文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > 自然科学 > 数学 > 基于信息融合的表面肌电信号模式分类研究
侵权投诉

基于信息融合的表面肌电信号模式分类研究

ABSTRACT

Thesurfaceelectromyography(SEMG)signalisakindofelectrophysiological

signalwhichisgeneratedbytheneuromuscularactivityduringvoluntarymovement

anddirectlyreflectsthemuscleactivity.ExtractingeffectivefeaturesfromSEMGfor

correctclassificationisthekeyproblemintheEMG—basedprosthesiscontrolsystem.

Thispaperproposesanapproachusinginformationfusiontechniquetoimprovethe

performanceoftheclassificationsystemandinvestigatestheprobablesolutionsfor

theproblemsduringinformationfusion.

Inthefirstsection,abriefoverviewofcurrentresearchforthefeature

extractiontechniquesandclassificationmethodsusedinSEMGsignalsisgivenand

theapplicationofinformationfusioninpattemrecognitionisintroduced.Inthe

followingsection,featureextractionforreal-timeEMG-basedprosthesiscontrolis

discussed.Toachievethegoalofthecontrolsystem,itisrequiredthatthefeatures

havegoodseparabilityandthecomputationalcomplexityislow.Thestatistical

characteristicsofthesignalsinthetimedomain,thecoefficientsofARmodeland

thesingularvaluesofthecoefficientmatricesofwavelettransformareextracted

fromtheoriginalsignalsasinputsforeachclassifier.inthethirdsection.fusionsof

decision-makinglevelarediscussedusingDempster-Shaferevidencetheoryand

fuzzyintegral.InthefusionsystembasedonD—Sevidencetheory,fortheconflict

evidences,themodelofevidencesourceismodifiedusingaveragedevidenceand

usingtheD—Scombinationrules.Theexperimentalresultsshowthatthe

ofconfictevidencescouldbesolvedeffectivelywhenthemostevidences

correct.Inthefuzzyintegralsystems,anefficientmethodforthecomputationof

densityisgivenaftercomparingtwoapproachesforfuzzydensitycomputation,

solvestheproblemofdeterminingtheparametersforthefusionofthe

level.Finally,theeffectsofthetwosystems,fusionsystemsusing

evidencetheoryandfuzzyintegral,arecompared.TheresultsrevealthatthelIcombinedproblemarefuzzywhichdecision-makingD—S

上一页第3页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email