基于S型函数预处理的RBF神经网络交通流量预测  

RBF Neural Network Traffic Flow Forecast Based on S-function Pre-processing

作　　者：温惠英[1] 周玮明[1] 

机构地区：[1]华南理工大学土木与交通学院,广州510640

出　　处：《交通信息与安全》2009年第4期22-25,共4页Journal of Transport Information and Safety

摘　　要：根据交通流复杂性的特点,提出了一种基于S型函数标准化数据预处理的交通流量RBF网络预测方法,缩短了RBF网络训练时间;同时采用OLS算法有效降低RBF网络训练的随机性。实验仿真结果表明,该算法可用于实时交通流量及参数预测,并具有可靠的精度和较好的收敛速度。A new RBF network traffic flow forecast method based on S-function by standardized data pre-processing was put forward according to the characteristics of the complexity of the traffic flow. As a result, the network training time was reduced. Meanwhile, an OLS algorithm was used to reduce the randomness of the RBF network training. The experimental results show that the method can be used for real-time traffic flow and parameters forecast with reliable accuracy and good convergence rate.

关 键 词：RBF神经网络 交通流量预测 S型函数 OLS算法 非线性问题 

分 类 号：U491[交通运输工程—交通运输规划与管理] TP391[交通运输工程—道路与铁道工程]