欢迎来到天天文库
浏览记录
ID:49700719
大小:7.27 MB
页数:67页
时间:2020-03-04
《Mining High Utility Itemsets Based on Multiple Minimum Support and Multiple Minimum Utility Thresholds论文.pdf》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库。
1、afcaiCoiiGdentialiClssiitonNo.tyUDCj式乂(^建攀纖NANJINGUNIVERSITYOFSCIENCE&TECHNOLOGYM,astersThesisMininHihUtilitItemsetsBasedOnggyMultipleMinimumSupportandMultipleMinimumUtilityThresholdsMdFazlaElaheSupervisorProfessorKunZhangDer
2、eeTitleMasterofEngineeringgDiscilineComputerSoftwareandTheorypResearchFieldDataMining*SubmissionDate15December.2016Note1:Universaldecimalclassification(UDC)M’astersThesisMinhiHihUtilitItemsetsBasedOnggyMultipleMinimumSupportand
3、MultipleMinimumUtilitThresholdsyByMdFazlaElaheSupervisedbyProf.KunZhangNaninUniversitofScience皮TechnolojgygyFebruar2017y,DeclarationIherebydeclare化at舶ssubmissionismyownworkand化at,to化eb的tofmyknowledeandbeliefitcontainsnomate
4、rialreviouslublishedorwrittenbg,pypyanotherersonormaterialwhichhastoasubstantialextentbeenaccetedfortheppawardofanyotherdereeordiplomaatanuniversitorotherinstitutionofgyyhigherlearning,exceptwheredueacknowledgmenthasbeenmadeint
5、hetext.心 ̄於口Signature:Date:!Authoriza社onStatementIherebauthorizedNaninUniversitofScienceandTechnolotodeosittheyjgygypsoftcoandhardcoofthis化esisand!;〇releaseartofortheentire化esis化pypy,potheroranizationsorin出viduals.The化sofconfid
6、entialitmu巧beholdgyconfidentialaccording化relevantreulationsandrocedures.gpi八/〇早^^Sgnature:Date:/_三M’astershesisMininHihUtilitItemsetsBasedOnMultileMinimumTggypSuortanduteinimumttressppMliplMUiliyThhold摘要髙效用项集挖掘指的是从交易数据库中挖掘那些含有比用户指定阀值更高效
7、用值的项集一。这在现实生活中是个重要的数据挖掘任务并且有着很广泛的应用。商效用一项集挖掘是当前研究的热点和难点,近些年提出了些方法来解决该问题。这些方法-MMU使用不同的搜索策略、数据结构、剪枝技术来提高方法的效率。诸如HUIM(--Mu-HiUtilitItemsetsMininltileMinimumUtilitthresho化高效用项集挖掘多重最班ygpy--Mu-小效用阔值算法)和MHUGrowth(ltiplehighutilitygrowth,多重高效用成长算法")的算法克服了在整个数据库中
8、使用单阀值的局限性,然而它们仍然难W解决稀有"-项问题。目前最常用的高效用项集挖掘算法E巧M(EficienthighutilityItem
此文档下载收益归作者所有