基于蚁群粒子群的模糊神经网络交通流量预测  

Fuzzy neural network model for forecasting short-time traffic flow based on ant algorithm and Particle Swarm Optimization

作　　者：于万霞[1] 杜太行[1] 郑宏兴[2] 

机构地区：[1]河北工业大学,天津300130 [2]天津工程师范学院电子工程系,天津300222

出　　处：《计算机工程与应用》2007年第25期197-199,共3页Computer Engineering and Applications

基　　金：国家自然科学基金(the National Natural Science Foundation of China under Grant No.60671009) 。

摘　　要：实时准确的交通流量预测是智能交通诱导和交通控制实现的前提和关键。针对城市交通流的特点,建立了模糊神经网络预测模型,并将全局优化的蚁群算法和粒子群算法组成递阶结构优化模糊神经网络的参数。算法中,主级为蚁群算法,进行全局搜索;从级为粒子群算法,进行局部搜索。仿真结果表明该模型能够取得比梯度下降法更高的预测精度。Real-time and accurate traffic flow prediction is very important to the intelligent traffic guidance and control.According to the characteristics of short-time traffic flow,a fuzzy neural network model has been proposed to solve short-time traffic flow prediction.The paper combines Particle Swarm Optimization（PSO） algorithm with ant algorithm for training the fuzzy neural network. The algorithm is formulated in a form of hierarchical structure.The master level is ant algorithm and slave level is PSO.The global search is performed at the master level,while the local search is carried out at the slave level.The simulation results demonstrate the proposed model can improve prediction accuracy,compared with BP based training techniques.

关 键 词：短时交通流 预测模型 模糊神经网络 粒子群算法 蚁群算法 

分 类 号：U491[交通运输工程—交通运输规划与管理]