简介:Thispaperproposesanewneuralfuzzyinferencesystemthatmainlyconsistsoffourparts.Thefirstpartisabouthowtouseneuralnetworktoexpresstherelationwithinafuzzyrule.Thesecondpartisthesimplificationofthefirstpart,andexperimentsshowthatthesesimplificationswork.Onthecontrarytothesecondpart,thethirdpartistheenhancementofthefirstpartanditcanbeusedwhenthefirstpartcannotworkverywellinthefuzzyinferencealgorithm,whichwouldbeintroducedinthefourthpart.Finally,thefourthpart"neuralfuzzyinferencealgorithm"isbeenintroduced.Itcaninferencethenewmembershipfunctionoftheoutputbasedonpreviousfuzzyrules.Theaccuracyofthefuzzyinferencealgorithmisdependentonneuralnetworkgeneralizationability.Evenifthegeneralizationabilityoftheneuralnetworkweusedisgood,westillgetinaccurateresultssincethenewcomingrulemaynotberelatedtoanyofthepreviousrules.Experimentsshowthisalgorithmissuccessfulinsituationswhichsatisfytheseconditions.
简介:Afaultdiagnosismodelisproposedbasedonfuzzysupportvectormachine(FSVM)combinedwithfuzzyclustering(FC).Consideringtherelationshipbetweenthesamplepointandnon-selfclass,FCalgorithmisappliedtogeneratefuzzymemberships.Inthealgorithm,sampleweightsbasedonadistributiondensityfunctionofdatapointandgeneticalgorithm(GA)areintroducedtoenhancetheperformanceofFC.Thenamulti-classFSVMwithradialbasisfunctionkernelisestablishedaccordingtodirectedacyclicgraphalgorithm,thepenaltyfactorandkernelparameterofwhichareoptimizedbyGA.Finally,themodelisexecutedformulti-classfaultdiagnosisofrollingelementbearings.Theresultsshowthatthepresentedmodelachieveshighperformancesbothinidentifyingfaulttypesandfaultdegrees.TheperformancecomparisonsofthepresentedmodelwithSVManddistance-basedFSVMfornoisycasedemonstratethecapacityofdealingwithnoiseandgeneralization.
简介:InthisstudyanewhybridaggregationoperatornamedasthegeneralizedintuitionisticfuzzyhybridChoquetaveraging(GIFHCA)operatorisdefined.Meantime,somedesirablepropertiesarestudied,andseveralimportantcasesareexamined.Furthermore,wedefinethegeneralizedShapleyGIFHCA(GS-GIFHCA)operator,whichdoesnotonlyoverallconsidertheimportanceofelementsandtheirorderedpositions,butalsogloballyreflectthecorrelationsamongthemandtheirorderedpositions.Inordertosimplifythecomplexityofsolvingafuzzymeasure,wefurtherdefinethegeneralizedλ-ShapleyGIFHCA(GλS-GIFHCA)operator.
简介:Weconsiderforafixedμ,theclassofpolynomialsPn,μ,s:=P(z)=zsanzn-s+n-s∑j=μan-jzn-j-s;1≤μ≤n-sofdegreen,havingallzerosin|z|≤k,k≤1,withs-foldzerosattheorigin.Inthispaper,wehaveobtainedinequalitiesinthereversedirectionfortheaboveclassofpolynomials.Besides,extensionsofsomeTuran-typeinequalitiesforthepolarderivativeofpolynomialshavebeenconsidered.
简介:Makingfulluseofwindpowerisoneofthemainpurposesofthewindturbinegeneratorcontrol.Conventionalhillclimbingsearch(HCS)methodcanrealizethemaximumpowerpointtracking(MPPT).However,thestepsizeofHCSmethodisconstantsothatitcannotconsiderbothsteady-stateresponseanddynamicresponse.Afuzzylogicalcontrol(FLC)algorithmisproposedtosolvethisprobleminthispaper,whichcantrackthemaximumpowerpoint(MPP)quicklyandsmoothly.ToevaluateMPPTalgorithms,fourperformanceindicesarealsoproposedinthispaper.Theyaretheenergycapturedbywindturbine,themaximumpower-pointtrackingtimewhenwindspeedchangesslowly,thefluctuationmagnitudeofrealpowerduringsteadystate,andtheenergycapturedbywindturbinewhenwindspeedchangesfast.ThreecasesaredesignedandsimulatedinMATLAB/Simulinkrespectively.ThecomparisonofthethreeMPPTstrategiesconcludesthattheproposedfuzzylogicalcontrolalgorithmismoresuperiortotheconventionalHCSalgorithms.
简介:Theworldisundergoingconstantandcomplicatedchange.Development,adjustmentandtransformationmakeuptheworld’smainmelody,whilepeaceanddevelopmentarestillthecurrentthemes.Multi-polarizationandeconomicglobalizationcontinuetobecomemoreentrenched,andculturaldiversityandsocialnetworkingacross
简介:Asymmetricstereoscopicvideocodingcantakeadvantageofbinocularsuppressioninhumanvisionbyrepresentingoneofthetwoviewsinlowerquality.Thispaperproposesabitallocationstrategyforasymmetricstereoscopicvideocoding.Inordertoimprovetheaccuracyofbitallocationandratecontrolintheleftview,aproportionalintegral-derivativecontrollerisadopted.Meanwhile,tocontrolthequalityfluctuationbetweenconsecutiveframesoftheleftview,aqualitycontrollerisadopted.Besides,afuzzycontrollerisproposedtocontrolthevariationinqualitybetweentheleftandrightviewsbycomparingthePSNRdisparityoftwoviewswithafixedthreshold,whichisusedtoquantizethebinocularpsycho-visualredundancyandadjustthequantizationparameter(QP)oftherightviewcorrespondingly.TheproposedalgorithmhasbeenimplementedinH.264/AVCvideocodec,andtheexperimentalresultsshowitseffectivenessinratecontrolwhilekeepingagoodqualityfortheleftview,andfewerbitsareallocatedfortherightviewsothattheoverallbitrateissavedby7.2%atmostwithoutthelossofsubjectivevisualqualityforstereoscopicvideo.
简介:UnlikethepreviousresearchworksanalyzingthestabilityoftheT-S(Takagi?Sugeno)fuzzymodel,anextensiononthestabilityconditionofT-Sfuzzysystemswithadifferentstrategyisprovided.Inthestrategyanewvariable,whichisrelativetothegradeoffuzzymembershipfunction,isintroducedtothestabilityanalysisandanewstabilityconclusionisdeduced.Thedefinitionofstabilityconditioninthispaperisdifferentfrompreviousworks,thoughtheyaresimilarinform.Withtheproposedmethod,thesimulationinflightcontrollawshowsabettereffectiveness.