| 基于S型函数预处理的RBF神经网络交通流量预测 |
| |
| 引用本文： | 温惠英,周玮明.基于S型函数预处理的RBF神经网络交通流量预测[J].交通与计算机,2009,27(4):22-25. |
| |
| 作者姓名： | 温惠英 周玮明 |
| |
| 作者单位： | 华南理工大学土木与交通学院,广州,510640 |
| |
| 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。
|
| 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 |
RBF Neural Network Traffic Flow Forecast Based on S-function Pre-processing |
| |
| WEN Huiying,ZHOU Weiming.RBF Neural Network Traffic Flow Forecast Based on S-function Pre-processing[J].Computer and Communications,2009,27(4):22-25. |
| |
| Authors: | WEN Huiying ZHOU Weiming |
| |
| Institution: | School of Civil Engineering and Transportation;South China University of Technology;Guangzhou 510640;China |
| |
| Abstract: | 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. |
| |
| Keywords: | RBF（radial basic function） neural network traffic flow forecast S function OLS algorithm non-linear problem |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
