简介:Inthispaper,weareconcernedwithuniformsuperconvergenceofGalerkinmethodsforsingularlyperturbedreaction-diffusionproblemsbyusingtwoShishkin-typemeshes.Basedonanestimateoftheerrorbetweensplineinterpolationoftheexactsolutionanditsnumericalapproximation,aninterpolationpost-processingtechniqueisappliedtotheoriginalnumericalsolution.Thisresultsinapproximationexhibitsuperconvergencewhichisuniformintheweightedenergynorm.Numericalexamplesarepresentedtodemonstratetheeffectivenessoftheinterpolationpost-processingtechniqueandtoverifythetheoreticalresultsobtainedinthispaper.
简介:ROW-ACTIONMETHODSFORCONVEXQUADRATICPROGRAMMINGGUOTiande(MathematicsDepartmentofQufuNormalUniversity,Qufu,Shandong273165,China...
简介:Basedonelementarygrouptheory,theblockpivotmethodsforsolv-ingtwo-dimensionalelasticfrictionalcontactproblemsarepresentedinthispaper.Itisprovedthatthealgorithmsconvergewithinafinitenumberofstepswhenthefrictioncoefficientis'relativesmall'.Unlikemostmathematicalprogrammingmeth-odsforcontactproblems,theblockpivotmethodspermitmultipleexchangesofbasicandnonbasicvariables.
简介:Thispaperpresentsaclassofhybridone-stepmethodsthatareobtainedbyusingCramer’sruleandrationalapproximationstofunctionexp(q).Thealgorithmsfallintothecatalogueofimplicitformula,whichinvolvessthorderderivativeands+1freeparameters.Theorderofthealgorithmssatisfiess+1≤p≤2s+2.Thestabilityofthemethodsisalsostudied,necessaryandsufficientconditionsforA-stabilityandL-stabilityaregiven.Inaddition,someexamplesarealsogiventodemonstratethemethodpresented.
简介:Inthepast,filminglateralradiogramneededtheassociationoffilmingbedandanglewooden-box.Whichhasthedefectsthatitrequiredtoocomplexoperationandcan'tavoidtheeontralateralshoulderwardingofftheray.TheauthorinventedanewwaytofilmLateralradiogramofmandiblethroughyears'practice,whichismoresimpleandconvenientandsuitableforroutineoperation.
简介:Errorestimatesareestablishedforthefinitedementmethodstosolveaclassofsecondordernonlinearparabolicequations.OptimalratesofconvergenceinL2-andH1-normsarederived.Meanwhile,theschenesaresecondordercorrectintime.
简介:Inthispaper,someeffectivecascadicmultigridmethodsareproposedforsolvingthelargescalesymmetricornonsymmetricalgebraicsystemsarisingfromthefinitevolumemethodsforsecondorderellipticproblems.Itisshownthatthesealgorithmsareoptimalinbothaccuracyandcomputationalcomplexity.Numericalexperimentsarereportedtosupportourtheory.
简介:Inthispaper,forgenerallinearmethodsappliedtostrictlydissipativeinitialvalueprobleminHilbertspaces,weprovethatalgebraicstabilityimpliesB-convergence,whichextendsandimprovestheexistingresultsonRunge-Kuttamethods.Specializingourresultsforthecaseofmulti-stepRunge-Kuttamethods,aseriesofB-convergenceresultsareobtained.
简介:Inthispaperweconsidertheglobalconvergenceofanyconjugategradientmethodoftheformd1=-g1,dk+1=-gk+1+βkdk(k≥1)withanyβksatisfyingsumeconditions,andwiththestrongwolfelinesearchconditions.Undertheconvexassumptionontheobjectivefunction,weprevethedescenfpropertyandtheglobalconvergenceofthismethod.
简介:NewalgorithmsbasedonartificialneuralnetworkmodelsarepresentedforcubicNURBScurveandsurfaceinterpolation.Whenallthknotspansareidentical,theNURBScurveinterpolationproceduredegeneratesintothatofuniformrationalB-splinecurves.Ifalltheweightsofdatapointsareidentical,thentheNURBScurveinterpolationproceduredegeneratesintotheintegralB-splinecurveinterpolation.
简介:AniterativemethodofDeJong,GreigandMadan(1985)forobtainingmaximumlikelihoodestimatesforcontingencytablesderivedfromaMover-Stayermodelisconsidered.Itisshownthatthismethodworksforothersamplingschemesleadingtoincompletecontingencytables.Moreover,compar-isonsindicatethatthemethodisveryfast.
简介:LetthelinearsystemAx=bwherethecoefficientmatrixA=(aij)∈Rm,nisanL-ma-trix(thatis,aij>0(?)iandaij≤0(?)i≠j),A=I-L-U,Iistheidentitymatrix,-Land-Uare,respectively,strictlylowerandstrictlyuppertriangularpartsofA.In[1]theauthorsconsideredtwopreconditionedlinearsystems?x=(?)and?x=(?)
简介:Assumethataconvergentmatrixsequence{An}:An→A(n→∞),An,A∈C3×3.Wewanttoformanewmatrixsequence{Hn},derivedfrom{An},whichhasalsoAaslimitandwhoseconvergenceisfasterthantheof{An}.Threerationalextrapolationmeth-odsforacceleratingtheconvergenceofmatrixsequences{An}arepresentedinthispaper.Theunderlyingmethodsarebasedonthegeneralizedinverseformatriceswhichisuseful