基于改进FCM聚类算法的高速公路交通状态识别

Identification on Traffic State of Expressway Based on Improved FCM Clustering Algorithm

为有效识别高速公路交通状态,提高路网服务水平,基于改进的模糊C均值(Fuzzy CMeans,FCM)聚类算法对高速公路交通数据进行分析。首先,采用熵权法确定交通流量、空间占有率、平均速度和路网充裕度4个交通状态分类指标的权重,并对每个样本赋予不同的加权系数。然后,将样本权重计算纳入算法迭代过程,进而实现高速公路交通状态识别。最后,比较改进FCM算法与传统FCM算法的目标函数值、迭代次数及运行时间,结果表明:与传统FCM算法相比,改进FCM算法的目标函数值较小,迭代次数较少,运行时间较短,在数据中表现出更好的适应性;由改进FCM算法得到的聚类结果能准确、全面地反映交通数据的变化情况,实现道路交通状态的有效识别。

In order to identify the expressway traffic state effectively and improve the service level of the road network,the traffic data of expressway was analyzed based on the improved FCM(Fuzzy CMeans)clustering algorithm.Firstly,entropy weight method was used to determine the weights of four traffic state classification indexes,including traffic flow,space occupancy,average speed and road network ample degree,meanwhile different weighting coefficient was assigned to each sample.Secondly,the calculation of sample weights was incorporated into the iterative process to identify the expressway traffic state.Finally,the objective function value,iteration times and running time of the improved FCM algorithm and the traditional FCM algorithm were compared.The results show that compared with the traditional FCM algorithm,the improved FCM algorithm has smaller objective function value,fewer iterations,shorter running time and better adaptability in data;the clustering results obtained by the improved FCM algorithm can reflect the changes of traffic data accurately and comprehensively,and can identify road traffic states effectively.