交通运输系统工程与信息

交通运输系统工程与信息 ›› 2002, Vol. 2 ›› Issue (4): 54-58 .

• 系统工程理论与方法 • 上一篇    下一篇

基于改进OLS算法的RBF神经网络
高速公路事件探测

杨耀华 ， 李昕，江芳泽   

  1. 上海大学机电工程与自动化学院，上海 200072
  • 收稿日期:2002-08-22 修回日期:1900-01-01 出版日期:2002-11-01 发布日期:2002-11-01

Freeway Incident Detection Using Improved
OLS Algorithm and RBF Neural Networks

YANG Yao-hua , LI Xin, JIANG Fang-ze   

  1. School of Electromechanical Engineering and Automation, Shanghai University. Shanghai 200072, China
  • Received:2002-08-22 Revised:1900-01-01 Online:2002-11-01 Published:2002-11-01

PDF

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Oils(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.

关键词: 高速公路事件探测, 模糊聚类, RBF神经网络, 正交最小二乘算法

Abstract: This paper presents a new hybrid intelligence algorithm for automatically detecting ft-way 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.

Key words: Freeway incidents detection, fuzzy clustering, RBF neural networks, OLS