區(qū)間數(shù)據(jù)庫(kù)的構(gòu)建及其在知識(shí)發(fā)現(xiàn)中的應(yīng)用.pdf

1、廣西師范大學(xué)碩士研究生學(xué)位論文◆7847口6區(qū)間數(shù)據(jù)庫(kù)的構(gòu)建及其在知識(shí)發(fā)現(xiàn)中的應(yīng)用ConstructionofIntervalDatabasesandItsApplicationsinKnowledgeDiscovery院系：年級(jí)：學(xué)科專業(yè)：研究方向：導(dǎo)師姓名：研究生：完成時(shí)間：數(shù)學(xué)與計(jì)算機(jī)科學(xué)學(xué)院2002級(jí)計(jì)算機(jī)軟件與理論數(shù)據(jù)庫(kù)與數(shù)據(jù)挖掘張師超教授、嚴(yán)小衛(wèi)教授尹云飛2005年4月廣西師范人學(xué)數(shù)學(xué)與計(jì)算機(jī)科學(xué)學(xué)院，桂林，中國(guó)(54100

2、4)廣西師范大學(xué)碩士學(xué)位論文AbstractAssociationruleminingisoneofimportanttopicsindataminingItisaprocedureofidentifyingstronginteractionsamongitemsetsindatabasesForexampleminingatransactiondatabaseinasupermarketcandiscoveryassociations

3、fcustomerbehaviors)withindifferentcommodities，suchasbreadandmilk，coffeeandsugar，toothpasteandtoothbrushWhilethevarecommonsense，associationrtileminingcanfindmanyotherinterestinginteractionssuehas‘beeranddiaper’ThisIeadsto

4、adeeperresearchondevelopmentandwideapplicationsofassociationruleminingForexample，itcanbehelpfulinsolvingstockcontrol，salespromotion，andcustomerbehavioranalysisinsupermarketsWiththedevelopmentofthesupermarketandthecommodi

5、tyindustries，bindingsale，namelybindingcommodity，israpidlypopularizedandbecomesanimportantmeaningsofgainingprofitsAssociationruleminingassistsinbindingsalesAfterourdeeperunderstandingandresearchingakindofnovelassociationr

6、ulesoftheformA一佃，C，，referredtoasintervalrules，isproPosedandstudiedinthisthesisTherearemanyadvantagesforusingintervalvaluestorepresentbindjngcommoditiesFirstiYanintervalcontainsmoreinformationthanasinglevalueBecauseasingl

7、evalueoffersthesinglevalueitself，whileanintervaloffersthedistributionofthevalues，ieanynumbersintheintervalcanbetakenTofollowupanintervalismoreexpressivethanameanthatistosayentropyofanintervalislargerthantheentropYofamean

8、ThirdlyinanintervaldatabaseitcanbediscoveredwhichcommoditiesarefittobeboundThisismuehmoreimpoftantinrealityBasedontheresearchabouttheintervalclusteringalgorithmsthispaperproposestotakethetwofieldsintraditionaldatabaseasa

9、newfieldandusesoneofthemtoexpressthe‘leftfield’ofthenewfield(theleftboundaryoftheintervallanduSestheothertoexpressthe‘ri曲tfield’ofthenewfield(therightboundaryoftheinterval)，SoweobtaintheintervaldatabaseThisPaperconductsa

10、deeoerresearchonthealgorithmsofstrongassociationrules(affinityrules)，andoffersthefunctionformulaforstrongassociationrules0nthebasisoftheresearchaboutthesefunetionvaluesacompleteintervalallocation1atticesystemisconstructe

11、d，andapropertysatisfiedbythecompleteintervalallocationlatticesystem、ieAAC=BACandAyC=ByCjA=BisusedtobindcommoditiesTheessenceofintervalassociationruleminingishowtofindoutthebindingcommoditiesie，todecidewhichcommoditiessho