基于支持向量机的高速公路事件检测

Freeway Incident Detection Based on Support Vector Machines

提出用支持向量机分类方法研究高速公路事件检测问题。阐述了支持向量机分类算法,根据交通事件对交通流参数的影响规律选择了支持向量机的输入量,用高速公路管理处提供的样本数据进行了仿真研究。仿真实验表明,支持向量机事件检测算法具有检测准确率高、训练时间短、泛化能力好等优点,它为事件检测提供了一种切实可行的新思路。

Support vector machine（SVM） classification method is proposed to study the problem of freeway incident detection.The algorithm of SVM classification is formulated.The SVM input variables are selected according to the influence of freeway incident on traffic flow parameters.Simulation research is carried out with the sample data provided by the freeway administrative office.Simulation experiments show that SVM incident detection algorithm has such advantages as high detection rate,fast training ability and good generalization.SVM classification method is a novel and practical way to realize freeway incident detection.