系统仿真学报 ›› 2019, Vol. 31 ›› Issue (7): 1429-1438.doi: 10.16182/j.issn1004731x.joss.18-CVR0696

• • 上一篇    下一篇

基于快速密度聚类的载客热点可视化分析方法

黄子赫1, 高尚兵1,*, 潘志庚2, 惠浩1, 廖麒羽1, 赵锋锋1   

  1. 1. 淮阴工学院计算机与软件工程学院,淮安 223001;
    2. 杭州师范大学数字媒体与人机交互研究中心,杭州 311121
  • 收稿日期:2018-06-15 修回日期:2018-10-21 发布日期:2019-12-12
  • 作者简介:黄子赫(1995-),男,江苏宿迁,硕士生,研究方向为数据挖掘、模式识别; 高尚兵(通讯作者1981-),男,江苏淮安,博士,教授,研究方向为图像处理、数据挖掘、模式识别。
  • 基金资助:
    国家重点研发计划(2018YFB1004904), 江苏省六大人才高峰资助项目(XYDXXJS-011), 江苏省333工程资助项目(BRA2016454)

Visualization Analysis Method of Passenger Hotspot Based on Fast Density Clustering

Huang Zihe1, Gao Shangbing1,*, Pan Zhigeng2, Hui Hao1, Liao Qiyu1, Zhao Fengfeng1   

  1. 1. College of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian 223001, China;
    2. Virtual Reality and Human-Computer Interaction Research Center, Hangzhou Normal University, Hangzhou 311121, China
  • Received:2018-06-15 Revised:2018-10-21 Published:2019-12-12

摘要: 随着城市化交通的发展,感知计算在智慧城市起着重要的作用。针对传统密度聚类算法无法适配海量出租车GPS轨迹数据及可视化的问题,提出了BCS-DBSCAN(Big-Data Cluster Center Statistics Density-Based Spatial Clustering of Applications with Noise)聚类算法。该算法可以对轨迹数据切分及并行化聚类且能够提取最大密度簇心,并将结果适配可视化模型。实验结果表明,与其它流行的方法相比,在海量数据下提取城市载客热点区域的聚类速度、精确化及可视化方面具有十分显著的优势,对进一步提升城市规划、提高交通效率提供了重要的决策信息。

关键词: 大数据切分, 簇心提取, 快速聚类, 热点可视化

Abstract: With the development of urbanized transportation, the perceptual computing plays an important role in smart cities. Aiming at the problem that the traditional density clustering algorithm cannot adapt to massive taxi GPS trajectory data and visualization, the BCS-DBSCAN (Big-Data Cluster Center Statistics Density-Based Spatial Clustering of Applications with Noise) clustering algorithm is proposed. The algorithm can segment and parallelize the trajectory data, extract the maximum density cluster, and adapt the result to the visualization model. The experimental results show that compared with other popular methods, this method has significant advantages in extracting clustering speed, accuracy and visualization of urban passenger hotspots from mass data, and provides important decision information for further improving urban planning and traffic efficiency.

Key words: big data segmentation, cluster heart extraction, rapid clustering, hotspot visualization

中图分类号: