加权马尔可夫模型在道路交通受伤人数预测中的应用  

Model for Predicting the Traffic Accident Injured Toll With the Weighted Markov Chain and its Application

作　　者：赵玲[1,2] 许宏科[1] 

机构地区：[1]长安大学电子与控制工程学院,陕西西安710064 [2]西安邮电大学通信与信息工程学院,陕西西安710121

出　　处：《数学的实践与认识》2012年第18期183-189,共7页Mathematics in Practice and Theory

基　　金：国家自然科学基金(60804049);陕西省教育厅自然科学基金(11JK0897)

摘　　要：为提高交通事故预测的可靠性,首先应用有序聚类的方法建立交通受伤人数的分级标准;然后针对事故受伤人数为相依随机变量的特点,采取以规范化的各阶自相关系数为权重,用加权的马尔可夫链模型来预测未来交通事故受伤人数的升降变化状况;最后以北京市1970-2010年共41年的事故受伤人数为例对该方法进行了具体应用,取得了较为满意的结果,为交通事故受伤人数的预测分析提供了新的途径.In order to improve the reliability of traffic accident prediction, this paper firstly applied sequential cluster method to set up the classification standard of traffic accident injured toll; then this paper presented a method which is called Markov chain with weights to predict the future death toll state by regarding the standardized self-coefficients as weights based on the special characteristics of injured toll being a dependent stochastic variable; and applied this method to a real situation： year＇s death tolls of Beijing road traffic through the year 1970 upto 2010 altogether 41 years at last. This method provided a new way to predict traffic injured toll, and the ideal result was obtained.

关 键 词：交通安全 交通事故预测 加权马尔可夫链 有序聚类 受伤人数 

分 类 号：O211.62[理学—概率论与数理统计] U491.3[理学—数学]