基于概率协作表示的运动想象脑电分类算法

doi:10.3976/j.issn.1002-4026.2018.02.017

山东科学 ›› 2018, Vol. 31 ›› Issue (2): 105-112.doi: 10.3976/j.issn.1002-4026.2018.02.017

基于概率协作表示的运动想象脑电分类算法

崔丽霞，杨济民*，常洪丽

山东师范大学物理与电子科学学院，山东济南 250358

收稿日期:2017-11-20 出版日期:2018-04-20 发布日期:2018-04-20
通信作者: 杨济民(1961—),男,教授,研究方向为电路与系统。E-mail:jmyang@sdnu.edu.cn E-mail:jmyang@sdnu.edu.cn
作者简介:崔丽霞(1991—),女,硕士研究生,研究方向为脑机接口的相关算法。E-mail:1562027422@qq.com
基金资助:
山东省重点研发计划（2017GGX10102）

Motor imagery EEG classification algorithm based on probabilistic collaboration representation

CUI Li-xia, YANG Ji-min*,CHANG Hong-li

School of Physics and Electronics, Shandong Normal University, Jinan 250358, China

Received:2017-11-20 Online:2018-04-20 Published:2018-04-20

摘要/Abstract

摘要：

在脑机接口的研究中，针对运动想象脑电信号的特征识别，提出了一种基于概率协作表示的分类方法（probabilistic collaborative representation based classification, ProCRC），通过比较测试样本在每个类别中的最大可能性，从而确定其所属的类别。采用BCI竞赛数据库Ⅲ中的数据集Ⅰ，利用S变换进行特征提取，然后对不同的分类器进行比较，以分类准确率作为评价标准验证了该算法的有效性。该算法的分类准确率能够达到90%,为脑机接口系统分类算法的研究提供了新思路。

关键词: 脑机接口, 运动想象, 概率协作表示, S变换

Abstract:

In the research of brain-computer interface, a classification method for recognizing the features of motor imagery EEG signals based on probabilistic collaborative representation (ProCRC) was proposed in this paper. The maximum likelihood that a test sample belonged to each of the multiple classes was compared, so as to determine the final classification that it belonged to.Performance of this method was tested using the data set of BCI competition Ⅲ. Firstly, the S transform was used to extract the electroencephalography features, and then different classifiers were compared. Finally, the classification accuracy was used as the evaluation criterion to verify the effectiveness of the algorithm. The accuracy of the algorithm proposed in this paper could reach 90%, which provided a new idea for the research of the classification algorithm of the braincomputer interface system.

Key words: probabilistic collaborative representation, motor imagery, S-transform, brain-computer interface

中图分类号:

TP302.7

崔丽霞，杨济民，常洪丽. 基于概率协作表示的运动想象脑电分类算法[J]. 山东科学, 2018, 31(2): 105-112.

CUI Li-xia, YANG Ji-min,CHANG Hong-li. Motor imagery EEG classification algorithm based on probabilistic collaboration representation[J]. SHANDONG SCIENCE, 2018, 31(2): 105-112.

参考文献

［1］WOLPAW J R, BIRBANME R N, McFARLAND D J, et al. Braincomputer Interface for communication and control[J]. Clinical Neurophysiology,2002, 113(6):767791.
［2］GAO S K, WANG Y J, GAO X R, et al. Visual and auditory braincomputer interfaces[J]. IEEE Transactions on Biomedical Engineering, 2014, 61(5):14361447.
［3］XU F, ZHOU W, ZHEN Y, et al. Classification of ECoG with modified Stransform for brain computer interface[J]. Journal of Computational Information Systems, 2014, 10(18):80298041.
［4］潘泉,张磊,孟晋丽,等.小波滤波方法及应用[M].北京:清华大学出版社,2006.
［5］STOCKWELL R G, MANSINHA L, LOWE R P, Localization of the complex spectrum：the S transform[J].IEEE Transaction on Signal Processing, 1996, 44(4):9981001.
［6］YAN Y, ZHU H. The generalization of discrete Stockwell transforms[M]//19th European Signal Processing Conference.[S.l.]：IEEE,2011:12091213.
［7］STOCKWELL R G. Abasis for efficient representation of the Stransform[J].Digital Signal Processing,2007,17(1):371393.
［8］UYAR M, YILDIRIM S, GENCOGLU M T, An expert system based on Stransform and neural network for automatic classification of power quality disturbances[J]. Expert Systems with Applications, 2009, 36(3):59625975.
［9］PINNEGAR C R, MANSINHA L. The stransform with windows of arbitrary and varying shape[J]. Geophysics, 2003, 68(10):381385.
［10］CAIS J, ZHANG L, ZUO W M, et al. A probabilistic collaborative representation based approach for pattern classification[M]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).[S.l.]: IEEE,2016:29502959.
［11］WRIGHT J, YANG A Y, GANESH A, et al. Robust face recognition via sparse representation[J].IEEE transactions on pattern analysis and machine intelligence, 2009, 31(2):210227.
［12］ZHANG L, YANG M, FENG X C. Sparse representation or collaborative representation: Which helps face recognition? [M]//2011 IEEE International Conference on Computer Vision. [S.l.]: IEEE, 2011:471478.
［13］SHIN Y, LEE S, AHN M, et al. Noise robustness analysis of sparse representation based classification method for nonstationary EEG signal classification[J].Biomedical Signal Processing and Control,2015, 21:818.
［14］MIAO M, WANG A, LIU F. A spatialfrequencytemporal optimized feature sparse representationbased classification method for motor imagery EEG pattern recognition[J]. Medical & Biological Engineering & Computing, 2017, 55(9):15891603.
［15］McFADDEN P D, COOK J G, FORSTER L M. Decomposition of gear vibration signals by the generalized Stransform[J].Mechanical Systems and Signal Processing, 1999,13(5):691707.
［16］GHAFFARZADEH H. A classification method for pulselike ground motions based on Stransform[J].Natural Hazards,2016,84(1):116.
［17］SEJDI C＇E，DJUROVI C＇ I，JIANG J.A window width optimized stransform[J].EURASIP Journal on Advances in Signal Processing,2007,2008(1):923938.
［18］BLANKERTZ B.BCI Competition III[EB/OL]. [20171011]. http://www.bbci.de/competition/iii/#data_set_i.
［19］LAL T N, HINTERBERGER T, WIDMAN G, et al. Methods towards invasive human brain computer interfaces[J]. Advances in neural information processing systems, 2005, 17: 737744.
［20］XU F, ZHOU W, ZHEN Y, et al. Classification of motor imagery tasks for electrocorticogram based braincomputer interface[J].Biomedical Engineering Letters,2014,4(2):149157.
［21］HOFFMANN U, VESIN J M, EBRAHIMI T, et al. An efficient P300based braincomputer interface for disabled subjects[J]. Journal of Neuroscience Methods, 2008, 167(1):115125.
［22］ZHANG Y,ZHOU W,YUAN S, et al. Seizure detection method based on fractal dimension and gradient boosting[J].EpilepsyBehavior,2015,43:3038.

基于概率协作表示的运动想象脑电分类算法

Motor imagery EEG classification algorithm based on probabilistic collaboration representation

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 0