简介:Duetothecapabilityofreflectingsocialperceptiononsemanticofresources,folksonomyhasbeenproposedtoimprovethesociallearningforeducationandscholarresearching.However,itsactualimpactissignificantlyinfluencedbythesemanticambiguityproblemoftags.So,inthispaper,weproposedanovelwayofdetectinghomonyms,oneofthemainsourcesoftag’ssemanticambiguityproblem,innoisyfolksonomies.Thestudyisbasedontwohypotheses:1)Usershavingdifferentintereststendtohavedifferentunderstandingofthesametag.2)Usershavingsimilarinteresttendtohavecommonunderstandingofthesametag.Therefore,wefirstlydiscoverusercommunitiesaccordingtousers’interests.Then,tagcontextsarediscoveredinsubsetsoffolksonomyonthebasisofusercommunities.Theexperimentalresultsshowthatourmethodiseffectiveandoutperformthemethodfindingtagcontextsusingalltagsinfolksonomywithoverlappingclusteringalgorithmespeciallywhenvarioususershavingdifferentinterestsarecontainedbythefolksonomy.
简介:Withthevigorousexpansionofnonlinearadaptivefilteringwithreal-valuedkernelfunctions,itscounterpartcomplexkerneladaptivefilteringalgorithmswerealsosequentiallyproposedtosolvethecomplex-valuednonlinearproblemsarisinginalmostallreal-worldapplications.ThispaperfirstlypresentstwoschemesofthecomplexGaussiankernel-basedadaptivefilteringalgorithmstoillustratetheirrespectivecharacteristics.ThenthetheoreticalconvergencebehaviorofthecomplexGaussiankernelleastmeansquare(LMS)algorithmisstudiedbyusingthefixeddictionarystrategy.ThesimulationresultsdemonstratethatthetheoreticalcurvespredictedbythederivedanalyticalmodelsconsistentlycoincidewiththeMonteCarlosimulationresultsinbothtransientandsteady-statestagesfortwointroducedcomplexGaussiankernelLMSalgonthmsusingnon-circularcomplexdata.Theanalyticalmodelsareabletoberegardasatheoreticaltoolevaluatingabilityandallowtocomparewithmeansquareerror(MSE)performanceamongofcomplexkernelLMS(KLMS)methodsaccordingtothespecifiedkernelbandwidthandthelengthofdictionary.
简介:Ageneralversionoftheinvertedexponentialdistributionisintroduced,studiedandanalyzed.ThisgeneralizationdependsonthemethodofMarshall-Olkintoextendafamilyofdistributions.Somestatisticalandreliabilitypropertiesofthisfamilyarestudied.Inaddition,numericalestimationofthemaximumlikelihoodestimate(MLE)parametersarediscussedindetails.Asanapplication,somerealdatasetsareanalyzedanditisobservedthatthepresentedfamilyprovidesabetterfitthansomeotherknowndistributions.
简介:Bistaticforward-lookingsyntheticapertureradar(SAR)hasmanyadvantagesandapplicationsowingtoitstwodimensionalimagingcapability.Therecouldbevariousimagingconfigurationsbecauseofthegeometricflexibilityofbistaticplatforms,resultinginkindsofmodelsbuiltindependentlyamongwhichtherecouldbesomesimilareventhesamemotionfeatures.Comprehensiveresearchonsuchsystemsinamorecomprehensiveandgeneralpointofviewisrequiredtoaddresstheirdifferenceandconsistency.PropertyanalysisofbistaticforwardlookingSARwitharbitrarygeometryisachievedincludingstripmapandspotlightmodesonairborneplatform,missile-borneplatform,andhybridplatformofboth.Emphasisisplacedonazimuthspacevarianceofsomekeyparameterssignificantlyaffectingthesubsequentimagingprocessing,basedonwhichthefrequencyspectraarefurtherdescribedandcomparedconsideringrespectivefeaturesofdifferentplatformsforfrequencyimagingalgorithmdeveloping.Simulationresultsconfirmtheeffectivenessandcorrectnessofouranalysis.
简介:Thispaperpresentsahumanactionrecognitionmethod.Itanalyzesthespatio-temporalgridsalongthedensetrajectoriesandgeneratesthehistogramoforientedgradients(HOG)andhistogramofopticalflow(HOF)todescribetheappearanceandmotionofthehumanobject.Then,HOGcombinedwithHOFisconvertedtobag-of-words(BoWs)bythevocabularytree.Finally,itappliesrandomforesttorecognizethetypeofhumanaction.Intheexperiments,KTHdatabaseandURADLdatabasearetestedfortheperformanceevaluation.Comparingwiththeotherapproaches,weshowthatourapproachhasabetterperformancefortheactionvideoswithhighinter-classandlowinter-classvariabilities.IndexTermsBag-of-words(BoWs),densetrajectories,histogramofopticalflow(HOF),histogramoforientedgradient(HOG),randomforest,vocabularytree.
简介:Forasyntheticapertureradar(SAR)systemmountedonageostationaryEarthorbit(GEO)satellite,thetrackcanbecurvilinear.Thus,abistaticSARsystembasedupongeostationarytransmitterand'receive-only'SARsystemonboardairplanes,namelyGEOspaceborne-airbornebistatic(GEOSA-BiSAR),issignificantlydifferentfromthetraditionalbistaticSAR.ThispapermainlystudiestheresolutioncharacteristicoftheslidingspotlightGEOSA-BiSARsystem.Firstly,thecommonazimuthcoverageandcoherentaccumulatedtimearetheoreticallyanalyzedindetail.Then,basedonthegradientmethod,theaccuratetwodimensionalresolutionofaGEOSA-BiSARsystemisanalyticallycalculated.Finally,thesimulationdatashowthecorrectnessandeffectivenessoftheproposedresolutionanalysismethod.