[交通运输] InferringTripPurposefromMobilePhoneGPSDatawithSupportVectorMachines

228 0
2024-12-8 12:50 | 查看全部 阅读模式

InferringTripPurposefromMobilePhoneGPSDatawithSupportVectorMachines.pdf
SinceGlobalPositioningSystem(GPS)moduleshavebeenattachedtosmartphones,manyresearchesfocusonhowtoobtainthepersonaltrip(PT)informationfromthemobilephone.Oneofthechallengesistoinfertrippurpose(oridentifyactivitytype)fromthesecontinuousGPSdata.ThispaperfocusesonobtainingtrippurposewiththemethodologyofSupportVectorMachines(SVM)whichhasnotbeenutilizedinthisfieldintheexistingresearches.ThreedifferentkindsofSVMareappliedandone-against-restSVMshowsahigheraccuracy.Furthermore,attributesrelatedtoactivityintensivelyinfluencetheaccuracyoftrippurposeinference.Also,excluding"others"purposefromthetrippurposelistimprovestheinferenceaccuracy.Thefinalfindingisthattreatingcontinuousbusinesstripsasasinglebusinesstripwillnotalwaysimprovetheaccuracybutdemonstratesthesignificantinfluencesimultaneouslyfromattributesrelatedtoactivity,demographicandtrip.
作者:GongLei YamamotoToshiyuki MorikawaTakayuki
作者单位:DepartmentofCivilEng.,NagoyaUniversity,Furo-cho,Chikusa-ku,Nagoya,464-8603,JapanEcoTopiaScienceInstitute,NagoyaUniversity,Furo-cho,Chikusa-ku,464-8603,JapanInstituteofInnovationforFutureSociety,NagoyaUniversity,Furo-cho,Chikusa-ku,464-8603,Japan
母体文献:2015年南京第十四届亚太智能交通论坛论文集
会议名称:2015年南京第十四届亚太智能交通论坛  
会议时间:2015年4月27日
会议地点:南京
主办单位:交通运输部
语种:chi
分类号:
关键词:ITS  trippurposeinference  activitytypeidentification  GPS  SVM  supervisedmachinelearning
在线出版日期:2019年1月18日
基金项目:
相似文献
相关博文
文件大小:
986.99 KB
高速下载
2026 资料下载 联系邮件:1991591830#qq.com 浙ICP备2024084428号-1