Please wait a minute...
Vis Inf
Vis Inf  2019, Vol. 3 Issue (3): 140-149    DOI: 10.1016/j.visinf.2019.10.002
论文     
利用主题子轨迹对出租车轨迹进行可视分析
Huan Liu, Sichen Jin, Yuyu Yan, Yubo Tao, Hai Linb
State Key Laboratory of CAD&CG, Zhejiang University, China
Visual analytics of taxi trajectory data via topical sub-trajectories
Huan Liu, Sichen Jin, Yuyu Yan, Yubo Tao, Hai Lin
State Key Laboratory of CAD&CG, Zhejiang University, China
 全文: PDF 
摘要： 基于GPS定位的出租车轨迹数据挖掘对交通运输和城市规划具有重要意义。主题模型可以有效地从出租车轨迹中提取语义信息，用于分析城市道路的交通情况。常用的LDA模型忽略了轨迹的方向，不能准确地挖掘出租车的运动模式，从而影响交通情况的分析粒度。因此，有必要在主题建模时考虑轨迹的方向信息。

出租车轨迹由若干个GPS位置组成，本文首先将GPS位置与道路名相匹配来对轨迹数据进行文本化，然后利用bigram主题模型提取轨迹主题。由于bigram模型根据前n-1个单词预测当前单词，因此将其结合主题模型用于轨迹主题的提取可以包含方向信息。

关键词： 轨迹模式挖掘;  轨迹可视化;  视觉分析;  主题模型    
Abstract: GPS-based taxi trajectories contain valuable knowledge about movement patterns for transportation and urban planning. Topic modeling is an effective tool to extract semantic information from taxi trajectory data. However, previous methods generally ignore trajectory directions that are important in the analysis of movement patterns. In this paper, we employ the bigram topic model rather than traditional topic models to analyze textualized trajectories and consider the direction information of trajectories. We further propose a modified Apriori algorithm to extract topical sub-trajectories and use them to represent each topic. Finally, we design a visual analytics system with several linked views to facilitate users to interactively explore movement patterns from topics and topical sub-trajectories. The case studies with Chengdu taxi trajectory data demonstrate the effectiveness of the proposed system.
Key words: Trajectory pattern mining    Trajectory visualization    Visual analytics    Topic model
出版日期: 2019-12-05
通讯作者: Huan Liu     E-mail: 21721064@zju.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Huan Liu
Sichen Jin
Yuyu Yan
Yubo Tao
Hai Lin

引用本文:

Huan Liu, Sichen Jin, Yuyu Yan, Yubo Tao, Hai Lin. Visual analytics of taxi trajectory data via topical sub-trajectories. Vis Inf, 2019, 3(3): 140-149.

链接本文:

http://www.zjujournals.com/vi/CN/10.1016/j.visinf.2019.10.002    或    http://www.zjujournals.com/vi/CN/Y2019/V3/I3/140

[1] Christina Gillmann, Robin G.C. Maack, Tobias Post, Thomas Wischgoll, Hans Hagen. 在知晓其不确定性的情况下运用分层图像语义进行锁孔手术规划的工作流程[J]. Vis Inf, 2018, 2(1): 26-36.
[2] Jian-Syuan Wong, Xiaolong “Luke” Zhang. MessageLens:可对MOOC论坛讨论进行多方面探索的可视分析系统[J]. Vis Inf, 2018, 2(1): 37-49.
[3] TakanoriFujiwara, JianpingKelvinLi, MisbahMubarak, CaitlinRoss, Christopher D.Carothers, Robert B.Ross, Kwan-LiuMa. 用于优化超级计算系统中大规模网络性能的可视分析系统[J]. Vis Inf, 2018, 2(1): 98-110.
[4] Yi Yang, Quanming Yao, Huamin Qu. VISTopic:通过分层主题建模来理解大型文本集的可视分析系统[J]. Vis Inf, 2017, 1(1): 40-47.