预览加载中，请您耐心等待几秒...

小波包变换检测肌肉.pdf

预览
1/3
2/3
3/3

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

20114thInternationalCongressonImageandSignalProcessing Fatiguemuscledetectionusingtime-frequency methods YaoRong1NicolasMoncel1,2YanZhang1DongyeZhang1DongmeiHao1 1.CollegeofLifeScienceandBioengineering,Beijing2.EcoleCentraled'Electronique UniversityofTechnologyParis,France Beijing,P.R.China Abstract—Inordertodetectmusclefatigueeffectively,weA.Experimentsanddataacquisition recordedsurfaceelectromyographic(sEMG)signalsontheright upperlimbsoftenyoungmenwhiletheywereimplementingInthisstudy,thoseright-handedsubjectswerevolunteers handgriptasks.Waveletpackettransformandbackpropagationfromourcollege.Thesestudentswithoutneuromuscular neuralnetworkweredesignedtoextractfeaturesofsEMGanddiseasesknowledgewereapproximatelytwenty-two-years-old recognizethemusclestates.7-foldcross-validationwasusedto(+/-oneyear).EMGsignalswereobtainedfromED,ECU testtheresults.OurresultsshowedaveryefficientfatigueandECRBofrightupperlimbusingAg-AgClelectrodesand recognitionusingthesemethodsevenifalargerscaleanalysisgripforceofrighthandwereobtainedsimultaneously.The wouldhavebeenbetter.Thestudyindicatesthatmusclefatiguerecordingdiameterofeachelectrodewas9mmandthe couldbedetectedbyanalyzingthesEMGsignals,whichallowuscenter-to-centerinter-electrodedistancewas20mm.A toconsiderapromisingfutureforpracticalapplications.referenceelectrodewasplacedontheskinoverlyingthewrist joint(Figure1).TheEMGsignalswereamplified(×500), Keywords-surfaceelectromyographysignals;musclefatigue;band-passfiltered(10Hz–1000Hz)anddigitized(1000 waveletpackettransform;backpropagationneuralnetwork;samples/s).Thesubjectsgrabbedthegripforcetransducer classificationwithmaximumvolunteercontraction(MVC).Thesustained contractionwasstoppediftheexertedforcedroppedover I.INTRODUCTION 10%formorethan3s.Eachsubjecthadtorepeatthetest Thesurfaceelectromyographysignals(SEMG)threetimes.Consequently,enoughresttimewasallowed characterizetheneuromuscularactivity.Thesebiologicalbetweencontractions.TheEMGsignalsandforcedatawere signalswhichenabletol