Anne-Sarah Briand 124

Anne-Sarah Briand 124

ID:40383585

大小:1.20 MB

页数:10页

时间:2019-08-01

Anne-Sarah Briand 124_第1页
Anne-Sarah Briand 124_第2页
Anne-Sarah Briand 124_第3页
Anne-Sarah Briand 124_第4页
Anne-Sarah Briand 124_第5页
资源描述:

《Anne-Sarah Briand 124》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、AMixtureModelClusteringApproachforTemporalPassengerPatternCharacterizationinPublicTransportAnne-SarahBriand,EtienneCome,MohamedK.ElMahrsi,andLatifaOukhellouˆUniversiteParis-Est,IFSTTAR,COSYS-GRETTIA,F-77447Marne-la-Valle,France´Email:anne-sarah.briand@ifsttar.fr,etienne.come

2、@ifsttar.fr,mohamed-khalil.el-mahrsi@ifsttar.fr,latifa.oukhellou@ifsttar.frAbstract—Smartcarddataprovideagreatnumberofinfor-andlocalauthoritiessinceitcanhelppredictandmanagemationthatareincreasinglyusednowadays.Inthefieldofinflow,measuretheadequacybetweentheexistingofferandtra

3、nsport,theyoffertheopportunitytostudypassengerbehavior,therealusage,andtaketheappropriatemeasurestoadaptleadingtoabetterknowledgeofpublictransitdemandandtotheobserveddemand.Thisgoalcanbeachievedbyusingtherebygrantingthetransportoperatorstheabilitytoadapttheirtransportofferan

4、dservicesaccordingly,bothinspaceandstatisticallearningtechniques,inparticularclusteranalysis:byintime.Inparticular,anaccuratecharacterizationofmobilitypartitioningpassengersintogroupsbasedontravelhours,itispatternsusingdataminingapprocheshasaverystronginterestpossibletoextra

5、ctgeneralpatternsdescribingdifferenttypesfortransportplanningpurposes.Thispaperaimstoproposeofusage(sporadicusage,typicalhome-workcommutebehav-atwo-levelgenerativemixturemodelthatpartitionspassengersior,etc.).Differentapproachestoclusteringpassengersusingaccordingtotheirtemp

6、oralprofiles.Usingthetimestampsofthepassengers’transactionsinthepublictransportnetwork,ticketinglogshavebeenpresentedintheliterature[1]–[4].thefirstlevelmodelsthepassengerspartitioningintoareducedHowever,mostpropositionsrelyonadiscreterepresentationsetofclusters,whereastheseco

7、ndlevelcaptureshowthetripsoftimeinwhichtripsareaggregatedoverpre-definedtimemadebyeachclusterofpassengersaredistributedovertime.slots(e.g.1hour).Thiscanleadtoissuesw.r.t.capturingtravelTheproposedapproachisappliedonrealticketingdatacollectedregularity.Forinstance,frequenttrip

8、smadeontheboundaryfromtheurbantransportnetworkofRennesMetropole(France).´Th

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。