Finding Popular Routes With Minimum Travel Cost From Taxi Trajectories 的文档的文档.pptx

下载文档

0
0
约5.53千字
约 25页
2023-06-10 发布于北京
举报
版权申诉
保障服务

Finding Popular Routes With Minimum Travel Cost From Taxi Trajectories 的文档的文档.pptx

1、本文档共25页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。

Popular Route Planning with Travel CostEstimationHuiping Liu, Cheqing Jin, Aoyin Zhou Institute for Data Science and Engineering, Software Engineering Institute,East China Normal University, China 1 AgendaIntroductionOverview Popular Traverse Graph ConstructionTravel Cost ModellingRoute PlanningExperimentsConclusion2 IntroductionShortest or fastest path is not enough in route planningABFinding the Popular Route with Accurate Travel Cost Estimation3 Existing WorkYuan J, Zheng Y, Zhang C, et al. T-drive: driving directions based on taxi trajectories. (SIGSPATIAL 2010)Based on road network informationPractical fastest path is not always popularWang Y, Zheng Y, Xue Y. Travel time estimation of a path using sparse trajectories. (KDD 2014)Travel time estimation of a given pathCan not be directly used in route planning4 Overview5 Popular Traverse Graph ConstructionA popular route has a support ≥ τ (predefined) Road network information is not always available.We try to construct a popular traverse graph G=(V,E) from trajectories, where V is the set of popular locations and E is the set of popular routes between locations.6 Popular Traverse Graph ConstructionPoints clusteringA popular route has a support ≥ τ (predefined) Road network information is not always available.We try to construct a popular traverse graph G=(V,E) from trajectories, where V is the set of popular locations and E is the set of popular routes between locations.7 Popular Traverse Graph ConstructionPoints clusteringTrajectory clustering(τ = 2)A popular route has a support ≥ τ (predefined) Road network information is not always available.We try to construct a popular traverse graph G=(V,E) from trajectories, where V is the set of popular locations and E is the set of popular routes between locations.8 Modeling travel cost on popular routeThe travel cost on each route varies at different timeWe mining the travel cost pattern at different time slots for an accurate time cost estimationA good partition for