[1]张德明,殷国栋,金贤建,等.基于CSP和SFFS-SFBS的两级双向脑电导联特征选取方法[J].东南大学学报(自然科学版),2019,49(1):125-132.[doi:10.3969/j.issn.1001-0505.2019.01.018]
 Zhang Deming,Yin Guodong,Jin Xianjian,et al.Two-stage and bi-direction feature selection method for EEG channel based on CSP and SFFS-SFBS[J].Journal of Southeast University (Natural Science Edition),2019,49(1):125-132.[doi:10.3969/j.issn.1001-0505.2019.01.018]
点击复制

基于CSP和SFFS-SFBS的两级双向脑电导联特征选取方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
49
期数:
2019年第1期
页码:
125-132
栏目:
信息与通信工程
出版日期:
2019-01-20

文章信息/Info

Title:
Two-stage and bi-direction feature selection method for EEG channel based on CSP and SFFS-SFBS
作者:
张德明1殷国栋1金贤建2庄伟超1
1东南大学机械工程学院, 南京 211189; 2上海大学机电工程与自动化学院, 上海 200444
Author(s):
Zhang Deming1 Yin Guodong1 Jin Xianjian2 Zhuang Weichao1
1School of Mechanical Engineering, Southeast University, Nanjing 211189, China
2School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China
关键词:
多任务运动想象 导联选取 公共空间模式 顺序浮动双向选择算法
Keywords:
multi-class motor imagery channel selection common spatial pattern(CSP) sequential floating forward selection-sequential floating backward selection algorithm(SFFS-SFBS)
分类号:
TN911.7
DOI:
10.3969/j.issn.1001-0505.2019.01.018
摘要:
针对多任务运动想象条件下脑电导联选取质量差、搜索时间长的问题, 提出了一种基于公共空间模式(CSP)和顺序浮动双向选择算法(SFFS-SFBS)的两级导联特征选取方法. 首先, 结合空域滤波分析各个被试的时频特性, 确定相应的特征时间和特征频率; 然后由训练集的CSP滤波系数计算各个导联在特征提取过程中的权重大小, 根据权重排序缩小导联搜索空间; 最后, 运用以训练集交叉检验正确率为评价准则的SFFS-SFBS算法在相应的搜索空间内双向选择最优的导联序列. 实验结果表明, 在保证较高分类正确率的前提下, 与传统SFFS算法和改进SFFS算法相比, 该方法选取的导联数量分别减少了51.36%, 47.52%, 对应的搜索时间缩短了90.95%, 80%. 因此, 基于CSP和SFFS-SFBS的两级特征选取方法可快速选择优质导联序列, 有效提高脑机接口的实际使用性能.
Abstract:
To solve the problem of poor quality and long searching time for the selection in electroencephalogram(EEG)channel under the condition of multi-class motor imagery, a two-stage channel selection method based on common spatial pattern(CSP)and sequential floating forward selection-sequential floating backward selection algorithm(SFFS-SFBS)was proposed. First, the characteristic time and the characteristic frequency were determined by analyzing the time-frequency properties of each subject with spatial filtering. Then, the weight about each channel in the feature extraction process was calculated using the CSP filtering coefficients of the training dataset, and the channel search space was reduced according to the rank of the weight. Finally, the SFFS-SFBS algorithm with the cross-validation accuracy of the training dataset as evaluation criterion was used to select the optimal channel sequence in the reduced search space. The experimental results demonstrate that the number of channels selected by the method is reduced by 51.36% and 47.52%, respectively, and the corresponding search time is shortened by 90.95% and 80% compared with the traditional SFFS algorithm and the improved SFFS algorithm under the premise of a higher classification accuracy. Therefore, the proposed method can select the channel sequence more accurately and quickly, improving of the brain-computer interface in practice.

参考文献/References:

[1] Sajda P, Muller K R, Shenoy K. Brain-computer interfaces[J]. IEEE Signal Processing Magazine, 2008, 25(1): 16-17. DOI:10.1109/msp.2008.4408438.
[2] Lotte F, Bougrain L, Cichocki A, et al. A review of classification algorithms for EEG-based brain-computer interfaces: A 10 year update[J]. Journal of Neural Engineering, 2018, 15(3): 031005. DOI:10.1088/1741-2552/aab2f2.
[3] Pfurtscheller G, Lopes da Silva F H. Event-related EEG/MEG synchronization and desynchronization: Basic principles[J]. Clinical Neurophysiology, 1999, 110(11):1842-1857. DOI:10.1016/s1388-2457(99)00141-8.
[4] Handiru V S, Prasad V A. Optimized bi-objective EEG channel selection and cross-subject generalization with brain-computer interfaces[J]. IEEE Transactions on Human-Machine Systems, 2016, 46(6):777-786. DOI:10.1109/thms.2016.2573827.
[5] Ge S, Wang R M, Yu D C. Classification of four-class motor imagery employing single-channel electroencephalography[J]. PLoS One, 2014, 9(6): e98019. DOI:10.1371/journal.pone.0098019.
[6] Lal T N, Schr�F6;der M, Hinterberger T, et al. Support vector channel selection in BCI[J]. IEEE Transactions on Biomedical Engineering, 2004, 51(6): 1003-1010. DOI:10.1109/tbme.2004.827827.
[7] Yang Y, Bloch I, Chevallier S, et al. Subject-specific channel selection using time information for motor imagery brain-computer interfaces[J]. Cognitive Computation, 2016, 8(3): 505-518. DOI:10.1007/s12559-015-9379-z.
[8] Astigarraga A, Arruti A, Muguerza J, et al. User adapted motor-imaginary brain-computer interface by means of EEG channel selection based on estimation of distributed algorithms[J]. Mathematical Problems in Engineering, 2016, 2016: 1435321. DOI:10.1155/2016/1435321.
[9] Liu H, Yu L. Toward integrating feature selection algorithms for classification and clustering[J]. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(4): 491-502. DOI:10.1109/tkde.2005.66.
[10] Chandrashekar G, Sahin F. A survey on feature selection methods[J]. Computers & Electrical Engineering, 2014, 40(1): 16-28. DOI:10.1016/j.compeleceng.2013.11.024.
[11] Alotaiby T, El-Samie F E A, Alshebeili S A, et al. A review of channel selection algorithms for EEG signal processing[J]. EURASIP Journal on Advances in Signal Processing, 2015, 2015: 66-01-66-21. DOI:10.1186/s13634-015-0251-9.
[12]Wang G, Ma J, Yang S. IGF-bagging: Information gain based feature selection for bagging[J]. International Journal of Innovative Computing Information and Control, 2011, 7(11):6247-6259.
[13]Solorio-Fernández S, Carrasco-Ochoa J A, Martínez-Trinidad J F. A new hybrid filter-wrapper feature selection method for clustering based on ranking[J]. Neurocomputing, 2016, 214: 866-880. DOI:10.1016/j.neucom.2016.07.026.
[14]Qiu Z Y, Jin J, Lam H K, et al. Improved SFFS method for channel selection in motor imagery based BCI[J]. Neurocomputing, 2016, 207: 519-527. DOI:10.1016/j.neucom.2016.05.035.
[15]Ding S F, Zhu Z B, Zhang X K. An overview on semi-supervised support vector machine[J]. Neural Computing and Applications, 2017, 28(5): 969-978. DOI:10.1007/s00521-015-2113-7.
[16]周蚌艳, 吴小培, 吕钊, 等. 基于共空间模式方法的多类运动想象脑电的导联选择[J]. 生物医学工程学杂志, 2015, 32(3):520-525.
  Zhou B Y, Wu X P, Lü Z, et al. Channel selection for multi-class motor imagery based on common spatial pattern[J]. Journal of Biomedical Engineering, 2015, 32(3):520-525.(in Chinese)
[17]郑戍华, 闫琛, 王向周. 一种重复二分CSP4类运动想象脑电信号特征提取算法[J]. 北京理工大学学报, 2016, 36(8): 844-850. DOI:10.15918/j.tbit1001-0645.2016.08.013.
Zheng S H, Yan C, Wang X Z. A repeated bisection CSP feature extraction algorithm of four-class motor imagery EEG[J]. Transactions of Beijing Institute of Technology, 2016, 36(8): 844-850. DOI:10.15918/j.tbit1001-0645.2016.08.013. (in Chinese)
[18]Khorshidtalab A, Salami M J E, Akmeliawati R. Motor imagery task classification using transformation based features[J]. Biomedical Signal Processing and Control, 2017, 33: 213-219. DOI:10.1016/j.bspc.2016.12.006.

备注/Memo

备注/Memo:
收稿日期: 2018-07-06.
作者简介: 张德明(1993—),男,硕士生;殷国栋(联系人),男,博士,教授,博士生导师,ygd@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(U1664258, 51575103)、国家重点研发计划资助项目(2016YFB0100906).
引用本文: 张德明,殷国栋,金贤建,等.基于CSP和SFFS-SFBS的两级双向脑电导联特征选取方法[J].东南大学学报(自然科学版),2019,49(1):125-132. DOI:10.3969/j.issn.1001-0505.2019.01.018.
更新日期/Last Update: 2019-01-20