A VARIATION OF GOLDFARB'S METHOD FOR LINEARLY CONSTRAINED OPTIMIZATIONPROBLEMS AND ITS SUPERLINEAR CONVERGENCE RATE

1.IntroductionRosen'sgradientprojectionmethodisaveryinterestingtechniqueinoptimization(see[1,2]),butitsglobalconvergenceisalong-standingopenproblemintheliterature.Thefirstconvergentversionwasfoundbyp.l.k[3].ButPolak'sversionistoocomplicated.Du[4]alsofoundasimplerconvergentversionbydeletingPolak'sspecialprocedure.CombiningRosen'smethodwithvariablemetricmethods,Goldfarb[sl,MurtaghandSargentl'lobtainedtwoefficientalgorithms.Theconvergenceofsuchalgorithmsisstillanopenproblem.However,severalcon…     

A New Approach to Optimal Filtering for SingularDiscrete-Time Stochastic Linear System

1IntroductionBecausetherealisticproblemwhichsingularsystemdescribesiswiderthanthenormalsystemsdo,theresearchofsingularsystemshasreceivedagreatdealofattention.Andmanyachievementshavebeenobtainedinthefieldsofstructuralcharacteranalysisanddesignmethodsofsingularsystems.Butforthestateestimationonlypreliminaryprobehasbeenmade.References[2]--[51proposedrespectivesolutionsbasedonleastsquaremethod.References[6]--[71transformsingularsystemsintonormalsystemsthroughmatrixresolutionandthenmakeuseofKalman…     

THE ASYMPTOTICALLY OPTIMAL EMPIRICALBAYES ESTIMATION IN ONE WAY ANOVA MODEL

1.IntroductionSincetheempiricalBayes(EB)approachtoastatisticaldecisionproblemwasfirstintroducedbyR.bbins[1'21?ithasreceivedmuchattentionintheliterature.Forlinearmodel,Singh[3]studiedtheEBestimationproblemofregressioncoefficientsinamultiplelinearregressionmodelunderknownerror-variance.Wei[4]consideredtheEBtestproblemforthesamemodel.ZhangandWeilsl,WeiandZhang[6]extendedSingh'sworktothecaseofunknownerror-variance,theydiscussedtheasymptoticoptimalityandconvergenceratesfortheestimationofregre…     

UPPER AND LOWER SOLUTIONS METHODS FOR EXISTENCE OF PERIODIC SOLUTIONS OF DUFFING EQUATION

1.IntroductionandNotationsInthispapertwestudytheexistenceofsolutionstothefollowingperiodicboundaryvalueproblemforthesecondorderDuffingequationwheresisarealparameter,g:[0,TIxR~RisaCarath6odoryfunctionandkER\{0}.Werecall(forexample,see[1])thatg:[0,TIxR~RiscalledaCarath6odoryfunctionifg(.,x)ismeasurableforallxERandg(t,.)iscontinuousfora.e.tE[0,TI.Theexistenceproblemfor(1.1)--(1.2)byusingtheupperandlowersolutionsmethodhasbeenstudiedbyFabryetal.in[2]foramoregeneralcasewhereacontinuousdampin…     

Scene matching based on non-linear pre-processing on referenceimage and sensed image

1.INTRODUCTION Downwardlookingscenematchingiswidelyusedin theaircraftautomaticguidance.Theaircraftobtains sensedimagesinthepresetflightrouteandcompares themwiththereferenceimagestoredbeforethemis sion.Withthecomparisonofthesetwoimages,the aircraftgetsitscurrentpositionintheflightmap.Al thoughtherearesomemethods,suchasthemethod basedonthefractaldimension[1],themethodbased ontheknowledgeofobjectedge[2],histogram based method[3],themeanandstandarddeviationquantiza tionmethod[4]andspatialr…     

Rolling optimization algorithm based on collision window for single machine scheduling problem

1.INTRODUCTION Thesinglemachinenon preemptiveschedulingto minimizetotalcompletiontimewithdynamicjobar rivalsisthebasicprobleminproductionscheduling.Manyworksfocusoneffectiveheuristicmethodsdue toitsstronglyNP hardcharacter.Themostcommon heuristicsareSPT[1](shortestprocessingtime),ECT[2](earliestcompletiontime),delayed SPT[3],PRTF[4](priorityrulefortotalflowtime),APRTF[4],etc.Withoutfullyutilizinganyinforma tionaboutjobswhichwillarriveinthefuture,the abovemyopicmethodsmayresultinpo…     

A Multipath Routing Assignment Model for Multi-Traffic Class Networks

1　IntroductionRoutingisakeytechnologyformoderndatanetworksandtherehavebeentremendousroutingalgorithms[1]～[5].MostoftheroutingalgorithmssuchasOSPFandRIP[5]arebasedontheshortestpathassignmentmodel,inwhicheveryrouterisonlyatransitionnode.Futurerouterisdestinationorientedandshouldhavetheabilitytosplittrafficloadovermulti-pathtoutilizethenetworkinfrastructureinanefficientway.Withthenetworktrafficincreasingmuchfaster,howtorealizeloadbalancinginthenetworkbecomesahotresearchtopic[2].UndertheOSP…     

A SINGLESTEP CHARACTERISTIC FINITE DIFFERENCE METHOD FOR TWO-DIMENSIO NALNON LINEAR CONVECTION-DIFFUSIONPROBLEMS

1.IntroductionThenonlinearconvection-diffusionproblemsareakindofveryimportantproblemssuchastheundergroundpercolation,air--pollution,fluidmechanicsmodelingetc.Thenumericalmethodsforsolvingthelinearproblemswiththeconvectivecoefficientsdominating,whicharethecharacteristicfiniteelementandcharacteristicfinitedifferencemethods,aregivenbyJ.DouglasandT.F.Russellin[1]andfurtherdevelopmentin[2]and[3],etc.ButtheconvergenceofmethodsneedstherestrictiveassumptionAt=O(h).Inpracticeonewouldliketotakebigger…     

Target tracking in glint noise using a MCMC particle filter

1.INTRODUCTION Insomeradarapplications[1～8],themeasurement noiseusuallyderivatesfromtheGaussianassumption.Forexample,complextargetsmightcauseirregular electromagneticwavereflection.Thisphenomenon variesthetargetcenterinaradarandgivesriseto outliersinangletracking,knownas“target glint”[1].Theglintnoisehasalong taileddistribu tionandcanseverelydegradetheKalmanfilterper formance[2～4].Filteringinnon Gaussianenviron mentshasbeenstudiedbymanyresearchers.Masre liez[5]usesascorefunctionbase…     

Function S-rough sets and mining-discovery of rough law in systems

1. INTRODUCTION S-rough sets (singular rough sets) was presented in Ref. [3] in 2002, and defined on α -element equival- ence class [x] with dynamic characteristic. S-rough sets has more advantages than Z.Pawlak’s rough sets[24]. S-rough sets has been applied in dynamic object recognition[21], mechanical engineering[22] and information science[8-13]. In 2005, function S-rough sets was put forward in Refs. [1,2], and is defined on α -function equivalence class [u] with dynamic charact…     

A FEW RESULTS ON ARNOLDI''''S METHOD AND IOM FOR LARGE NON-HERMITIAN LINEAR SYSTEMS

1.IntroductionArnoldi'smethod[1'2]anditsincomplete0rth0g0nalizati0nversion(IOM)["']areextensivelyusedforsolvinglargenon-Hermitianlinearsystems.Itiswellknownthattheformerisanorthogonalprojectionmethod,whilethelatterisanobliqueprojecti0nmethod.Wereferto[2,4]and[3]forconvergenceanalyses0fthesetwomethods,respectively.RecelltlyBrown[5],Chronopoul0sI6landSaadl2,7]andmanyothershavederivedupdatingrecursionsoftheresidualnormsandaPprokimatesolutionsobtainedbyArnoldi'smethod.TheaPproachestheyuseeith…     

ON THE ONE-SIDED LOGARITHMIC LAW FOR ARRAYS

1.IntroductionLet{X.,n2l}beasequenceofindependentandidenticallydistributed(i.i.d.)randomvariables.TheHartmanandWintner,sllllawoftheiteratedlogarithmstatesthatifEXI~0andEX7=1Moreover,itisprovedin[2]and[3]that(1)holdsifandonlyifEXI~0andEX7=1.Nowlet{Xnk,k=1,2,''tntn~1,2,'.}beanarrayofi.i.d.randomvariables.FOreveryn21setS.~Z:--,X.k'ThealmostsureconvergenceofSahasbeenstlldiedbyHu,MoriczandTaylor[41,HuandWeb.rls]andQi[6].HuandWeber[5]showedundertheconditionsEXll=0,EX7,=1andEXt,相似文献   

A New Deghosting Algorithm with Hypothesis Testing Data Fusion

1 .INTRODUCTIONInrecentyears,themultisensordistributeddatafu sionhasattractedmuchattention[5] .Oneoftheim portantaspectsispassivecrosslocation[2 ] .Themea surementfromarealtargetisatrueLOS (line of sight)angleplussomemeasurementnoise.Torrieri[1 ] proposedthebasicmethodsofestimationanddeterminedtheaccuracyofasuitableestimator.However,theLOSmeasurementsofmultipletargetsoccurringinthesameplanewouldcreateanumberoffalseintersec tions ( ghosts) .Eliminatingthefalseintersectingpoints(deghosti…     

An Impulse Weakly Observability of Generalized Linear Systems

1.INTRODUCTIONConsiderthelineartime-invariantsystemsWhereE,AeRI"",BERI"",CeR"""jDERrxm.Vt6R :=to' OO),x(t)ER",u(t)6Re,y(t)6R",Herenoregularityassumptionofthepencil[E,A]ismade,i.e.,detIsE--AImaybeZero'polynomial.SincetheworkofRosenbrock[if,alotofcontributionhasbeenmadetosuch.systems,whichhJD=B=0,thestructuresofinfiniteandfinitezerosarecharacterized[21,observabilityandstrongobser.vabilityareanalyzed[3].TothecaseofD=0,regularizabilityofsingularsystemsisproved[61,interiorgeometr…     

THE RELATIONSHIP BETWEEN THE CONE-WEAK SUBDIFFERENTIAL AND CONE-WEAK DIRECTION DERIVATIVE FOR CONVEX SET-VALUED MAPPING

1.IntroductionInrecentyears,thetheoriesofgenerealdifferentialhaveplayedimportantrQleinthestudyanddevelopmelitofnonlinearfields(see[1-6])-Wehaveintroducedatypeofthecone-weaksubdfferentialofconvexset-valuedmappinginalocallyconvextopologicalvectorspacein[7-1l].ItdifferentsfromthosedefinedbyJ-P-Aubin,Ekeland,T.Tanino,Y.Sawaragi,B.S.Mordukhovichin[3-6].Ithasbeenusedtosolvetheoptimalproblemsofset-va-luedmaPpingssuchasthestabilityofoptimalsolutions,optimalconditions,dualtheorem,saddlepointstheo…     

CONVERGENCE IN THE CHEMOSTAT MODELWITH DELAYED RESPONSE IN GROWTH

1.IntroductionThechemostatisalaboratoryapparatususedforcontinuouscultureofmicroorganisms.Itcanbeusedtostudycompetitionbetweendifferentpopulationsofmicroorganismsforagrowthlimitingsubstrate,andhastheadvantagethatcertainofthebiologicalparameterspresumedtoinfluencecompetitiveoutcomecanbecontrolledbytheeXPerimellter.TheglobalanalysesofthechemostatmodelwithMichaelis--MentenkineticsfornutrielltuptakeweregivenbyHsu,HubbedandWaltmanin[2]andHsuin[31.Undertheassumptionthatalltheparametersaredistinct…     

ON THE THEORY OF RESOLVENTS AND ITS APPLICATIONS

1.IntroductionSomefrequentlyusedalgebraicalgorithmssharethesamepropertythattheytransformasetofpolynomialequationstoasinglepolynomialequationsuchthatthezerosetofthepolynomialsetandthehypersurfacedefinedbythesinglepolynomialareequivalentincertainsense.FOralgorithmswiththisproperty,wemaymention'thealgorithmtofindaprimitiveelementforafinitelygeneratedalgebraicextensionfield[1],thealgorithmtofindaplanecurvewhichisbirationaltoaspacealgebraiccur.e[2]!etc.Inthispaper,wepresentageneralalgorithmwhichcan…     

LOWER BOUND ON K-SEQUENCE

1.IntroductionK-sequenceswereilltroducedbyKl0vein[1]-Itisaclassofsequencesthatinparticularcoatainsthesonarsequences[2]andBh-sequences.Resultsthatwerepreviouslyconsideredforeach0fthesesubclassescaninmanycasesbegeneralizedtoK-sequencesandbegivenaunifiedtreatment.Thesesequenceshaveanumber0fapplicati0ns.F0rinstance,Bh-sequenceswereappliedininterm0dulation-freefrequenciesassignment(see[3,4]).AclassofK-sequencesnotpreviouslyconsideredwereimportaninaconstructionofilltermodulationfreefrequenciesass…     

Cheater identifiable visual secret sharing scheme

1.INTRODUCTION Thevisualsecretsharingschemeisoneofthesecret sharingschemes[1]inwhichthesecretinformationis animagethatconsistsofacollectionofblackand whitepixels[2].Thesharedimages,eachofwhich consistsofacollectionofblackandwhitepixels,are distributedtotheparticipants,andthesecretinfor mationcanberecovereddirectlybyprintingeach sharedimageontransparencyandstackingthemto gether.KogaandYamamotohaveproposedtheex tendedschemeforcolorandgray scaleimage[3].Be sidesthresholdscheme.arbitraryv…     

A Bid Markup Estimate System Using Case-Based Reasoning

1　IntroductionBiddingdecision-markingproblemssuchasthebid/no-biddecisionandthepercentmarkupdetermination,arefacedbygeneralcontractorsincompetitivebiddingsituations[1].Biddingdecisionsareveryimportantastheyhaveprofoundeffectsontheday-to-dayoperationsandthelong-termperformanceoftheconstructionfirm.Researchershavebeenconcernedwiththeproblemofbiddingstrategysincethemid-1950s,whenFriedman[2]proposedhismodelandGates[3]proposedasimilarmodel.Inpractice,Themarkupdecisioninvolvesalargelyqualitativean…