论文部分内容阅读
智能检测系统已为高速公路交通事件检测提供了有效的途径.为了更加细致地了解高速公路交通运行状态,为突发事件的应急处理提供更加高效、可靠的决策支持,将支持向量机两分类问题延伸到多分类上来.根据交通事件的发生过程,将其分为自由流状态,交通拥堵加剧状态,交通拥堵消散状态.采集VISSIM对交通事件各阶段进行仿真的原始数据集,运用主成分分析方法对交通输入特性进行降维处理,构建支持向量机多分类事件检测模型,最后用遗传算法选择支持向量机模型参数,获得了满意的检测效果.
Intelligent detection system has provided an effective way for highway traffic incident detection.In order to understand traffic state of expressway more carefully and provide more efficient and reliable decision support for emergency handling of emergencies, Extend to multi-classification.According to the occurrence process of traffic accidents, it is divided into free flow state, traffic congestion aggravate state and traffic congestion dissipated state.VISSIM is used to simulate the original data set of each phase of traffic accident, and the principal component analysis The input characteristics of traffic are reduced dimensioned to construct the multi-class event detection model of support vector machine. Finally, genetic algorithm is used to select the support vector machine model parameters, and the satisfactory detection result is obtained.