基于LDA的表面肌电信号分类研究

计算机工程与科学

基于LDA的表面肌电信号分类研究

马正华,乔玉涛,李雷,戎海龙

（常州大学信息科学与工程学院、数理学院,江苏常州 213164）

收稿日期:2015-09-08 修回日期:2015-11-04 出版日期:2016-11-25 发布日期:2016-11-25
基金资助:
江苏省自然科学基金（BK20140265）;江苏省普通高校研究生科研创新计划(KYLX_1105)

Classification of surface EMG signals based on LDA

MA Zhenghua,QIAO Yutao,LI Lei,RONG Hailong

（School of Information Science & Engineering,School of Mathematics & Physics,

Changzhou University,Changzhou 213164,China）

Received:2015-09-08 Revised:2015-11-04 Online:2016-11-25 Published:2016-11-25

摘要/Abstract

摘要：

研究了一种基于LDA分类器的模式识别方法，比较了五种特征参数组合方式，分析了无关联线性判别分析

ULDA和PCA两种降维方法，通道数量和窗口长度对肌电信号分类的影响，最后应用LDA分类器对降维后的

数据进行分类。实验结果表明：均方根和四阶AR系数两种特征组合在4通道和8通道下的准确率分别可以

达到90%和96%，增加通道数量或特征数量可以进一步提高准确率；通过ULDA将特征矢量的维数降低到6维

时，仍可以保证较高的准确率；6种手势的识别率超过了94%，其中4种手超过了97%，分类出错的窗口主

要集中在过渡阶段。

关键词: 表面肌电, 无关联线性判别分析, 线性判别式分析

Abstract:

We describe a pattern recognition method which is based on a linear discriminant

classifier.We also make a comparison among the combination types of the five feature

parameters,and analyze the two dimension reduction methods of uncorrelated linear

discriminant analysis (ULDA) and principal component analysis (PCA),as well as the impact

of channel number and window length on the classification of EMG signals.Then the LDA

classifier is used to classify the reduced dimension data.Experimental results are as

follows: 1) the accuracy of the combination of the mean square root and the four order AR

coefficients under four channels and eight channels can reach 90% and 96% respectively;2)

increasing the number of channels or features can further improve the accuracy rate;3) when

reducing the dimension of feature vectors to six dimensions by using the ULDA,a high

accuracy rate can still be ensured;4) the recognition accuracy of six hand gestures are

more than 94%,among which the recognition accuracy of four hand gestures can reach more

than 97%.Classification errors mainly occur in the transition phase.

Key words:

surface EMG, uncorrelated linear discriminant analysis (ULDA), linear discriminant analysis (LDA)

马正华,乔玉涛,李雷,戎海龙. 基于LDA的表面肌电信号分类研究[J]. 计算机工程与科学.

MA Zhenghua,QIAO Yutao,LI Lei,RONG Hailong.

Classification of surface EMG signals based on LDA

[J]. Computer Engineering & Science.

参考文献

［1］Hudgins B,Parker P,Scott R N.A new strategy for multifunction myoelectric control［J］

.IEEE Transactions on Biomedical Engineering,1993,40(1):8294.

［2］Nishikawa D, Yu W, Yokoi H, et al.EMG prosthetic hand controller discriminating ten

motions using realtime learning method［C］∥Proc of IEEE/RSJ International Conference

on,Intelligent Robots and Systems,1999(IROS’99),1999:15921597.

［3］Chu J U,Moon I,Mun M S.A realtime EMG pattern recognition system based on linear

nonlinear feature projection for a multifunction myoelectric hand.［J］.IEEE Transactions

on Biomedical Engineering,2006,53(11):22322239.

［4］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.

［5］Chu J U,Lee Y J.Conjugatepriorpenalized learning of Gaussian mixture models for

multifunction myoelectric hand control［J］.IEEE Transactions on Neural Systems &

Rehabilitation Engineering,2009,17(3):287297.

［6］Wang Dongyan,Li Qingling,Du Zhijiang,et al.Control method of a 5 DOF wearable

rehabilitation robot for upper limb［J］.Journal of Harbin Institute of Technology,2007,39

(9):13831387.(in Chinese)

［7］Li Qingling,Kong Mingxiu,Du Zhijiang,et al.Interactive rehabilitation exercise

control strategy for 5DOF upper limb rehabilitation arm［J］.Chinese Journal of

Mechanical Engineering,2008,44(9):169176.(in Chinese)

［8］Li Qingling,Kong Minxiu,Du Zhijiang,et al.A novel 5DOF exoskeletal

rehabilitation robot system for upper limbs［J］.High Technology Letters,2009,15(3):245

249．

［9］Smith A,Brown E E.Myoelectric control techniques for a rehabilitation robot

［J］.Applied Bionics & Biomechanics,2011,8(1):2137.

［10］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.

［11］Khushaba R N,AlJumaily A,AlAni A.Evolutionary fuzzy discriminant analysis feature

projection technique in myoelectric control［J］.Pattern Recognition Letters,2009,30(7):699

707.

［12］Khushaba R N,AlAni A,AlJumaily A.Orthogonal fuzzy neighborhood discriminant

analysis for multifunction myoelectric hand control［J］.IEEE Transactions on Biomedical

Engineering,2010,57(6):14101419.

［13］Romero L M R.XIII mediterranean conference on medical and biological engineering and

computing 2013［J］.Ifmbe Proceedings,2014,41(2):631634.

［14］Zhang Yi,Zhao Huilong,Zhang Xianggang,et al.Support vector machine based feature

extraction and recognition of EMG signals during lower extremity movement［J］.Manned

Spaceflight,2015(2):179186.

［15］Zhao Mandan,Li Dongxu,Fan Caizhi,et al.A method of hand pattern recognition

based on SEMG hierarchical［J］.Beijing Biomedical Engineering,2014,33(5):490496.(in

Chinese)

［16］Na Y,Kim S J,Min S,et al.Personalized protocol to select usable movements for

myoelectric pattern recognition［C］∥Proc of the 6th European Coference of the

Interhectcinal Federetion for Medical and Biological Engineering,2015:2933.

［17］Ding Qichuan,Zhao Xingang,Han Jianda.Recognizing hand motions based on fault

tolerant classification with EMG signals［J］.Robot,2015(1):916.(in Chinese)

［18］Ferreira J M,Lima C.Distributed system for acquisition and processing the sEMG signal

［C］∥Proc of the International Conference on Health Informatics,2014:335338.

［19］Vesa E P,Ilie B.Equipment for SEMG signals acquisition and processing［M］∥ Proc of

International Conference on Advancements of Medicine and Health Care through Technology,

2014:187192.

［20］Ye J,Janardan R,Li Q,et al.Feature reduction via generalized uncorrelated linear

discriminant analysis［J］.IEEE Transactions on Knowledge & Data Engineering,2006,18

(10):13121322.

附中文参考文献：

［6］王东岩,李庆玲,杜志江,等.5 DOF穿戴式上肢康复机器人

控制方法研究［J］.哈尔滨工业大学学报,2007,39(9):13831387.

［7］李庆玲,孔民秀,杜志江,等.5DOF上肢康复机械臂交互式康复训练控制策略［J］.机械工程学

报,2008,44(9):169176.

［14］张羿, 赵慧龙, 张向刚, 等. 基于 SVM 的下肢运动表面肌电信号的特征提取与辨识分析［J］.载

人航天,2015(2):179186.

［15］赵漫丹,李东旭,范才智,等.基于肌电信号层级分类的手部动作识别方法［J］.北京生物医学工

程,2014,33(5):490496.

［17］丁其川,赵新刚,韩建达.基于肌电信号容错分类的手部动作识别［J］.机器人,2015(1):916.