|
|
|
| Electromyography movement recognition of lower limb based on
multiple kernel learning |
| SHE Qingshan, MENG Ming, LUO Zhizeng, MA Yuliang |
| College of Automation, Hangzhou Dianzi University, Hangzhou 310018, China |
|
|
|
Abstract In order to improve the precision of multimotion pattern recognition in lower limb myoelectric control system, a multiclass recognition method was proposed based on the feature extraction using the interscale dependency by the wavelet transform and the multiple kernel learning (MKL). A MKLbased multiclassifier was constructed by the binary tree combined strategy according to the MKL theory. Four channel surface electromyography signals of lower limb were decomposed by the stationary wavelet transform. Eigenvectors were extracted using the interscale correlations between wavelet coefficients, and inputted into the MKLbased multiclassifier. Five subdividing patterns were identified in levelground walking, i.e. support prophase, support metaphase, support telophase, swing prophase and swing telophase. Experimental results show that the method can successfully identify these subdividing patterns with better accuracy than the standard single kernel support vector machine (SVM) classifier.
|
|
Published: 01 July 2010
|
|
|
基于多核学习的下肢肌电信号动作识别
为了提高下肢肌电控制系统中多运动模式识别的准确性,提出一种基于多核学习(MKL)和小波变换尺度间相关性特征提取的多类识别方法.根据多核学习理论,采用二叉树组合策略构造基于多核学习的多类分类器.对下肢4路表面肌电信号进行离散平稳小波变换,用小波系数尺度间的相关性提取特征向量输入构造的多类分类器,对水平行走时划分的支撑前期、支撑中期、支撑末期、摆动前期、摆动末期这5个细分运动状态进行分类.实验结果表明,所提的多模式识别方法能够以较高识别率区分多个细分运动状态,得到比标准的单核支持向量机(SVM)分类器更好的准确性.
|
|
| ［1］ VAPNIK V N. The nature of statistical learning theory ［M］. 2nd ed. New York: SpringerVerlag, 1999: 123167.
［2］ BURGES C J C. A tutorial on support vector machines for pattern recognition ［J］. Knowledge Discovery and Data Mining, 1998, 2(2): 121167.
［3］ CASTELLINI C, SMAGT P. Surface SEMG in advanced hand prosthetics ［J］. Biological Cybernetics, 2009, 100(1): 3547.
［4］ LUCAS M F, GAUFRIAU A S, PASCUAL S. Multichannel surface SEMG classification using support vector machines and signalbased wavelet optimization ［J］. Biomedical Signal Processing and Control, 2008, 3(2): 169174.
［5］ 席旭刚,李仲宁,罗志增.基于相关性分析和支持向量机的手部肌电信号动作识别［J］.电子与信息学报,2008,30(10): 23152319.
XI Xugang, LI Zhongning, LUO Zhizeng. SEMG movement pattern recognition of hand based on correlation analysis and SVM ［J］. Journal of Electronics and Information Technology, 2008, 30(10): 23152319.
［6］ 崔建国,李一波,李忠海,等.基于小波包与支持向量机的复杂信号模式识别［J］.数据采集与处理,2008,23(2): 163167.
CUI Jianguo, LI Yibo, LI Zhonghai, et al. Complicated signal pattern recognition based on wavelet packet and support vector machine ［J］. Journal of Data Acquisition and Processing, 2008, 23(2): 163167.
［7］ 张军峰,胡寿松.基于多重核学习支持向量回归的混沌时间序列预测［J］.物理学报,2008,57(5): 27082713.
ZHANG Junfeng, HU Shousong. Chaotic time series prediction based on multikernel learning support vector regression ［J］. Acta Physica Sinica, 2008, 57(5): 27082713.
［8］ LANCKRIET G, CRISTIANINI N, GHAOUI L E, et al. Learning the kernel matrix with semidefinite programming ［J］. Journal of Machine Learning Research, 2004, 5(1): 2772.
［9］ SONNENBURG S, RATSCH G G, SCHAFER C, et al. Large scale multiple kernel learning ［J］. Journal of Machine Learning Research, 2006, 7(1): 15311565.
［10］ RAKOTOMAMONJY A, BACH F R, GRANDVALET S Y. SimpleMKL ［J］. Journal of Machine Learning Research, 2008, 9(1): 24912521.
［11］ LANCKRIET G, BIE T B, CRISTIANINI N, et al. A statistical framework for genomic data fusion ［J］. Bioinformatics, 2004, 20(16): 26262635.
［12］ 张军峰,胡寿松.基于多重核学习支持向量机的歼击机故障诊断［J］.东南大学学报：自然科学版,2007,37(S1): 15.
ZHANG Junfeng, HU Shousong. Fighter fault diagnosis based on multiple kernel learning SVMs ［J］. Journal of Southeast University: Natural Science Edition, 2007, 37(S1): 15.
［13］ OSKOEI M A, HU H S. Support vector machinebased classification scheme for myoelectric control applied to upper limb ［J］. IEEE Transactions on Biomedical Engineering, 2008, 55(8): 19561965. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
