[1]佘青山,马鹏刚,马玉良,等.基于张量线性拉普拉斯判别的肌电特征提取方法[J].东南大学学报(自然科学版),2017,47(6):1117-1122.[doi:10.3969/j.issn.1001-0505.2017.06.006]
　She Qingshan,Ma Penggang,Ma Yuliang,et al.EMG feature extraction based on tensor linear Laplacian discriminant[J].Journal of Southeast University (Natural Science Edition),2017,47(6):1117-1122.[doi:10.3969/j.issn.1001-0505.2017.06.006]
点击复制

基于张量线性拉普拉斯判别的肌电特征提取方法()
分享到：

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

卷:
47
期数:
2017年第6期
页码:
1117-1122
栏目:
计算机科学与工程
出版日期:
2017-11-20

文章信息/Info

Title:
EMG feature extraction based on tensor linear Laplacian discriminant
作者:
佘青山; 马鹏刚; 马玉良; 孟明
杭州电子科技大学智能控制与机器人研究所, 杭州 310018
Author(s):
She Qingshan;  Ma Penggang;  Ma Yuliang;  Meng Ming
Institute of Intelligent Control and Robotics, Hangzhou Dianzi University, Hangzhou 310018, China
关键词:
表面肌电信号;  人机交互;  特征提取;  张量线性拉普拉斯判别
Keywords:
surface electromyogram;  human-robot interaction;  feature extraction;  tensor linear Laplacian discriminant
分类号:
TP391
DOI:
10.3969/j.issn.1001-0505.2017.06.006
摘要:
为了有效分析表面肌电(sEMG)信号蕴含的时-频-空域多维特征,提出了一种基于张量线性拉普拉斯判别(TLLD)的sEMG特征提取方法.首先对sEMG信号做复Morlet小波变换,构造具有时间、空间、频率、任务的四阶张量数据;然后运用TLLD分析方法获得投影矩阵,把训练集和测试集分别投影在投影矩阵中获得具有较大区分度的特征;最后使用分类器对腕屈、腕伸、上臂内旋、上臂外旋、握拳、伸拳6种动作模式进行识别.实验结果表明, 所提方法平均分类准确率达到了98%以上,识别性能优于均方根、自回归系数、张量高阶判别分析3种特征提取方法.
Abstract:
To analyze the multi-dimensional characteristics in the time-frequency-space domain implied in the surface electromyogram(sEMG)signlas, a novel feature extraction method for sEMG was proposed based on tensor linear Laplacian discriminant(TLLD)First, sEMG signals were transformed into the 4-D tensor data including the information of temporal, spatial, spectral, and trials by complex morlet wavelet. Secondly, the TLLD analysis algorithm was used to obtain the projection matrix, and the training and test sets were projected into the projection matrix to obtain features with greater discrimination. Finally, the linear discriminant analysis algorithm was used to identify six forearm movements, including the wrist flexion, wrist extension, forearm pronation, forearm supination, hand close, and hand open. The experimental results show that the accuracy of the proposed method is more than 98%, and its recognition performance is better than that of three methods of the root mean square, autoregressive coefficient and tensor high order discriminant analysis.

参考文献/References:

[1] 侯增广, 赵新刚, 程龙, 等.康复机器人与智能辅助系统的研究进展[J]. 自动化学报, 2016, 42(12): 1765-1779. DOI:10.16383/jaas2016y000006.
Hou Zengguang, Zhao Xingang, Cheng Long, et al. Recent advances in rehabil-itation robots and intelligent assistance systems[J]. Acta Automatica Sinica, 2016, 42(12): 1765-1779.DOI:10.16383/jaas2016y000006. (in Chinese)
[2] 丁其川, 熊安斌, 赵新刚, 等.基于表面肌电的运动意图识别方法研究及应用综述[J]. 自动化学报, 2016, 42(1): 13-25.DOI:10.16383/jaas2016c140563.
Ding Qichuan, Xiong Anbin, Zhao Xingang, et al. A review on researches and applications of sEMG-based motion intent recognition methods[J]. Acta Automatica Sinica, 2016, 42(1): 13-25.DOI:10.16383/jaas2016c140563. (in Chinese)
[3] 王涛, 侯文生, 吴小鹰,等.用于肌电假肢手控制的表面肌电双线性模型分析[J]. 仪器仪表学报, 2014, 35(8): 1907-1913.
　　Wang Tao,Hou Wensheng,Wu Xiaoying, et al. Analysis of the sEMG bilinear model for the control of hand prosthesis[J]. Chinese Journal of Scientific Instrument, 2014, 35(8): 1907-1913.(in Chinese)
[4] 刘建, 邹任玲, 张东衡, 等.表面肌电信号特征提取方法研究发展趋势[J]. 生物医学工程学进展, 2015, 36(3): 164-168. DOI:10.3969/jissn1674-1242.2015.02.009.
Liu Jian,Zou Renling,Zhang Dongheng, et al. Research and development trend of feature extraction methods of surface electromyogrphic signals [J]. Progress in Biomedical Engineering, 2015, 36(3): 164-168. DOI:10.3969/jissn1674-1242.2015.02.009. (in Chinese)
[5] Vervliet N, Debals O, Sorber L, et al. Breaking the curse of dimensionality using decompositions of incomplete tensors: Tensor-based scientific computing in big data analysis [J]. IEEE Signal Processing Magazine, 2014, 31(5): 71-79. DOI:10.1109/MSP2014.2329429.
[6] Papalexakis E E, Faloutsos C, Sidiropoulos N D. Tensors for data mining and data fusion: Models, applications, and scalable algorithms [J]. ACM Transactions on Intelligent Systems and Technology, 2016, 8(2): 16-1-16-44. DOI: http://dxdoiorg/10.1145/2915921.
[7] Vasilescu M A O, Terzopoulos D. TensorTextures: Multilinear image-based rendering [J]. ACM Transactions on Graphics, 2004, 23(3): 336-342. DOI: 10.1145/1186562.1015725.
[8] Savas B, Elden L. Handwritten digit classification using higher order singular value decomposition [J]. Pattern Recognition, 2007, 40(3): 993-1003. DOI: 10.1016/jpatcog2006.08.004.
[9] Zhang J, Xu C, Jing P, et al. A tensor-driven temporal correlation model for video sequence classification[J]. IEEE Signal Processing Letters, 2016, 23(9): 1246-1249. DOI: 10.1109/LSP2016.2577601.
[10] Phan A H, Cichocki A, Vu-Dinh T. A tensorial approach to single trial recognition for brain computer interface [C]//Proceedings of IEEE International Conference on Advanced Technologies for Communications. Ho Chi Minh City, Vietnam, 2010: 138-141. DOI: 10.1109/ATC2010.5672697.
[11] Li L, Boulware D. High-order tensor decomposition for large-scale data analysis [C]//Proceedings of IEEE International Congress on Big Data. New York, USA, 2015: 665-668. DOI: 10.1109/BigdDataCongress2015.104.
[12] Phan A H, Cichocki A. Tensor decompositions for feature extraction and classification of high dimensional datasets [J]. Nonlinear Theory and Its Applications, 2010, 1(1): 37-68. DOI: 10.1587/nolta1.37.
[13] Zhang W, Lin Z, Tang X. Tensor linear Laplacian discrimination(TLLD)for feature extraction [J]. Pattern Recognition, 2009, 42(9): 1941-1948.DOI: 10.1016/jpatcog2009.01.010.
[14] 皋军, 王士同, 王晓明,等.基于语境距离度量的拉普拉斯最大间距判别准则[J]. 自动化学报, 2010, 36(12): 1661-1673.DOI 10.3724/SPJ1004.2010.01661.
　　Gao Jun, Wang Shitong, Wang Xiaoming, et al. Contextual-distance metric based laplacian maximum margin criterion [J]. Acta Automatica Sinica, 2010, 36(12): 1661-1673. DOI 10.3724/SPJ1004.2010.01661.(in Chinese)
[15] de Lathauwer L, de Moor B, Vandewalle J. A multilinear singular value decomposition [J]. Siam Journal on Matrix Analysis & Applications, 2000, 21(4): 1253-1278.DOI: 10.1137/S0895479896305696.
[16] Xie P, Song Y. Multi-domain feature extraction from surface EMG signals using nonnegative tensor factorization [C]//Proceedings of IEEE International Conference on Bioinformatics and Biomedicine. Shanghai, China, 2013: 322-325. DOI: 10.1109/bibm2013.6732510.
[17] He X, Cai D, Liu H, et al. Image clustering with tensor representation [C]//Proceedings of ACM International Conference on Multimedia. Singapore, 2005: 132-140.DOI: 10.1145/1101149.1101169.
[18] Wang H, Yan S, Xu D, et al. Trace ratio vs ratio trace for dimensionality reduction [C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN, USA, 2007: 1-8. DOI: 10.1109/CVPR2007.382983.
[19] He X, Cai D, Niyogi P. Tensor subspace analysis [J]. Advances in Neural Information Processing Systems, 2005: 499-506. DOI:10.1016/0031-3203(94)00135-9.
[20] Li X, Lin S, Yan S, et al. Discriminant locally linear embedding with high-order tensor data [J]. IEEE Transactions on Systems Man and Cybernetics-Part B: Cybernetics, 2008, 38(2): 342-352. DOI:10.1109/TSMCB2007.911536.
[21] Jiang N, Englehart K B, Parker P A. Extracting simultaneous and proportional neural control information for multiple-DOF prostheses from the surface electromyographic signal [J]. IEEE Transactions on Biomedical Engineering, 2009, 56(4): 1070-1080. DOI:10.1109/TBME2008.2007967.
[22] Naik G R, Nguyen H T. Nonnegative matrix factorization for the identification of EMG finger movements: Evaluation using matrix analysis [J]. IEEE Journal of Biomedical & Health Informatics, 2015, 19(2): 478-485. DOI: 10.1109/JBHI2014.2326660.
[23] 罗志增, 杨广映.表面肌电信号的AR参数模型分析方法[J]. 传感技术学报, 2003, 16(4): 384-387.DOI: 10.3969/jissn1004-1699.2003.04.002.
Luo Zhizeng, Yang Guangying. Surface electromyography analytical method based on the parameter of AR model [J]. Chinese Journal of Sensors and Actuators, 2003, 16(4): 384-387.DOI:10.3969/jissn1004-1699.2003.04.002. (in Chinese)

相似文献/References:

[1]邵将,薛澄岐,王海燕,等.基于图标特征的头盔显示界面布局实验研究[J].东南大学学报(自然科学版),2015,45(5):865.[doi:10.3969/j.issn.1001-0505.2015.05.010]
　Shao Jiang,Xue Chengqi,Wang Haiyan,et al.Experimental study on HMDs interface layout based on icon characteristics[J].Journal of Southeast University (Natural Science Edition),2015,45(6):865.[doi:10.3969/j.issn.1001-0505.2015.05.010]
[2]张晶,薛澄岐,沈张帆,等.基于认知分层的图像复杂度研究[J].东南大学学报(自然科学版),2016,46(6):1149.[doi:10.3969/j.issn.1001-0505.2016.06.007]
　Zhang Jing Xue Chengqi Shen Zhangfan Wang Haiyan Zhou Lei Zhou Xiaozhou Chen Xiaojiao.Study on image complexity based on cognitive layering method[J].Journal of Southeast University (Natural Science Edition),2016,46(6):1149.[doi:10.3969/j.issn.1001-0505.2016.06.007]
[3]熊鹏文,雷耀,李鸣.基于GRNN的人机交互下遥操作力预测方法[J].东南大学学报(自然科学版),2018,48(6):1130.[doi:10.3969/j.issn.1001-0505.2018.06.021]
　Xiong Pengwen,Lei Yao,Li Ming.Teleoperation force perception method in human-computer interaction based on GRNN[J].Journal of Southeast University (Natural Science Edition),2018,48(6):1130.[doi:10.3969/j.issn.1001-0505.2018.06.021]

备注/Memo

备注/Memo:
收稿日期: 2017-06-17.
作者简介: 佘青山(1980—),男,博士,副教授, qsshe@hdu.edu.cn.
基金项目: 国家自然科学基金资助项目(61201302, 61372023, 61671197)、浙江省自然科学基金资助项目(LY15F010009).
引用本文: 佘青山,马鹏刚,马玉良,等.基于张量线性拉普拉斯判别的肌电特征提取方法[J].东南大学学报(自然科学版),2017,47(6):1117-1122. DOI:10.3969/j.issn.1001-0505.2017.06.006.
更新日期/Last Update: 2017-11-20