基于FCM城市区域道路交通状态时空分层判别方法*

为了解决城市区域路网交通状态的时空分析问题,提出了一种基于模糊C均值聚类(FCM)道路交通状态判别模型及分析方法。通过路网的空间单元交通状态的定量分析和对大量的历史数据进行FCM分析,挖掘出各空间单元的各类交通状态的聚类中心,并将实时采集的交通数据与聚类中心进行匹配,评判其实时交通状态,最后根据空间单元在路网空间分布,获得各状态下点、线、面的空间分层分析结果。实例结果表明,判别方法能准确地实现区域路网的交通状态时空判别,为交通精细化管理提供辅助决策信息。

Spatial and temporal model for urban regional traffic state analysis based on fuzzy C-means clustering

This paper developed a spatial and temporal hierarchical model based on fuzzy C-means clustering for area traffic state analysis to predict area traffic states.Firstly,it quantitatively analyzed the traffic state of the unit of the road network.Then gained the cluster centers of each traffic state for the unit of the road network based on the method of fuzzy C-means clustering.After this,it recognized and classified the real-time traffic state combining its real-time traffic data.According the units’ space distribution in the network,the model presented the different kinds of spatial distribution under different traffic states.The result of example proves that this analytical method obtain the spatial and temporal traffic state accurately.It also supplies the assistant decision-making information for transportation system managers.