bigmine-soft-csgdt

bigmine-soft-csgdt

ID:37943247

大?。?.70 MB

頁(yè)數(shù):8頁(yè)

時(shí)間:2019-06-03

bigmine-soft-csgdt_第1頁(yè)
bigmine-soft-csgdt_第2頁(yè)
bigmine-soft-csgdt_第3頁(yè)
bigmine-soft-csgdt_第4頁(yè)
bigmine-soft-csgdt_第5頁(yè)
資源描述:

《bigmine-soft-csgdt》由會(huì)員上傳分享,免費(fèi)在線閱讀,更多相關(guān)內(nèi)容在行業(yè)資料-天天文庫(kù)。

1、Soft-CsGDT:SoftCost-sensitiveGaussianDecisionTreeforCost-sensitiveClassi?cationofDataStreamsNingGuoYanhuaYuMeinaSonggn@bupt.edu.cnyuyanhua@bupt.edu.cnmnsong@bupt.edu.cnJundeSongYuFujdsong@bupt.edu.cnddskyfuyu@gmail.comPCN&CADCenter,BeijingUniversityofPostsandTelecommunicationsBeijing

2、100876,ChinaABSTRACT1.INTRODUCTIONNowadaysinmanyreal-worldscenarios,highspeeddataIndataminingapplications,suchasmedicaldiagnosis,streamsareusuallywithnon-uniformmisclassi cationcostscreditfrauddetection,andintrusiondetection,thedatavol-andthuscallforcost-sensitiveclassi cationalgorit

3、hmsofumeisalwaysverylargeandcontinuouslygrowing.Thesedatastreams.However,onlylittleliteraturefocusesonthisapplicationscanbemodeledasatypicalclassi cationprob-issue.Ontheotherhand,theexistingalgorithmsforcost-lemofdatastreams.Atpresent,inthe eldofdatastreamsensitiveclassi cationcanach

4、ieveexcellentperformanceinclassi cationthemajorconcernisaccuracy-basedlearningthemetricoftotalmisclassi cationcosts,butalwayslead[2,3,4,15],whichaimsatminimizingerrorrate.However,toobviousreductionofaccuracy,whichrestrainstheprac-thereal-worlddatastreamsalwayscomewithnon-uniformtical

5、applicationgreatly.Inthispaper,wepresentanim-misclassi cationcosts,thereforetheexistingdatastreamprovedfolktheorem.Basedonthenewtheorem,theexist-learningalgorithms,whichdon'ttakemisclassi cationcostingaccuracy-basedclassi cationalgorithmcanbeconvertedintoaccount,donotperformwell.into

6、softcost-sensitiveoneimmediately,whichallowsustoInthescenarioofcreditfrauddetection,themisclassi ca-takebothaccuracyandcostintoaccount.Followingtheideationerror,whichismadeinjudgingthebaduserbehaviorsofthistheorem,thesoft-CsGDTalgorithmisproposedtothatcausehugeeconomiclossesasnormalb

7、ehaviors,isal-processthedatastreamswithnon-uniformmisclassi cationwaysmuchmoreserious(inotherwords,highcost)thanthecosts,whichisanexpansionofGDT.Withbothsyntheticoppositetypeoferror,whichjudgessomeoneasbadwhenandreal-worlddatasets,theexperimentalresultsshowthattheyareinfactwithnormal

8、behaviors.Th

當(dāng)前文檔最多預(yù)覽五頁(yè),下載文檔查看全文

此文檔下載收益歸作者所有

當(dāng)前文檔最多預(yù)覽五頁(yè),下載文檔查看全文
溫馨提示:
1. 部分包含數(shù)學(xué)公式或PPT動(dòng)畫(huà)的文件,查看預(yù)覽時(shí)可能會(huì)顯示錯(cuò)亂或異常,文件下載后無(wú)此問(wèn)題,請(qǐng)放心下載。
2. 本文檔由用戶上傳,版權(quán)歸屬用戶,天天文庫(kù)負(fù)責(zé)整理代發(fā)布。如果您對(duì)本文檔版權(quán)有爭(zhēng)議請(qǐng)及時(shí)聯(lián)系客服。
3. 下載前請(qǐng)仔細(xì)閱讀文檔內(nèi)容,確認(rèn)文檔內(nèi)容符合您的需求后進(jìn)行下載,若出現(xiàn)內(nèi)容與標(biāo)題不符可向本站投訴處理。
4. 下載文檔時(shí)可能由于網(wǎng)絡(luò)波動(dòng)等原因無(wú)法下載或下載錯(cuò)誤,付費(fèi)完成后未能成功下載的用戶請(qǐng)聯(lián)系客服處理。
相關(guān)文章
更多
相關(guān)標(biāo)簽