Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (1): 54-59.DOI: 10.11772/j.issn.1001-9081.2017.01.0054

Previous Articles     Next Articles

Trajectory structure-based moving object hotspots discovery

LYU Shaoqian, MENG Fanrong, YUAN Guan   

  1. College of Computer Science and Technology, China University of Mining and Technology, Xuzhou Jiangsu 221116, China
  • Received:2016-08-15 Revised:2016-08-25 Online:2017-01-10 Published:2017-01-09
  • Supported by:
    This work is supported by the Natural Science Foundation of Jiangsu Province (BK20130208).

基于轨迹结构的移动对象热点区域发现

吕绍仟, 孟凡荣, 袁冠   

  1. 中国矿业大学 计算机科学与技术学院, 江苏 徐州 221116
  • 通讯作者: 吕绍仟
  • 作者简介:吕绍仟(1992-),男,江苏南京人,硕士研究生,主要研究方向:轨迹数据挖掘、机器学习;孟凡荣(1962-),女,辽宁沈阳人,教授,博士,CCF会员,主要研究方向:数据库、数据挖掘;袁冠(1982-),男,江苏徐州人,副教授,博士,CCF会员,主要研究方向:轨迹数据挖掘。
  • 基金资助:
    江苏省自然科学基金资助项目(BK20130208)。

Abstract: Focused on the issue that the existing algorithms are unable to accurately detect active hotspots from trajectory data, a novel Trajectory Structure-based Hotspots discovery (TS_HS) algorithm was proposed. TS_HS consisted of the following two algorithms:Candidate Hotspots Discovery (CHSD) algorithm and Hotspots Filter (HSF) algorithm. First, trajectory dense regions were detected by the grid based clustering method CHSD as candidate hotspots. Second, the active hotspots region of moving objects were filtered by using HSF algorithm according to moving feature and time-varying characteristic of trajectories. The experiments on the Geolife dataset show that TS_HS is an effective solution for multi-density active hotspot problem, compared with Global Density threshold based Hot Region discovery (GD_HR) and Spatio-temporal Hot Spot Region Discovering (SDHSRD). The simulation results show that the proposed framework can detect active hotspots effectively based on the structure feature and time-varying characteristic of trajectory.

Key words: moving object, trajectory structure, hotspot, trajectory data, data mining

摘要: 针对现有热点区域发现算法难以从轨迹数据集中准确识别活动热点的问题,提出了基于轨迹结构的热点区域发现框架(TS_HS)。TS_HS由候选区域发现(CHSD)算法和热点区域过滤(HSF)算法组成。首先,使用基于网格相对密度的CHSD识别空间上的轨迹密集区域作为候选热点区域;然后,利用HSF根据候选区域中轨迹的活动特征和时间变化特征,筛选出移动对象活动频繁的热点区域。在Geolife数据集上进行的实验表明,与基于全局密度的热门区域发现算法(GD_HR)以及移动轨迹时空热点区域发现算法(SDHSRD)相比,TS_HS能更有效地解决多密度热点区域的识别问题。实验结果表明,TS_HS能够根据轨迹的活动特征准确发现移动对象的活动热点区域。

关键词: 移动对象, 轨迹结构, 热点区域, 轨迹数据, 数据挖掘

CLC Number: