首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于改进SWF神经网络多因素行程时间预测模型与算法
引用本文:马洪伟,周溪召.基于改进SWF神经网络多因素行程时间预测模型与算法[J].交通与计算机,2012(4):24-27.
作者姓名:马洪伟  周溪召
作者单位:[1]上海海事大学交通运输学院,上海200135 [2]上海电机学院商学院,上海201306
基金项目:上海市教委科研创新基金项目(批准号:11YS272); 上海海事大学科研基金项目(批准编号:20110021); 上海高校青年教师培养资助计划项目(批准号:sdju009); 上海海事大学研究生创新能力培养专项基金资助项目(批准号:yc2011046); 上海电机学院重点学科建设项目(批准号:10XKJ01)资助
摘    要:行程时间预测一直是交通领域研究的重点问题之一,道路系统的复杂性使预测工作变得困难。将影响路段行程时间的多种因素和改进后的样条权函数神经网络结合起来,根据机动车运行特点,建立行程时间预测模型,可以刻划道路运行的多种状态,能较准确的估计出路段的行程时间,也继承了样条权函数神经网络算法的各种优点。

关 键 词:交通量  样条权函数  神经网络  行程时间  信号周期

A Multi-factor Travel Time Prediction Model and Algorithm Based on Improved SWF Neural Network
MA Hongwei,ZHOU Xizhao.A Multi-factor Travel Time Prediction Model and Algorithm Based on Improved SWF Neural Network[J].Computer and Communications,2012(4):24-27.
Authors:MA Hongwei  ZHOU Xizhao
Institution:1.College of Transport and Communications,Shanghai Maritime University,Shanghai 200135,China; 2.Business School,Shanghai Dianji University,Shanghai 201306,China)
Abstract:The prediction of travel time is one of the most important research topics in transportation field.The complexity of the road system makes the forecasting difficult.According to the operating characteristics of automobile vehicles,this paper establishes a travel time prediction model by considering a variety of factors affecting the travel time within an improved spline weight functions(SWF) neural networks.It is found out that the model proposed can describe a variety of traffic flow states and accurately estimate the travel time of road segments.At the same time,the model also inherits many merits of the SWF neural network algorithm.
Keywords:traffic volume  spline weight function  neural network  travel time  signal period
本文献已被 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号