.A study of the existing problems of estimating the information transferrate in online brain-computer interfaces[J].Journal of Neural Engineering,2013,10(2):026014.
[22]SERBY H,YOM-TOV E,INBAR G F.An improved P300-based brain-computer interface[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2005,13(1):89-98.
[23]ZEYL T,YIN E,KEIGHTLEY M,et al.Adding realtime Bayesian ranks to error-related potential scores improves error detection and auto-correction in a P300speller[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2016,24(1):46-56.
[24]YIN E,ZHOU Z,JIANG J,et al.A dynamically optimized SSVEP brain-computer interface(BCI)speller[J].IEEE Transactions on Biomedical Engineering,2015,62(6):1447.
[2]YIN E,ZEYL T,SAAB R,et al.An auditory-tactile visual saccade-independent P300 brain-computer[J].International Journal of Neural Systems,2016,26(1):1650001.
[3]李佳宁,蒲江波,崔红岩,等.基于体感电刺激诱发P300的脑机接口[J].仪器仪表学报,2017,38(6):1353-1360.LI J N,PU J B,CUI H Y,et al.Electrical somatosensory based P300 for a brain computer interface system[J].Chinese Journal of Scientific Instrument,2017,38(6):1353-1360.
[4]刘晶,白艳茹,许敏鹏,等.基于Farwell范式诱发ERP的身份识别研究[J].电子测量与仪器学报,2015,29(2):221-226.LIU J,BAI Y G,XU M P,et al.Research of person identi-fication using ERP based on Farwell paradigm[J].Journal of Electronic Measurement and Instrumentation,2015,29(2):221-226.
[5]PICHIORRI F,DE V F F,CINCOTTI F,et al.Sensorimotor rhythm-based brain-computer interface training:the impact on motor cortical responsiveness[J].Journal of Neural Engineering,2011,8(2):025020.
[6]ZHANG Y,ZHOU G,JIN J,et al.Frequency recognition in SSVEP-based BCI using multiset canonical correlation analysis[J].International Journal of Neural Systems,2014,24(4):1450013.
[7]李鹏海,许敏鹏,万柏坤,等.视觉诱发电位脑-机接口实验范式研究进展[J].仪器仪表学报,2016,37(10):2340-2351.LI P H,XU M P,WAN B K,et al.Review of experimental paradigms in brain-computer interface based on visual evoked potential[J].Chinese Journal of Scientific Instrument,2016,37(10):2340-2351.
[8]安兴伟,曹勇,焦学军,等.基于视听交互刺激的认知机理与脑机接口范式研究进展[J].电子测量与仪器学报,2017,31(7):983-993.AN X W,CAO Y,JIAO X J,et al.Research on cognitive mechanism and brain computer interface application in visual auditory crossmodal stimuli[J].Journal of Electronic Measurement and Instrumentation,2017,31(7):983-993.
[9]XU M,QI H,WAN B,et al.A hybrid BCI speller paradigm combining P300 potential and the SSVEP blocking feature[J].Journal of Neural Engineering,2013,10(2):026001.
[10]VIALATTE F B,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.
[11]JIA C,GAO X,HPNG B,et al.Frequency and phase mixed coding in SSVEP-based brain-computer interface[J].IEEE Transactions on Biomedical Engineering,2011,58(1):200-206.
[12]CHEN X,WANG Y,NAKANISHI M,et al.High-speed spelling with a noninvasive brain-computer interface[J].Proceedings of the National Academy of Sciences of the United States of America,2015,112(44):e6058.
[13]ZHANG Y,PENG X,LIU T,et al.Multiple frequencies sequential coding for SSVEP-based brain-computer interface[J].Plos One,2012,7(3):e29519.
[14]BIN G,GAO X,YAN Z,et al.An online multi-channel SSVEP-based brain-computer interface using a canonical correlation analysis method[J].Journal of Neural Engineering,2009,6(4):046002.
[15]WANG Y,NAKANISHI M,WANG Y T,et al.Enhancing detection of steady-state visual evoked potentials using individual training data[C].36th Annual International Conf.of the IEEE Engineering in Medicine and Biology Society,2014:3037-3040.
[16]NAKANISHI M,WANG Y,CHEN X,et al.Enhancing detection of SSVEPs for a high-speed brain speller using task-related component analysis[J].IEEE Transactions on Biomedical Engineering,2017,65(1):104-112.
[17]SCHREUDER M,HOHNE J,BLANKERTZ B,et al.Optimizing event-related potential based brain-computer interfaces:A systematic evaluation of dynamic stopping methods[J].Journal of Neural Engineering,2013,10(3):036025.
[18]LENHARDT A,KAPER M,RITTER H J.An adaptive P300-based online brain-computer interface[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2008,16(2):121-130.
[19]JIN J,ALLISON B Z,SELLERS E W,et al.An adaptive P300-based control system[J].Journal of Neural Engineering,2011,8(3):036006.
[20]THROCKMORTON C S,COLWELL K A,RYAN D B,et al.Bayesian approach to dynamically controlling data collection in P300 spellers[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2013,21(3):508-517.
[21]YUAN P,GAO X,ALLISON B,et al.A study of the existing problems of estimating the information transferrate in online brain-computer interfaces[J].Journal of Neural Engineering,2013,10(2):026014.
[22]SERBY H,YOM-TOV E,INBAR G F.An improved P300-based brain-computer interface[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2005,13(1):89-98.
[23]ZEYL T,YIN E,KEIGHTLEY M,et al.Adding realtime Bayesian ranks to error-related potential scores improves error detection and auto-correction in a P300speller[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2016,24(1):46-56.
[24]YIN E,ZHOU Z,JIANG J,et al.A dynamically optimized SSVEP brain-computer interface(BCI)speller[J].IEEE Transactions on Biomedical Engineering,2015,62(6):1447.