简介：AimingtosolvethemisclassificationproblemsofunsupervisedpolarimetricWishartclassificationalgorithmbasedonFreemandecomposition,anunsupervisedPolarimetricSyntheticApertureRadar(SAR)Interferomery(PolInSAR)classificationalgorithmbasedonoptimalcoherencesetparametersisstudiedandproposed.ThisalgorithmusestheresultofFreemandecompositiontodividetheimageintothreebasiccategoriesincludingsurfacescattering,volumescattering,anddouble-bounce.Then,thePolInSARoptimalcoherencesetparametersareusedtofinelydivideeachofthethreebasiccategoriesinto9categories,andthewholeimageisdividedinto27categories.BecauseboththeFreemandecompositionresultandoptimalcoherencesetparametersindicatespecificscatteringcharacteristics,thewholeimageismergedinto16categoriesbasedonphysicalmeaning.Atlast,theWishartclusterisemployedtoobtainthefinalclassificationresult.Topreservethepurityofscatteringcharacteristics,pixelswithsimilarscatteringcharacteristicsarerestrictedtobeclassifiedwithotherpixels.Thefinalclassificationresultseffectivelyresolvethemisclassificationproblem,notonlythebuildingscanbeeffectivelydistinguishedfromvegetationinurbanareas,butalsotheroadiswelldistinguishedfromgrass.Inthispaper,theE-SARPolInSARdataofGermanAerospaceCenter(DLR),areusedtoverifytheeffectivenessofthealgorithm.

简介：Fieldcomputation,anemergingcomputationtechnique,hasinspiredpassionofintelligencescienceresearch.Anovelfieldcomputationmodelbasedonthemagneticfieldtheoryisconstructed.Theproposedmagneticfieldcomputation(MFC)modelconsistsofafieldsimulator,anon-derivativeoptimizationalgorithmandanauxiliarydataprocessingunit.ThemathematicalmodelisdeducedandprovedthattheMFCmodelisequivalenttoaquadraticdiscriminantfunction.Furthermore,thefiniteelementprototypeisderived,andthesimulatorisdeveloped,combiningwithparticleswarmoptimizerforthefieldconfiguration.Twobenchmarkclassificationexperimentsarestudiedinthenumericalexperiment,andonenotableadvantageisdemonstratedthatlesstrainingsamplesarerequiredandabettergeneralizationcanbeachieved.

简介：

简介：基于地面的云分类由于在在不同大气的条件下面的云的外观的极端变化是挑战性的。质地分类技术最近被介绍了处理这个问题。一个新奇质地描述符，突出的本地二进制模式(SLBP)，为基于地面的云分类被建议。SLBP利用最经常发生的模式(突出的模式)捕获描述的信息。这个特征使SLBP柔韧到噪音。用基于地面的云图象的试验性的结果证明建议方法能比当前的最先进的方法完成更好的结果。

简介：

简介：电子显微镜学图象分类的目的是根据他们的类似把设计图象分成不同的类。区分图象通常要求这些图象首先被排列。然而，图象的排列是为一个高度吵闹的数据集合的一项困难的任务。在这份报纸，我们为避免排列建议一个翻译和基于Fourier变换不变的旋转。一个新奇分类方法因此被建立。加速分类速度，第二等班在分类过程被介绍。测试结果也证明我们的方法很有效、有效。分类结果用我们的不变也与用另外的存在invariants的结果相比，显示出那我们的不变导致好一些的结果。[从作者抽象]

简介：Inthispaper,wepresentasimplebutpowerfulensembleforrobusttextureclassification.Theproposedmethodusesasingletypeoffeaturedescriptor,i.e.scale-invariantfeaturetransform(SIFT),andinheritsthespiritofthespatialpyramidmatchingmodel(SPM).Inaflexiblewayofpartitioningtheoriginaltextureimages,ourapproachcanproducesufficientinformativelocalfeaturesandtherebyformareliablefeaturepondortrainanewclass-specificdictionary.Totakefulladvantageofthisfeaturepond,wedevelopagroup-collaborativelyrepresentation-basedstrategy(GCRS)forthefinalclassification.Itissolvedbythewell-knowngrouplasso.Butwegobeyondofthisandproposealocality-constraintmethodtospeedupthis,namedlocalconstraint-GCRS(LC-GCRS).Experimentalresultsonthreepublictexturedatasetsdemonstratetheproposedapproachachievescompetitiveoutcomesandevenoutperformsthestate-of-the-artmethods.Particularly,mostofmethodscannotworkwellwhenonlyafewsamplesofeachcategoryareavailablefortraining,butourapproachstillachievesveryhighclassificationaccuracy,e.g.anaverageaccuracyof92.1%fortheBrodatzdatasetwhenonlyoneimageisusedfortraining,significantlyhigherthananyothermethods.

简介：

简介：Objective:Toexploretherelationshipbetweenperoxisomeproliferatoractivatedreceptor-gamma(PPARγ)andperoxisomeproliferator-activatedreceptor-gammacoactivator-1(PGC-1)expressioningastriccarcinoma(GC),andanalyzetheircorrelationswithclinicopathologicalfeaturesandclinicaloutcomesofpatients.Methods:Thetwo-stepimmunohistochemicalmethodwasusedtodetecttheexpressionofPPARγandPGC-1in179casesofGC,and108casesofmatchednormalgastricmucosa.Besides,16casesoffreshGCspecimensandcorrespondingnormalgastricmucosaweredetectedforPGC-1expressionwithWesternblotting.Results:ThepositiveratesofPPARγandPGC-1expressionweresignificantlylowerinGC(54.75%,49.16%)thaninnormalgastricmucosa(70.37%,71.30%),respectively(P<0.05).ThedecreasedexpressionofPGC-1inGCwasconfirmedinourWesternblotanalysis(P=0.004).PPARγandPGC-1expressionswererelatedtoLauren’stypesofGC(P<0.05).PositivecorrelationwasfoundbetweenPPARγandPGC-1expressioninGC(rk=0.422,P<0.001).ThesurvivaltimeofPPARγnegativeandpositivepatientswas36.6±3.0vs.38.5±2.7months,andnostatisticaldifferencewasfoundbetweenthe5-yearsurvivalratesoftwogroups(34.4%vs.44.1%,P=0.522,log-ranktest);thesurvivaltimeofPGC-1negativeandpositivepatientswas36.2±2.8vs.39.9±2.9months,whilenostatisticaldifferencewasfoundbetweenthe5-yearsurvivalratesofthetwogroups(32.0%vs.48.2%,P=0.462,log-ranktest)Conclusions:DecreasedexpressionofPPARγandPGC-1inGCwasrelatedtotheLauren’sclassification.TheirexpressionsinGCwerepositivelycorrelated,indicatingthattheirfunctionsingastriccarcinogenesismaybecloselyrelated.