摘要
外骨骼机器人与军事和人们的日常生活联系日益紧密,通过人体动作的准确识别进而实现外骨骼机器人的精确控制,对外骨骼机器人实用化有重要意义。首先搭建人体下肢s EMG感知系统,然后采用小波变换和LS-SVM相结合的方法,完成了人体下肢六种典型动作s EMG信号的模式识别。结果表明:基于MOC方法的多类LS-SVM分类器,平均识别率达到87.5%,所需的数据样本少、识别精度高,肌电信号用于外骨骼机器人的控制有很好的应用前景。
引文
[1]R.GOPURA,K.KIGUCHI,D.BANDARA,“A brief re view on upper extremity robotic exoskeleton systems,”6th IEEE International Conference on Industrial and Information Systems(ICIIS),2011:346-351.
[2]CARLO J.DELUCA.“Physiology and Mathematics of Myo electric Signals,”IEEE Transactions on Biomedical Engineering,Vol.BME-26,no.6,1979:313-325,June.
[3]CLAUDIO CASTELLINI,ANGELO EMANUELE FIORIL LA,GIULIO SANDINI.“Multi-subject/daily-life activity EMG-based control of mechanical hands,”Journal of NeuroEngineering and Rehablitation,vol.6,2009:41.
[4]R.A.R.C.GOPURA,K.KIGUCHI.“EMG-based Control of an exoskeleton robot for human forearm and wrist motion assist,”IEEE International Conference on Robotics and Automation,pp.731-736,May 2008.
[5]李芳,王人成.肌电信号及其运动模式辨识方法的发展趋势[J].中国康复医学杂志,2005,20(7):492-493.
[6]杨广映,罗志增.肌电信号的功率谱分析方法[J].传感技术学报,2004,9(3):355-358.
[7]崔建国,王旭.基于AR参数模型与聚类分析的肌电信号模式识别方法[J].计量学报,2007,27(3):286-289.
[8]M.UNSER AND A.ALDROUBI.“A review of wavelets in biomedical applications,”Proc.IEEE,vol.84,no.4,1996:626-638.
[9]ALBERT BOGGESS,FRANCIS J.NARCOWICH.“A First Course in Wavelet with Fourier Analysis,”Publishing House of Electronics Industry,2002.
[10]S.MIHOV,R.IVANOV,A.POPOV.“Denoising Speech Sig nals by Wavelet Transform,”The 18th International Scientific and Applied Science Conference Electronics et-2009,B1,ISSN 1313-1842,2009:60-72.
[11]刘东,葛运建.基于SVM预测器的传感器故障诊断与信号恢复研究[J].传感器学报,2005,18(2):247-249.
[12]潘明清.基于支持向量机的机械故障模式分类研究[D].浙江:浙江大学,2005.
[13]SAMUL XAVIER-DE-SOUZA,JOHAN A.K.SUYKENS,JOOS VANDEWALLE,DESIRE BOLLE.Coupled Simulated Annealing[J].IEEE Transactions on Systems,Man and Cybernetics-Part B,40(2),320-335.