适于营运车辆超速时空特征分析的改进DBSCAN算法  

Improved DBSCAN Algorithm for Spatiotemporal Characteristics Analysis of Commercial Vehicles Speeding Behavior

作　　者：胡继华[1,2] 程智锋[1,2] 詹承志[1,2] 唐巍[1,2] 

机构地区：[1]中山大学工学院智能交通研究中心,广东广州510006 [2]广东省智能交通系统重点实验室,广东广州510275

出　　处：《交通标准化》2012年第12期59-64,共6页Communications Standardization

基　　金：国家自然科学基金项目(40971098)

摘　　要：营运车辆的超速违法行为具有较大的危害性,分析其超速的时间和空间分布规律,对于加强道路运输安全管理具有重要意义。鉴于此,提出一种适于营运车辆超速时空特征分析的改进DBSCAN算法,通过添加时间半径达到对时间维度的支持,对营运车辆超速多发点在时空维度上进行聚类,揭示营运车辆超速违法行为的时空分布特征。然后在广东省重点车辆监控平台上对算法进行验证。实验结果表明,该算法能够快速对超速数据进行时间和空间维度的聚类分析,有效完成超速路段和时段的排查,为查找营运车辆超速常发路段和时段提供了新的分析方法。Analyzing the spatiotemporal distribution of speeding behavior oi commercial vehicles is slgnmcant for the road transport safety management. An improved DBSCAN algorithm is proposed to analyze the spa- tiotemporal characteristics of speeding behavior of commercial vehicles. Time radius is added to support the time dimension. Speeding spots are clustered in the space-time dimension to reveal the spatiotemporal distribution characteristics of commercial vehicles. Then the algorithm is verified on the main vehicle supervision system of Guangdong Province. Experimental results show that the improved DBSCAN algorithm, which provides a new method for searching speeding area and period, can cluster the speeding spots quickly and discover the speeding links and period effectively.

关 键 词：聚类 时空 营运车辆 超速 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]