基于改进OLS算法的RBF神经网络高速公路事件探测  

Freeway Incident Detection Using Improved OLS Algorithm and RBF Neural Networks

作　　者：杨耀华[1] 李昕[1] 江芳泽[1] 

机构地区：[1]上海大学机电工程与自动化学院,上海200072

出　　处：《交通运输系统工程与信息》2002年第4期54-58,共5页Journal of Transportation Systems Engineering and Information Technology

基　　金：上海市科技发展基金(012D14019).

摘　　要：提出了一种基于模糊聚类技术和RBF神经网络的混合智能高速公路事件自动探测算法,同时改进了用于RBF神经网络训练的OLS(正交最小二乘)选择算法.仿真实验证明,改进的OLS选择算法大大提高了RBF神经网络的训练速度,同时具有无须事先确定RBF中心的优点,将之运用于公路事件探测可以获得满意的性能.This paper presents a new hybrid intelligence algorithm for automatically detecting freeway incidents, which employs fuzzy clustering and RBF neural computing technique. An improved OLS (Orthogonal Least Squares ) selection algorithm for training RBF neural networks is also proposed. The simulation results illustrate that the improved OLS selection algorithm accelerates the training of the RBF neural networks substantially and it need not to decide the number of RBF centers in advance. The satisfactory performance can be achieved by using this algorithm in freeway incidents detection.

关 键 词：改进OLS算法 RBF神经网络 高速公路事件探测 模糊聚类 正交最小二乘算法 

分 类 号：U412.366[交通运输工程—道路与铁道工程] TP1[自动化与计算机技术—控制理论与控制工程]