Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2018, Vol. 52 Issue (7): 1239-1246    DOI: 10.3785/j.issn.1008-973X.2018.07.002
机器人建模与控制     
基于改进支持向量机的人手动作模式识别方法
都明宇, 鲍官军, 杨庆华, 王志恒, 张立彬
浙江工业大学 机械工程学院, 浙江 杭州 310014
Novel method in pattern recognition of hand actions based on improved support vector machine
DU Ming-yu, BAO Guan-jun, YANG Qing-hua, WANG Zhi-heng, ZHANG Li-bin
College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou 310014, China
 全文: PDF(1433 KB)   HTML
摘要：

为了提高基于表面肌电信号（sEMG）控制的手部运动康复器对人手多种动作模式的识别率，比较常规支持向量机（SVM）多类分类器的特点，提出改进的决策树支持向量机多类分类方法.该方法引入基于sEMG特征向量的类间距离可分性测度来指导决策树的构建，能够为每个SVM子分类器的训练提供识别率较高的样本划分方案，在提高决策树内部节点分类成功率的同时，简化了分类器结构.通过实验对比可知，新方法在20种手部动作模式的识别训练过程中，单项动作最低识别率较常规决策树方式提高了7.1%，平均识别率达到88.9%，训练速度较一对一支持向量机分类器提高了5.8%.
Abstract:

A multi-classification method that employs an improved decision tree support vector machine (DT-SVM) was proposed after detailed comparison of the characteristics of the conventional support vector machine (SVM) multi-classifiers in order to improve the accuracy of hand actions recognition for hand movement rehabilitation device controlled by the surface electromyography (sEMG). The method introduced the measure of distance between classes based on sEMG feature vectors in order to guide the construction of decision tree. The method can provide a sample classification scheme with high recognition rate for the training of each SVM sub-classifier, which can further improve the classification of nodes in the decision tree and simplify the classifier's structure. Experiments for the recognizing process of the 20 kinds of hand motions were conducted. Results showed that the minimum recognition rate of single motion increased by 7.1% compared with the conventional DT-SVM, the average recognition rate reached 88.9%, and the training speed increased by 5.8% compared with the one-versus-one SVM.
收稿日期: 2017-10-25 出版日期: 2018-06-26
CLC:  TP241  
基金资助:

国家自然科学基金资助项目（51775499）；浙江省自然科学基金资助项目（LQ15E050008）；浙江省教育厅科研资助项目（Y201121563）；北京市智能机器人与系统高精尖创新中心开放基金资助项目（2016IRS03）.
通讯作者: 张立彬,男,教授,博导.orcid.org/0000-0003-0486-9312.     E-mail: robot@zjut.edu.cn
作者简介: 都明宇(1977-),男,博士生,从事机器人技术、计算机控制技术等研究.orcid.org/0000-0002-2880-3679.E-mail:dumingyu@zjut.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　

引用本文:

都明宇, 鲍官军, 杨庆华, 王志恒, 张立彬. 基于改进支持向量机的人手动作模式识别方法[J]. 浙江大学学报(工学版), 2018, 52(7): 1239-1246.

DU Ming-yu, BAO Guan-jun, YANG Qing-hua, WANG Zhi-heng, ZHANG Li-bin. Novel method in pattern recognition of hand actions based on improved support vector machine. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(7): 1239-1246.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2018.07.002    或    http://www.zjujournals.com/eng/CN/Y2018/V52/I7/1239

[1] VERENA K M, JAVIER B, KATRIN C, et al. Three-dimensional, task-specific robot therapy of the arm after stroke:a multicentre, parallel-group randomized trial[J]. The Lancet Neurology, 2014, 13(2):159-166.
[2] 杨启志,曹电锋,赵金海.上肢康复机器人研究现状的分析[J].机器人,2013,35(5):630-640. YANG Qi-zhi, CAO Dian-feng, ZHAO Jin-hai. Analysis on state of the art of upper limb rehabilitation robots[J]. Robot, 2013, 35(5):630-640.
[3] BOUTERAA Y, ABDALLAH I B. Exoskeleton robots for upper-limb rehabilitation[C]//IEEE International Multi-Conference on Systems, Signals and Devices.[S. l.]:IEEE, 2016:1-6.
[4] 郭晓辉,王晶,徐光华.手部功能康复机器人研究最新进展[J].中国康复医学杂志,2017,32(2):235-240. GUO Xiao-hui, WANG Jing, XU Guang-hua. Research on hand function rehabilitation robot[J]. Chinese Journal of Rehabilitation Medicine, 2017, 32(2):235-240.
[5] SHANECHI M M, HU R C, WILLIAMS Z M. A cortical-spinal prosthesis for targeted limb movement in paralysed primate avatars[J].Nature Communications, 2014,5(5):32-37.
[6] 郑悦,景晓蓓,李光林.人际智能协同在医疗康复机器人领域的应用[J].仪器仪表学报,2017,38(10):2373-2380. ZHENG Yue, JING Xiao-bei, LI Guang-lin. Application of human-machine intelligence synergy in the field of medical and rehabilitation robot[J]. Chinese Journal of Scientific Instrument, 2017, 38(10):2373-2380.
[7] 王行愚,金晶,张宇,等.脑控:基于脑-机接口的人机融合控制[J].自动化学报,2013,39(3):208-221. WANG Xing-Yu, JIN Jing, ZHANG Yu, et al. Brain control:human-computer integration control based on brain-computer interface[J]. Acta Automatica Sinica, 2013, 39(3):208-221.
[8] ROSATI G, GALLINA P, MASIERO S. Design, implementation and clinical tests of a wire-based robot for neurorehabilitation[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2007, 15(4):560-569.
[9] KHUSHABA R N, KODAGODA S, TAKRURI M, et al. Toward improved control of prosthetic fingers using surface electromyogram (EMG) signals[J]. Expert Systems with Applications, 2012, 39(12):10731-10738.
[10] DE L C J, ADAM A, WOTIZ R, et al. Decomposition of surface EMG signals[J]. Journal of Neurophysiology, 2006, 96(3):1646-1657.
[11] KHEZRI M, JAHED M. A neuro-fuzzy inference system for Semg-based identification of hand motion commands[J]. IEEE Transactions on Industrial Electronics, 2011, 58(5):1952-1960.
[12] 黄鹏程,林雪,鲍官军,等.手指肌电信号稀疏分解重构与活动段特征提取研究[J].机电工程,2016,33(5):566-572. HUANG Peng-cheng, LIN Xue, BAO Guan-jun, et al. Sparse decomposition and reconstruction of finger EMG and feature extraction of active segment[J]. Journal of Mechanical and Electrical Engineering, 2016, 33(5):566-572.
[13] 官龙,易金华,李继才,等.握速可调式肌电假手的系统研究[J].中国生物医学工程学报,2013,32(4):471-476. GUAN Long, YI Jin-hua, LI Ji-cai, et al. A control system for the myoelectric prosthetic hand with adjustable grip speed[J]. Chinese Journal of BiomedicalEngineering, 2013, 32(4):471-476.
[14] MATSUBARA T, MORIMOTO J. Bilinear modeling of EMG signals to extract user-independent features for multiuser myoelectric interface[J]. IEEE Transactions on Biomedical Engineering, 2013, 60(8):2205-2213.
[15] CHU J U, MOON I, LEE Y J, et al. A supervised feature-projection-based real-time EMG pattern recognition for multifunction myoelectric hand control[J]. IEEE/ASME Transactions on Mechatronics, 2007,12(3):282-290.
[16] 谢平,魏秀利,杜义浩,等.基于自排序熵的表面肌电信号特征提取方法[J].模式识别与人工智能,2014,27(6):496-501. XIE Ping, WEI Xiu-li, DU Yi-hao, et al. Featureextraction method of Semg based on auto permutation entropy[J]. Pattern Recognition and Artificial Intelligence, 2014, 27(6):496-501.
[17] 丁帅,王亮.基于块稀疏贝叶斯学习的肌电信号特征提取[J]. 仪器仪表学报,2014,35(12):2731-2738. DING Shuai, WANG Liang. Feature extraction of surface electromyography based on block sparse Bayesian learning[J]. Chinese Journal of Scientific Instrument, 2014, 35(12):2731-2738.
[18] AMSUSS S, GOEBEL P M, JIANG N, et al. Self-correcting pattern recognition system of surface EMG signals for upper limb prosthesis control[J]. IEEE Transactions on Biomedical Engineering, 2014, 61(4):1167-1176.
[19] FUTAMATA M, NAGATA, MAGATANI K. The evaluation of the discriminant ability of multiclass SVM in a study of hand motion recognition by using sEMG[C]//2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).[S. l.]:IEEE, 2012:5246-5249.
[20] 佟丽娜,侯增广,彭亮,等.基于多路sEMG时序分析的人体运动模式识别方法[J].自动化学报,2014,40(5):810-821. TONG Li-na, HOU Zeng-guang, PENG Liang, et al. Multi-channels EMG time series analysis based human motion recognition method[J]. Acta Automatica Sinica, 2014, 40(5):810-821.
[21] 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. DING Qi-chuan, XIONG An-bin, ZHAO Xin-gang, et al. A review on researches and applications of s EMG-based motion intent recognition methods[J]. Acta Automatica Sinica, 2016, 42(1):13-25.
[22] VAPNIK V N.统计学习理论[M].许建华,张学工,译.北京:电子工业出版社,2009.
[23] CRAMMER K, SINGER Y. On the learnability and design of output codes for multiclass problems[J]. Machine Learning, 2002, 47:201-233.
[24] 刘飚,陈春萍,封化民,等.基于Fisher准则的SVM参数选择算法[J].山东大学学报:理学版,2012,47(7):50-54. LIU Biao, CHEN Chun-ping, FENG Hua-min, et al. A SVM parameters selection algorithm based on Fisher criterion[J]. Journal of Shandong University:Natural Science, 2012, 47(7):50-54.
[25] 都明宇.基于表面肌电信号的人手动作模式识别关键技术研究[D].杭州:浙江工业大学,2017. DU Ming-yu. Research on key technologies of handaction pattern recognition based on surface electromyography[D]. Hangzhou:Zhejiang University of Technology, 2017.
[26] 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. LIU Jian, ZOU Ren-ling, ZHANG Dong-heng, et al. Research and development trend of feature extraction methods of surface electromyogrphic signals[J]. Progress in Biomedical Engineering, 2015, 36(3):164-168.
[1] 秦超, 梁喜凤, 路杰, 彭明, 金超杞. 七自由度番茄收获机械手的轨迹规划与仿真[J]. 浙江大学学报(工学版), 2018, 52(7): 1260-1266.
[2] 王禹, 韦巍. 采用频域Prony方法估计信号重叠双分量[J]. 浙江大学学报(工学版), 2018, 52(6): 1157-1166.
[3] 王扬威, 兰博文, 刘凯, 赵东标. 形状记忆合金丝驱动的柔性机械臂建模与实验[J]. 浙江大学学报(工学版), 2018, 52(4): 628-634.
[4] 王卫星, 孙守迁, 李超, 唐智川. 基于卷积神经网络的脑电信号上肢运动意图识别[J]. 浙江大学学报(工学版), 2017, 51(7): 1381-1389.