城市道路交通事故多发位置鉴别

Black Position Identification of Urban Road Traffic Accident

针对现有相关鉴别法的不足,以核密度估计和计数数据模型为理论基础,GIS为技术基础,建立基于点模式和面模式的空间聚类分析模型,提出了1种基于空间聚类分析技术的城市道路事故多发位置鉴别方法,充分挖掘空间数据,实现分析结果的可视化。研究表明,空间单元标准化Z值>2.58,对应于α=0.01的显著性水平,表明该单元是1个极高值的空间聚类,为1级事故多发点;1.96<Z<2.58对应于α=0.05的显著性水平,表明该单元是1个高值的空间聚类,为2级事故多发点。

This paper proposes a new method of black position identification of urban road traffic accident by using spatial clustering analysis model based on point and plane models .The proposed method is based on the kernel density es-timation ,count data model ,and GIS technology .The proposed method can mine the spatial data and visualize the analysis results .Results from the crash data show that there are two spatial clusters of high values .The first one has the unit standardization Z value above 2 .58 ,which corresponds to the first level of accident black points .The second has the unit standardization Z value between 1 .96 and 2 .58 ,corresponding to the second level of accident black points .