資源描述：
《基于粗糙集的屬性約簡(jiǎn)算法及其應(yīng)用研究》由會(huì)員上傳分享，免費(fèi)在線閱讀，更多相關(guān)內(nèi)容在學(xué)術(shù)論文-天天文庫(kù)。
1、江南大學(xué)碩士學(xué)位論文基于粗糙集的屬性約簡(jiǎn)算法及其應(yīng)用研究姓名：顏艷申請(qǐng)學(xué)位級(jí)別：碩士專業(yè)：檢測(cè)技術(shù)與自動(dòng)化裝置指導(dǎo)教師：楊慧中20080301AbstractRoughSet限S)theory,introducedbyPawlakZ，isanovelmathematicaltooltodeal塒tllvaguenessanduncertainty．Itisapowerfulmathematicaltoolforanalyzinguncertain，fuzzyknowledgeandcaneffectivelydeal謝t11theimpre
2、cise，incomplete，oruncertaindata．Nowithasattractedmuchattentionofresearchersaroundtheword．Inrecentyears，ithasbeensuccessfullyappliedtodatamining，machinelearning，knowledgediscoveryfromdatabase，decisionsupportsystems，faultdiagnosisetc．Thisarticleemphaticallystudiesononeofthei
3、mportantproblemofRoughSettheory—也ereductionofthedecisiontable．Attributereductionpreservestheoriginalmeaningandreducestheirrelevantandunimportantknowledge．Thedetailsarestudiedasfollows：Inregardtoacompleteanddiscreteinformationsystem，considerattributereductionintheviewofinfo
4、rmationtheory．Adevelopedattributeimportancemeasuremethodisdefinedbasedonthemutualinformationbetweenselectedattributeanddecisionattribute，andthemeasureisusedastheheuristicinformationintheproposedalgorithm．Conditionalinformationentropyisusedtocomputerelevanceofattributesandi
5、tisusedinfitnessfunctionofgeneticalgorithmtoassurereductionhasfewattributesandrelevancebetweenattributes．TraditionalRoughSettheoryisgenerallyincapableofhandlingincompleteinformationsystem．AfterstudyingtheextensionsofRoughSetmodel，pointouttheirshortages．Foressentialityofatt
6、ributeexistingdifference，adevelopedattributeimportancemeasuremethodisdefinedbasedonthedifferencedegreeofattributes。It’Sproposed趴attributereductionalgorithmbasedonconnectiondegreeofessentialityofattribute．Anexampleshowsthattheproposedalgorithmisaneffectivemethod．AnothertheR
7、oughSettheorydefectwhichblocksitsdevelopmentandapplicationisthatitcallnotbeemployedoncontinuousvaluesdirectly．Previouslydiscretizationmethodisappliedbeforehandinordertotransformthedataintodiscretevalues，butthismayresultininformationloss．nlenotionsofsimilaritybetweenobjects
8、andimprovedgeneralimportantdegreeofanattributeareintroduced．Theglobalsimilaritymeasurebet
