基于运动想象的脑机接口关键技术研究

doi:10.3969/j.issn.0258-8021.2014. 06.02

摘要
图/表
参考文献
相关文章 (6)

全文: PDF (1061 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要基于运动想象的脑机接口技术，被广泛的认为是最具有前景的一类脑机接口，但目前在该技术的发展过程中存在着一系列急需解决的问题。本文从信号获取、特征提取、模式分类、在线系统等方面，介绍了一些解决问题的方法，特别是基于笔者长期研究工作的系列解决方案。如信号获取中能够去除低频偏置的放大器设计方法；特征识别方面针对在运动想象脑机接口中广泛使用的共空间模式方法的改进算法，使其具有更强的抗噪音能力；模式识别方面所提出的基于线性判别分析的改进算法，以较大幅度提高分类准确率。最后介绍了基于上述方法而设计实现的一种基于运动想象和运动启动电位的在线脑机接口系统。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	刘铁军^＃张锐徐鹏^＃*

关键词 ：运动想象, 放大器, 共空间模式, 模式识别, 运动启动视觉诱发电位

Abstract：Motor imagery based braincomputer interface (MI BCI) has been considered as the most promising BCI in practical application. However, several urgent problems need to be solved for MI BCI. Based on our research experience in past several years, this paper discusses the developed methods in our group for signal acquisition, feature extraction, pattern recognition and online BCI system. As for the acquisition aspect, we designed an amplifier that can remove the DC offset effectively. Several improved algorithms based on common spatial pattern (CSP) are developed to increase the immunity to noises. As for pattern recognition, several variants of linear discriminative analysis are developed to improve the recognition rates. Based on those methods, we built a hybrid online BCI system that combined motor imagery and motion onset visual evoked potential (MOVEP).

Key words： motor imagery amplifier common spatial pattern (CSP) pattern recognition motion onset visual evoked potential

基金资助:国家自然科学基金（61175117）；国家高技术研究发展计划(863计划)（2012BAI16B02）

引用本文:

刘铁军^＃张锐徐鹏^＃*. 基于运动想象的脑机接口关键技术研究[J]. 中国生物医学工程学报, 2014, 33(6): 644-651.
LIU Tie Jun^＃ZHANG Rui XU Peng^＃*. Key Techniques in Motor Imagery Based BrainComputer Interface. journal1, 2014, 33(6): 644-651.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2014. 06.02 或 http://cjbme.csbme.org/CN/Y2014/V33/I6/644

［1］Wolpaw JR, Birbaumer N, McFarland DJ, et al. Braincomputer interfaces for communication and control ［J］.Clin Neurophysiol, 2002, 113(7):67-91.
［2］Mason SG, Bashashati A, Fatourechi M, et al. A comprehensive survey of brain interface technology designs［J］. Ann Biomed Eng, 2007, 35(2):137-169.
［3］高上凯. 浅谈脑-机接口的发展现状与挑战［J］. 中国生物医学工程学报,2007,26(6):801-803.
［4］Degen T, Jackel T. A pseudodifferential amplifier for bioelectric events with DCoffset compensation using twowired amplifying electrodes［J］. IEEE Transactions on Biomedical Engineering, 2006,53(2): 300-310.
［5］郜东瑞,刘铁军,尧德中. 消除直流偏移的放大器［P］. 中国专利：2013100242650, 2013-01-23
［6］郜东瑞,刘铁军,尧德中. 脑电采集装置［P］. 中国专利：2013105136997, 2013-10-28
［7］Liao Xiang, Yao Dezhong, Wu Dan. Combining spatial filtersfor the classification of singletrial EEG in a finger movementtask ［J］. IEEE Transactions on Biomedical Engineering, 2007, 54(1): 821-831.
［8］Park C, Looney D, Rehman N, et al. Classification of motor imagery BCI using multivariate empirical mode decomposition［J］.,IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2012, 21(1):10-22.
［9］Blankertz B, Muller K, Curio G, et al. The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials［J］. IEEE Transactions on Biomedical Engineering, 2004,51(6): 1044-1051.
［10］Blankertz B, Muller K, Krusienski D, et al. The BCI competition III: validating alternative approaches to actual BCI problems［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2006, 14(2): 153-159.
［11］Zhang Rui, Xu Peng, Liu Tiejun, et al. Local temporal correlation common spatial patterns for single trial EEG classification during motor imagery ［J］. Computational and Mathematical Methods in Medicine, 2013, 2013(1): 1-7.
［12］Li Peiyang, Xu Peng, Zhang Rui, et al. L1 norm based common spatial patterns decomposition for scalp EEG BCI［J］. Biomed Eng Online, 2013, 12: 77.
［13］Xu Peng, Liu Tiejun, Zhang Rui, et al. Using particle swarm to select frequency band and time interval for feature extraction of EEG based BCI［J］. Biomedical Signal Processing and Control, 2014,10（2）: 289-295.
［14］Lei Xu, Yang Ping, Yao Dezhong, et al. An empirical bayesian framework for braincomputer interfaces［J］. IEEE Transactions on Neural Syst Rehabil Eng, 2009, 17(6): 521-529.
［15］Dornhege G, Blankertz B, Curio G, et al. Boosting bit rates in noninvasive EEG singletrial classifications by feature combination and multiclass paradigms［J］. IEEE Transactions on Biomedical Engineering, 2004,51(6): 993-1002.
［16］Zhong MJ, Lotte F, Girolami M, et al. Classifying EEG for brain computer interfaces using Gaussian processes［J］. Pattern Recognition Letters,2008,29(3): 354-359.
［17］Lal TN, Schroder M, Hinterberger T. Support vector channel selection in BCI［J］. IEEE Transactions on Biomedical Engineering, 2004,51(6): 1003-1010.
［18］Xu Peng, Yang Ping, Lei Xu, et al. An enhanced probabilistic LDA for multiclass brain computer interface［J］.PLoS One, 2011, 6(1): e14634. 
［19］Zhang Rui, Xu Peng, Guo Lanjin, et al. Zscore linear discriminant analysis for EEG based braincomputer interfaces［J］. PLoS One, 2013, 8(9): e74433.
［20］尧德中,刘铁军,雷旭,等.基于脑电的脑-机接口: 关键技术和应用前景［J］.电子科技大学学报, 2009, 38(5): 550-554.
［21］Muller S, Bastos T, Sarcinelli M. Proposal of a SSVEPBCI to command a robotic wheelchair［J］. Journal of Control, Automation and Electrical Systems, 2013, 24(2): 97-105.［22］Pfurtscheller G, Leeb R, Keinrath C, et al. Walking from thought［J］. Cognitive Brain Research,2006,1(1):145-152.