基于马尔科夫切换过程的运动想象信号分类

doi:10.3969/j.issn.0258-8021.2014. 06.05

摘要
图/表
参考文献
相关文章 (7)

全文: PDF (2214 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要隐马尔科夫模型（HMM）在脑机接口（BCI）领域中已经得到很好的应用，尤其是在运动想象（MI）信号的分类中。但是，很多传统的方法只是利用隐马尔科夫模型描述信号的动态特性，再根据观测数据求得模型参数，然后进行信号分类。由于脑电信号低信噪比、高维数和状态复杂的特点，在研究中先用分层Dirichlet 过程（HDP）描述MI信号，利用HDP自聚类特性，然后使用AR模型描述MI信号的时间特性，最后结合马尔科夫切换过程（MSP）描述MI信号的动态特性，以此来充分地描述MI信号。随后对实验室采集的数据和2003年BCI国际大赛的部分数据，使用HDPARHMM模型对MI信号分类，获得很好的分类效果，准确率分别是9900%、9200%和7246%。实验结果表明，所提出的方法可以取得更好的运动想象信号分类。

	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
	吴俊¹杨雅² 俞祝良^1#*顾正晖¹ 李远清^1#

关键词 ：运动想象, 脑机接口, 马尔科夫切换, AR模型, 信号分类

Abstract：Hidden Markov model (HMM) is well applied in brain computer interface, especially in the classification of motor imagery(MI) electroencephalogram (EEG) signal. Conventional methods use HMM to model EEG signal, then use the observed signal under controlled state to estimate the HMM parameters and finally classify the EEG signal through the trained HMMs. However, due to the characteristics of low signaltonoise ratio(SNR), high dimensionality and complexity of motor imagery EEG signal, HMM cannot fully describe the dynamic property of motor imagery EEG signal. In this paper, we use hierarchical Dirichlet process (HDP) with selfclustering ability to describe MI signals and then use AR/VAR model to highlight the time property of MI signal. Finally we combine them with Markov switching processing (MSP) so that we can get more information of MI signal. In order to verify this method, we tested the algorithm on our inhouse data and some of the 2003 BCI international competition data sets. High accuracy on classification of MI is obtained.

Key words： motor imagery rain computer interface (BCI) Markov switching processes AR model signal classification

基金资助:广东省自然科学基金（S2012020010945）；国家自然科学基金 (61105121,61175114,91120305)

引用本文:

吴俊¹杨雅² 俞祝良^1#*顾正晖¹ 李远清^{1#WU Jun¹YANG Ya²YU ZhuLiang^1#*GU Zheng Hui¹LI YuanQing^1#. Motor Imagery Signal Classification Based on HDP AR HMM. journal1, 2014, 33(6): 666-672.}

链接本文:

http://cjbme.csbme.org/CN/ 10.3969/j.issn.0258-8021.2014. 06.05 或 http://cjbme.csbme.org/CN/Y2014/V33/I6/666

［1］Vidal JJ. Toward direct braincomputer communication ［J］. Annual Review of Biophysics and Bioengineering, 1973, 2(1):157-180.
［2］Wolpaw JR, McFarland DJ, Vaughan TM. Braincomputer interface research at the Wadsworth Center ［J］. IEEE Transactions on Rehabilitation Engineering, 2000,8(2):222-226.
［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］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．
［5］Obermaier B, Neuper C, Guger C, et al. Information transfer rate in a fiveclasses braincomputer interface ［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2001, 9(3):283-288.
［6］Bishop CM, Nasser MN. Pattern Recognition and Machine Learning ［M］. New York: Springer, 2006. 
［7］Obermaier BG, Guger C, Neuper C, et al. Hidden Markov models for online classification of single trial EEG data ［J］. Pattern Recognition Letters,2001,22(12): 1299-1309. ［8］Rabiner L. A tutorial on hidden Markov models and selected applications in speech recognition ［J］. Proceedings of the IEEE, 1989, 77(2):257-286.
［9］Faisan S, Thoraval L, Armspach JP, et al. Unsupervised learning and mapping of active brain functional MRI signals based on hidden semiMarkov event sequence models ［J］. IEEE Transactions on Medical Imaging, 2005, 24(2):263-276.
［10］Fox EB, Sudderth EB, Jordan MI, et al. A sticky HDPHMM with application to speaker diarization ［J］.The Annals of Applied Statistics, 2011, 5(2A):1020-1056.
［11］Fox EB, Sudderth EB, Jordan MI, et al. Bayesian nonparametric methods for learning Markov switching processes ［J］. IEEE Signal Processing Magazine, 2010,27(6): 43-54. 
［12］Willsky AS, Sudderth EB, Jordan MI, et al. Nonparametric Bayesian learning of switching linear dynamical systems ［J］.Advances in Neural Information Processing Systems, 2008,21:457-464.
［13］Yang Y, Yu Z, Gu Z, et al. A new method for motor imagery classification based on hidden Markov model ［C］//Industrial Electronics and Applications (ICIEA). Singapore city: IEEE, 2012:1588-1591. 
［14］Lu R, David BD, Lawrence C. The dynamic hierarchical Dirichlet process［C］//Proceedings of the 25th International Conference on Machine Learning. Helsinki: ACM, 2008:824-831. 
［15］周建英, 王飞跃, 曾大军. 分层 Dirichlet 过程及其应用综述［J］. 自动化学报, 2011,37(4):389-407.
［16］Mousavi SR, Niknazar MB. Vosoughi V. Epileptic seizure detection using AR model on EEG signals［C］ //Biomedical Engineering Conference. Cairo: IEEE, 2008:1-4. 
［17］Neal RM. Markov chain sampling methods for Dirichlet process mixture models ［J］.Journal of Computational and Graphical Statistics, 2000,9(2): 249-265. ［18］Xu T, Zhang Z, Long B, et al. Evolutionary clustering by hierarchical dirichlet process with hidden markov state［C］ //International Conference on Data Mining.Pisa: IEEE,2008:658-667.