基于人工免疫分类器的高速公路事件检测

Freeway incident detection based on artificial immune classifier

采用一种有限资源人工免疫分类器研究高速公路事件检测问题。阐述了人工免疫识别系统(AIRS)的算法,然后分析了高速公路事件对交通流的影响,并选取多个时刻的上游流量、上游占有率和下游流量、下游占有率作为AIRS的输入量,最后用高速公路管理部门提供的样本数据进行了仿真实验。实验结果表明,人工免疫分类器具有很快的学习速度和较高的分类精度,它为高速公路事件检测提供了一种切实可行的新途径。

A resource limited artificial immune classifier is used to study the problem of freeway incident detection. The algorithm of AIRS （artificial immune recognition system） is formulated, firstly. The influence of freeway incident on the traffic flow is analyzed. The upstream flow, upstream occupancy, downstream flow and downstream occupancy in different periods are selected as the input varia- bles of AIRS. Finally, simulation experiment is carried out with the sample data provided by the freeway administration office. Simulation results show that the artificial immune classifier has fast learning speed and good classification ability. AIRS is found to be a novel and practical way to realize freeway incident detection.