预览加载中，请您耐心等待几秒...

基于信息量的悲观多粒度粗糙集粒度约简.docx

预览
1/5
2/5
3/5
4/5
5/5

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

基于信息量的悲观多粒度粗糙集粒度约简 Abstract Informationmeasureiswidelyusedindatacompression,informationtheory,andotherfields.Granularcomputingisapromisingmethodinroughsettheory,whichcanprocessmulti-granulardataandreducecomplexity.Basedonthesetwotheories,pessimisticmulti-granularityroughset(PMGRS)isproposedandusedforgranularreductionindataanalysis.Inthispaper,weintroduceaspecificapplicationofPMGRS,whichismulti-granularityroughsetforgranularreductionbasedoninformationmeasure.Wepresentitsdefinition,algorithm,andanalyzeitseffectivenessthroughexperimentaltests. Keywords:Informationmeasure,Granularcomputing,Roughsettheory,Multi-granularity,Pessimisticmulti-granularityroughset(PMGRS) Introduction Dataanalysisisattheheartofscientificresearch,technologicalinnovation,anddecision-making.Withtherapiddevelopmentofbigdata,thecomplexityanddiversityofdatahaveincreasedsharply.Therefore,howtoextractvaluableinformationfrommassivedatahasbecomeanessentialgoalofdataanalysis.Asapowerfultoolfordataanalysisandprocessing,roughsettheoryhasbeenwidelystudiedandappliedinvariousfields,suchasdatamining,machinelearning,andpatternrecognition.However,traditionalroughsettheoryonlydealswithsinglegranularitydata,whichisinsufficientforcomplexdataanalysis. Granularcomputingisapromisingmethodinroughsettheory,whichcanprocessmulti-granulardataandreducecomplexity.Multi-granulardatarefertodatawithdifferentlevelsofgranularity,suchasfine-grained,medium-grained,andcoarse-graineddata.Granularcomputingcanunifyandclassifythesedifferentlevelsofgranularityintomeaningfulinformationunits.Basedongranularcomputing,manygranularreductionalgorithmshavebeenproposed,whichcaneffectivelyreducethecomplexityofdataanalysis. Informationmeasureisafundamentalconceptininformationtheoryandhasbeenwidelyusedindatacompression,codingtheory,andsignalprocessing.Entropy,mutualinformation,anddivergencearetypicalinformationmeasuresusedtoquantifytheinformationcontentandsimilaritybetweendata.Informationmeasureprovidesaquantitativebasisforevaluatingthequalityofdat