论文部分内容阅读
为弥补基于传统交通信息采集技术的高速公路交通事件检测算法仅能判断交通事件发生与否而无法判断车辆个体是否受到交通事件影响的不足,作者提出了一种基于RFID和FOA-GRNN的高速公路交通事件对车辆影响的判断模型。该模型使用RFID获取关键交通信息,利用广义回归神经网络对交通信息进行归类,应用果蝇优化算法获取广义回归神经网络的最佳平滑参数值。用VISSIM进行了仿真,对模型进行了验证,结果表明该判断模型具有检测率高、误警率低的特点,能迅速判断出受到交通事件影响的车辆,为交通疏导工作提供支持。
In order to make up for the shortage of traffic incident detection algorithm based on traditional traffic information acquisition technology, which can only judge whether a traffic incident happens or not and can not judge whether a vehicle is affected by a traffic accident, the author proposes a freeway based on RFID and FOA-GRNN Judgment Model of Traffic Impact on Vehicles. The model uses RFID to obtain the key traffic information, classifies the traffic information by using generalized regression neural network, and obtains the best smoothing parameter value of generalized regression neural network by using Drosophila optimization algorithm. VISSIM was used to simulate the model. The results show that this model has the characteristics of high detection rate and low false alarm rate, which can quickly determine the vehicles affected by traffic accidents and provide support for traffic diversion.