基于SVM_RFE的多任务导联选择算法建模

doi:10.16182/j.issn1004731x.joss.201812002

系统仿真学报 ›› 2018, Vol. 30 ›› Issue (12): 4506-4512.doi: 10.16182/j.issn1004731x.joss.201812002

• 专栏:生机电一体化系统建模与仿真 • 上一篇下一篇

基于SVM_RFE的多任务导联选择算法建模

冯建奎, 金晶^*, 王蓓, 牛玉刚, 王行愚

华东理工大学信息科学与工程学院,上海 200237

收稿日期:2018-09-27 修回日期:2018-10-26 出版日期:2018-12-10 发布日期:2019-01-03
通讯作者: 金晶(1981-),男,上海崇明,博士,教授,研究方向为脑机接口,模式识别。
作者简介:冯建奎(1992-),男,山东菏泽,硕士,研究方向为脑机接口,信号处理。
基金资助:
国家重点研发计划(2017YFB13003002),国家自然科学基金(61573142, 61773164, 91420302), 111引智计划(B17017)

Multi-tasks Channel Selection Algorithmic Modeling Based on SVM-RFE

Feng Jiankui, Jin Jing^*, Wang Bei, Niu Yugang, Wang Xingyu

College of Information Science and Engineering, East China University, Shanghai 200237, China

Received:2018-09-27 Revised:2018-10-26 Online:2018-12-10 Published:2019-01-03

摘要/Abstract

摘要： 在BCI (Brain computer interface)的研究中,导联选择能够用于确定与目标任务关联较大的脑功能区域。以往的导联选择方法都是基于一个数据集进行统一的导联选择,不同任务下的对应脑区是不一样的,无法抑制同一数据集中不同任务特征的干扰。基于运动想象脑电数据展开相关研究,利用SVM_RFE (Support vector machine recursive feature elimination)导联选择方法以召回率作为依据为两类运动任务分别选择最适合的导联。研究结果表明,基于SVM_RFE多任务导联选择方法在平均分类准确率上优于传统的SVM_RFE导联选择方法。

关键词: 脑机接口, 运动想象, SVM_RFE, 多任务

Abstract: Channel selection is used to locate the mental task related brain area in the brain computer interface systems. In the previous studies, the channels were selected based on the data recoded from the multi-mental tasks. However, the different mental tasks are corresponding to the different brain area. If one same brain area is selected for different mental tasks, the features of one mental task would be noises of another mental task. In this paper, a new method was presented to solve this problem based on the data of motor imagery tasks. The SVM-RFE method was used to select the channels for each motor imagery task based on recall rate. The result showed that the proposed channel selection method was superior to the traditional method in classification accuracy.

Key words: brain-computer interface, motor imagery, SVM-RFE, multi-tasks

中图分类号:

TP273

冯建奎, 金晶, 王蓓, 牛玉刚, 王行愚. 基于SVM_RFE的多任务导联选择算法建模[J]. 系统仿真学报, 2018, 30(12): 4506-4512.

Feng Jiankui, Jin Jing, Wang Bei, Niu Yugang, Wang Xingyu. Multi-tasks Channel Selection Algorithmic Modeling Based on SVM-RFE[J]. Journal of System Simulation, 2018, 30(12): 4506-4512.

参考文献

[1] Lin Y, Sheng X, Zhang D, et al.A BCI System Based on Somatosensory Attentional Orientation[J]. IEEE Trans Neural Syst Rehabil Eng (S2095-4409), 2017, 25(1): 78-87.
[2] Jin J, Sellers E W, Zhou S, et al.A P300 Brain-Computer Interface Based on a Modification of the Mismatch Negativity Paradigm[J]. International Journal of Neural Systems (S0129-0657), 2015, 25(3): 1550011.
[3] Önder Aydemir.Classification of 2-dimensional cursor movement imagery EEG signals[C]// International Conference on Telecommunications and Signal Processing. USA: IEEE, 2016: 370-373.
[4] Feng J, Yin E, Jin J, et al.Towards correlation-based time window selection method for motor imagery BCIs[J]. Neural Netw (S0893-6080), 2018, 102: 87-95.
[5] Thiyam D, Cruces S, Olias J, et al.Optimization of Alpha-Beta Log-Det Divergences and their Application in the Spatial Filtering of Two Class Motor Imagery Movements[J]. Entropy (S1099-4300), 2017, 19(3): 89.
[6] Sun Y, Ye N, Yang J.An asynchronous MI-BCI system based on masterslave features[C]// International Congress on Image and Signal Processing, Biomedical Engineering and Informatics. USA: IEEE, 2017: 1456-1461.
[7] Sun H, Zhang Y, Gluckman B J, et al.Optimal-channel Selection Algorithms in Mental Tasks based Brain-computer Interface[C]// International Conference. 2018: 118-123.
[8] Qiu Z, Jin J, Lam H K, et al.Improved SFFS method for channel selection in motor imagery based BCI[J]. Neurocomputing (S0925-2312), 2016, 207(C): 519-527.
[9] Wang Y, Gao S, Gao X.Common Spatial Pattern Method for Channel Selection in Motor Imagery Based Brain-computer Interface.[C]// Engineering in Medicine and Biology Society, 2005. Ieee-Embs 2005. International Conference of the. USA: IEEE, 2005: 5392-5395.
[10] Goksu F, Ince N F, Tewfik A H.Greedy solutions for the construction of sparse spatial and spatio-spectral filters in brain computer interface applications[J]. Neurocomputing (S0925-2312), 2013, 108(5): 69-78.
[11] Tam W K, Hu X L, Tong K Y.Channel selection in chronic stroke rehabilitation[J]. Ifac Proceedings Volumes (S1474-6670), 2013, 46(20): 339-344.
[12] Shan H, Xu H, Zhu S, et al.A novel channel selection method for optimal classification in different motor imagery BCI paradigms[J]. BioMedical Engineering OnLine (S1475-925X), 2015, 14(1): 1-18.
[13] Guyon I, Weston J, Barnhill S.Gene selection for cancer classification using support vector machines[J]. Machine Learning(S1573-0565), 2002, 46: 389-422.
[14] Duan K, Rajapakse J C.A variant of SVM-RFE for gene selection in cancer classification with expression data[C]// Computational Intelligence in Bioinformatics and Computational Biology, 2004. CIBCB '04. Proceedings of the 2004 IEEE Symposium on. USA: IEEE, 2004: 49-55.
[15] Ang K K, Guan C.Brain-computer interface in stroke rehabilitation[J]. Journal of Computer Science and Engineering (S1976-4677), 2013, 7(2): 139-142.
[16] Arvaneh M, Guan C, Kai K A, et al.Spatially sparsed Common Spatial Pattern to improve BCI performance[C]// IEEE International Conference on Acoustics, Speech and Signal Processing. USA: IEEE, 2011: 2412-2415.
[17] Lotte F, Guan C.Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms[J]. IEEE Trans Biomed Eng (S1573-0565), 2011, 58(2):355-362.
[18] Selim S, Tantawi M, Shedeed H, et al.Reducing Execution Time for Real-Time Motor Imagery Based BCI Systems[C]// Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2016. Germany: Springer International Publishing, 2016.
[19] Dai M, Zheng D, Liu S, et al.Transfer Kernel Common Spatial Patterns for Motor Imagery Brain-Computer Interface Classification[J]. Computational & Mathematical Methods in Medicine (S1748-670X), 2018: 1-9.
[20] Belwafi K, Romain O, Gannouni S, et al.An embedded implementation based on adaptive filter bank for brain-computer interface systems[J]. Journal of neuroscience methods (S0165-0270), 2018, 305(15): 1-6.
[21] Hasan B A S, Gan J Q, Zhang Q. Multi-objective evolutionary methods for channel selection in brain-computer interfaces: some preliminary experimental results[C]// Evolutionary Computation (CEC), 2010 IEEE Congress on. IEEE, 2010: 1-6.
[22] Park C, Looney D, ur Rehman N, et al. Classification of motor imagery BCI using multivariate empirical mode decomposition[J]. USA: IEEE Transactions on neural systems and rehabilitation engineering (S1534-4320), 2013, 21(1): 10-22.
[23] Zhang H, Guan C, Kai K A, et al.BCI Competition IV - Data Set I: Learning Discriminative Patterns for Self-Paced EEG-Based Motor Imagery Detection[J]. Frontiers in Neuroscience (S1662-453X), 2012, 6: 7.

基于SVM_RFE的多任务导联选择算法建模

Multi-tasks Channel Selection Algorithmic Modeling Based on SVM-RFE

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	邓欣, 龙灿, 米建勋, 张博宪, 孙开伟, 王进. 基于多域特征与随机子空间集成的脑电分类[J]. 系统仿真学报, 2020, 32(9): 1787-1798.
[2]	蔡兴泉, 涂宇欣, 葛亚坤, 杨哲. 基于CNN网络和多任务损失函数的实时叶片识别[J]. 系统仿真学报, 2020, 32(7): 1279-1286.
[3]	杨帮华, 李博. 基于脑机接口的康复训练系统[J]. 系统仿真学报, 2019, 31(2): 174-180.
[4]	纪连恩, 赵妮, 梁适宜, 黄博. 支持多用户的三维地震体远程可视化关键技术[J]. 系统仿真学报, 2018, 30(7): 2540-2549.
[5]	陈超, 平尧, 郝斌, 徐瑞. 基于脑机接口技术的写字系统建模仿真与实现[J]. 系统仿真学报, 2018, 30(12): 4499-4505.