arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.07402cs.LGcs.CY
收藏

行程时间估计的多视角时空模型

Multi View Spatial-Temporal Model for Travel Time Estimation

Wuhan University of Technology(武汉理工大学);East China Normal University(华东师范大学);Sun Yat-sen University(中山大学)

ZiChuan Liu, Zhaoyang Wu, Meng Wang, Rui Zhang

摘要:

出租车到达时间预测是构建智能交通系统的基础。传统的预测方法主要依赖于从交通地图中提取特征,无法对复杂的情况和非线性的时空关系进行建模。因此,我们提出了多视图时空模型(MVSTM)来捕捉时空关系和轨迹特征的相互依赖性。具体来说,我们使用graph2vec模型的空间视图,双通道的时间模型的轨迹视图,和结构嵌入模型的交通语义。在大规模滑行轨迹数据上的实验表明,该方法比现有的新方法更有效。源代码可以在https://github.com/775269512/SIGSPATIAL-2021-GISCUP-4th-Solution上找到。

英文摘要:

Taxi arrival time prediction is essential for building intelligent transportation systems. Traditional prediction methods mainly rely on extracting features from traffic maps, which cannot model complex situations and nonlinear spatial and temporal relationships. Therefore, we propose Multi-View Spatial-Temporal Model (MVSTM) to capture the mutual dependence of spatial-temporal relations and trajectory features. Specifically, we use graph2vec to model the spatial view, dual-channel temporal module to model the trajectory view, and structural embedding to model traffic semantics. Experiments on large-scale taxi trajectory data have shown that our approach is more effective than the existing novel methods. The source code can be found at https://github.com/775269512/SIGSPATIAL-2021-GISCUP-4th-Solution.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑