基于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 Particle Swarm Optimization

作　　者：于万霞[1] 杜太行[1] 郑宏兴[2] 于越[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：《微计算机信息》2008年第4期232-233,157,共3页Control & Automation

基　　金：国家自然科学基金项目(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,本文建立了模糊神经网络模型预测短时交通流量,并采用全局优化的粒子群算法优化模糊神经网络的参数。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 traffic control. According to the characteristics of short-time traffic flow, a fuzzy neural network model is proposed to solve short-time traffic flow prediction. A fast global optimization algorithm, particle swarm optimization (PSO) algorithm is applied to training the fuzzy neural network. The simulation results demonstrate the proposed model can improve prediction accuracy, compared with BP based tr...

关 键 词：短时交通流 预测模型 模糊神经网络 粒子群算法 

分 类 号：U491.14[交通运输工程—交通运输规划与管理]