Support Vector Machine For Functional Data Classification

Support Vector Machine For Functional Data Classification

ID:41466201

大小:421.12 KB

页数:26页

时间:2019-08-25

Support Vector Machine For Functional Data Classification_第1页
Support Vector Machine For Functional Data Classification_第2页
Support Vector Machine For Functional Data Classification_第3页
Support Vector Machine For Functional Data Classification_第4页
Support Vector Machine For Functional Data Classification_第5页
资源描述:

《Support Vector Machine For Functional Data Classification》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、SupportVectorMachineForFunctionalDataClassificationFabriceRossia,∗,NathalieVillab,aProjetAxIS,INRIA-Rocquencourt,DomainedeVoluceau,Rocquencourt,B.P.105,78153LeChesnayCedex,FrancebEquipeGRIMM-Universit´eToulouseLeMirail,5all´eesA.Machado,31058Toulousecedex1-FR

2、ANCE∗Correspondingauthor:FabriceRossiProjetAxISINRIARocquencourtDomainedeVoluceau,Rocquencourt,B.P.10578153LECHESNAYCEDEX–FRANCETel:(33)139635445Fax:(33)139635892Emailaddresses:Fabrice.Rossi@inria.fr(FabriceRossi),villa@univ-tlse2.fr(NathalieVilla).Preprints

3、ubmittedtoElsevierScienceJuly1,2005SupportVectorMachineForFunctionalDataClassificationAbstractInmanyapplications,inputdataaresampledfunctionstakingtheirvaluesininfi-nitedimensionalspacesratherthanstandardvectors.Thisfacthascomplexcon-sequencesondataanalysisalg

4、orithmsthatmotivatemodificationsofthem.Infactmostofthetraditionaldataanalysistoolsforregression,classificationandcluster-inghavebeenadaptedtofunctionalinputsunderthegeneralnameofFunctionalDataAnalysis(FDA).Inthispaper,weinvestigatetheuseofSupportVectorMa-chine

5、s(SVMs)forfunctionaldataanalysisandwefocusontheproblemofcurvesdiscrimination.SVMsarelargemarginclassifiertoolsbasedonimplicitnonlinearmappingsoftheconsidereddataintohighdimensionalspacesthankstokernels.Weshowhowtodefinesimplekernelsthattakeintoaccountthefuncti

6、onalnatureofthedataandleadtoconsistentclassification.Experimentsconductedonrealworlddataemphasizethebenefitoftakingintoaccountsomefunctionalaspectsoftheproblems.Keywords:FunctionalDataAnalysis,SupportVectorMachine,Classification,ConsistencyPreprintsubmittedtoEl

7、sevierScienceJuly1,20051INTRODUCTION31IntroductionInmanyrealworldapplications,datashouldbeconsideredasdiscretizedfunc-tionsratherthanasstandardvectors.Intheseapplications,eachobservationcorrespondstoamappingbetweensomeconditions(thatmightbeimplicit)andtheobs

8、ervedresponse.Awellstudiedexampleofthosefunctionaldataisgivenbyspectrometricdata(seesection6.3):eachspectrumisafunctionthatmapsthewavelengthsoftheilluminatinglighttothecorrespondingab-sorbances(

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。