«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《电机与控制学报》[ISSN:1007-449X/CN:23-1 408/TM]

卷:

21

期数:

2017年12

页码:

75-84

栏目:

出版日期:

2017-12-01

文章信息/Info

Title:

Feature extraction algorithm for hand motion modes

作者:

尤波1;  李忠杰1;  黄玲1;  赵汗青2

(1． 哈尔滨理工大学 自动化学院，黑龙江 哈尔滨 150080;2． 黑龙江科技大学 机械工程学院，黑龙江 哈尔滨 150022)

Author(s):

YOU Bo1;  LI Zhong-jie1;  HUANG Ling1;  ZHAO Han-qing2

(1． School of Automation，Harbin University of Science and Technology，Harbin 150080，China;2． School of Mechanical Engineering，Heilongjiang Institute of Science and Technology，Harbin 150022，China)

关键词:

表面肌电信号;  特征提取;  模式识别;  小波变换

Keywords:

surface electromyogram signal;  feature extraction;  pattern recognition;  wavelet transform

分类号:

TP 301. 6

DOI:

10.15938/j.emc.2017.12.010

文献标志码:

A

摘要:

针对人手抓取动作问题，如何有效地提取表面肌电信号特征是提高其模式识别率的关键。通过对前人不同手部抓取动作的分类方法及日常生活工作中使用的频度进行统计学分析，决定选取 8 种抓取动作进行研究。实验显示，随着手部动作姿态种类的增加，基于表面肌电信号的不同特征提取算法分类能力出现不同程度的下降甚至失效。为取得更为理想的抓取动作分类效果，提出将抓取动作分割为预抓取和抓取两个动作过程。选择采集预抓取动作前臂肌电信号，除对其时域、频域及时频域常用特征量进行分析对比外，还增添了对时频域中小波系数最大模值的分析，旨在找出最有效表征肌电信号动作分类的特征量。实验结果表明，小波系数最大模值量最有特征可分性，区分效果比较理想。

Abstract:

Extracting s EMG signal feature availably is the key to improve the pattern recognition rate．Eight kinds of grasping motions were studied according to the frequency statistical analysis on predeces-sors’various classification method for hand grassping motion used in daily life． The experimental resultsshow that with the increase of hand gestures types，the classification ability of different feature extractionalgorithms based on the s EMG became decline in different levels and even failed． The grasping motionswere divided into prefetch and grab action process to achieve better results． Prefetch forearm electromyo-graphic signals were chosen，not only the commonly used features were analyzed and compared in time do-main and frequency domain as well as time and frequency domain，but also maximum modulus of waveletcoefficients was analyzed in time and frequency domain，which was to find out the most effective charac-teristic quantity of s EMG classification． The experimental results show that the maximum modulus of wave-let coefficients has the most characteristic separability，and the classification result is better．

参考文献/References:

-

相似文献/References:

[1]黄建,胡晓光,巩玉楠,等.高压断路器机械故障诊断专家系统设计[J].电机与控制学报,2011,(10):43.
　HUANG Jian,HU Xiao-guang,GONG Yu-nan,et al.Machinery fault diagnosis expert system for high voltage circuit breaker[J].,2011,(12):43.
[2]安宗裕,汪泉弟,彭河蒙,等.汽车雨刮电机电磁干扰特征提取方法[J].电机与控制学报,2012,(07):1.
　AN Zong-yu,WANG Quan-di,PENG He-meng.Electromagnetic interference feature extraction for vehicle wiper motor signals based on wavelet decomposition[J].,2012,(12):1.
[3]张怡卓,曹军,许雷,等. 实木地板缺陷形态学分割与SOM识别[J].电机与控制学报,2013,(04):116.
　ZHANG Yi-zhuo,CAO Jun,XU Lei,et al.[J].,2013,(12):116.
[4]孙靖杰,赵建军,王汉昌,等. 基于FRFT-KPCA的模拟电路非线性故障特征提取[J].电机与控制学报,2013,(08):100.
　SUN Jing-jie,ZHAO Jian-jun,WANG Hang-chang,et al.[J].,2013,(12):100.
[5]杨青,王栗,刘彧诚,等.FICA-IPNN 集合型滚动轴承故障诊断方法[J].电机与控制学报,2014,18(03):73.
　YANG Qing,WANG Li,LIU Yu-cheng,et al.FICA-IPNN ensemble fault diagnosis approach of rolling bearing[J].,2014,18(12):73.
[6]曹莹,段玉波,刘继承,等.多尺度形态滤波模态混叠抑制方法[J].电机与控制学报,2016,20(09):110.[doi:10． 15938 / j． emc． 2016． 09． 016]
　CAO Ying,DUAN Yu-bo,LIU Ji-cheng,et al.Multi-scale morphological filtering method for mode mixing suppression[J].,2016,20(12):110.[doi:10． 15938 / j． emc． 2016． 09． 016]
[7]汪可,张书琦,李金忠,等. 基于灰度图像分解的局部放电特征提取与优化[J].电机与控制学报,2018,22(05):25.[doi:10.15938/j.emc.2018.05.004]
　WANG Ke,ZHANG Shu-qi,LI Jin-zhong,et al. Partial discharge feature extraction and optimizationbased on gray image decomposition[J].,2018,22(12):25.[doi:10.15938/j.emc.2018.05.004]

备注/Memo

备注/Memo:

收稿日期: 2016 － 11 － 16
基金项目: 国家”863”重大项目子课题高性能仿人型假手( 2009AA043803) ; 哈尔滨市科技创新人才基金( 2009ＲFQGG207) ; 黑龙江省研究生创新科研基金 ( YJSCX2009 － 059HLJ)
作者简介: 尤 波( 1962—) ，男，教授，博士生导师，研究方向为智能机器人及机电一体化等;
李忠杰( 1991—) ，男，硕士研究生，研究方向为图像处理及深度学习;黄 玲( 1975—) ，女，博士，教授，研究方向为控制理论及其应用;
赵汗青( 1970—) ，女，教授，研究方向为肌电信号分析与处理。

常用功能

更新日期/Last Update: 2018-03-19