文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > IT/计算机 > 互联网 > 2014A rough set-based method for updating decision rules on attribute
侵权投诉

2014A rough set-based method for updating decision rules on attribute

Aroughset-basedmethodforupdatingdecisionrulesonattributevalues’coarsening

andre ning

HongmeiChen,TianruiLi*,IEEESeniorMember,ChuanLuo,Shi-JinnHorng,IEEEMember,

andGuoyinWang,IEEESeniorMember

Abstract—RuleinductionmethodbasedonRoughSetTheory(RST)hasreceivedmuchattentionrecentlysinceitmaygenerateaminimalsetofrulesfromthedecisionsystemforreal-lifeapplicationsbyusingofattributereductionandapproximations.Thedecisionsystemmayvarywithtime,e.g.,thevariationofobjects,attributesandattributevalues.ThereductionandapproximationsofthedecisionsystemmayalteronAttributeValues’CoarseningandRe ning(AVCR),akindofvariationofattributevalues,whichresultsinthealterationofdecisionrulessimultaneously.Thispaperaimsfordynamicmaintenanceofdecisionrulesw.r.t.AVCR.Thede nitionofminimaldiscernibilityattributesetisproposed rstly,whichaimstoimprovetheef ciencyofattributereductioninRST.Then,principlesofupdatingdecisionrulesincaseofAVCRarediscussed.Furthermore,theroughset-basedmethodsforupdatingdecisionrulesintheinconsistentdecisionsystemareproposed.ThecomplexityanalysisandextensiveexperimentsonUCIdatasetshaveveri edtheeffectivenessandef ciencyoftheproposedmethods.IndexTerms—Inconsistentdecisionsystem,Roughsettheory,Incrementallearning,Decisionrule,Attributereduction,Approximations

1INTRODUCTION

OUGH

SetTheory(RST),animportantmethodforclassi cationproblems[35],hasbeenwidelyusedinintelligentinformationprocessing[29],machinelearningandimageprocessing[20][34].If-thendeci-sionrulesdeducedbyRSTarerelatedtotwokindsofworks,i.e.,attributereductionandcomputationofapproximations.AttributereductionisanimportantapplicationofRST[2][4][12][23][42],whichaimstoremovetheunnecessaryattributesfromthedecisionsystemwhilekeepingitsclassi cationability(orotherproperties).Certainanduncertaindecisionrulesareinduceddirectlyfromapproximationsofthedecisionclasses.Attributereductiondecidestheantecedentofdecisionrules.Approximationsareusedtodeducedecisionrulesfromdifferentequivalenceclassesindifferentregions.Inreal-lifeapplications,thedecisionsystemS=(U,A,V,F,G)evolvesdynamically,i.e.,

R

第1页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email