基于LMS算法的自适应组合滤波器-外文翻译

《基于LMS算法的自适应组合滤波器-外文翻译》由会员上传分享，免费在线阅读，更多相关内容在学术论文-天天文库。

1、CombinedAdaptiveFilterwithLMS-BasedAlgorithms´Abstract:Acombinedadaptivefilterisproposed.ItconsistsofparallelLMS-basedadaptiveFIRfiltersandanalgorithmforchoosingthebetteramongthem.Asacriterionforcomparisonoftheconsideredalgorithmsintheproposedfilter,wetaketheratiobetweenbiasandvarianceoftheweightin

2、gcoefficients.Simulationsresultsconfirmtheadvantagesoftheproposedadaptivefilter.Keywords:Adaptivefilter,LMSalgorithm,Combinedalgorithm,Biasandvariancetrade-off1．IntroductionAdaptivefiltershavebeenappliedinsignalprocessingandcontrol,aswellasinmanypracticalproblems,[1,2].Performanceofanadaptivefilterdep

3、endsmainlyonthealgorithmusedforupdatingthefilterweightingcoefficients.ThemostcommonlyusedadaptivesystemsarethosebasedontheLeastMeanSquare(LMS)adaptivealgorithmanditsmodifications(LMS-basedalgorithms).TheLMSissimpleforimplementationandrobustinanumberofapplications[1–3].However,sinceitdoesnotalwaysco

4、nvergeinanacceptablemanner,therehavebeenmanyattemptstoimproveitsperformancebytheappropriatemodifications:signalgorithm(SA)[8],geometricmeanLMS(GLMS)[5],variablestep-sizeLMS(VSLMS)[6,7].EachoftheLMS-basedalgorithmshasatleastoneparameterthatshouldbedefinedpriortotheadaptationprocedure(stepforLMSandS

5、A;stepandsmoothingcoefficientsforGLMS;variousparametersaffectingthestepforVSLMS).Theseparameterscruciallyinfluencethefilteroutputduringtwoadaptationphases:transientandsteadystate.Choiceoftheseparametersismostlybasedonsomekindoftrade-offbetweenthequalityofalgorithmperformanceinthementionedadaptation

6、phases.WeproposeapossibleapproachfortheLMS-basedadaptivefilterperformanceimprovement.Namely,wemakeacombinationofseveralLMS-basedFIRfilterswithdifferentparameters,andprovidethecriterionforchoosingthemostsuitablealgorithmfordifferentadaptationphases.ThismethodmaybeappliedtoalltheLMS-basedalgorithms,

7、althoughwehereconsideronlyseveralofthem.Thepaperisorganizedasfollows.AnoverviewoftheconsideredLMS-basedalgorithmsisgiveninSection2.Section3proposesthecriterionforevaluationandcombinationofadaptivealgorithms.Simulationresults