«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

25

期数:

2015年02期

页码:

103-017

栏目:

智能、算法、系统工程

出版日期:

2015-02-10

文章信息/Info

Title:

 Research on an Improved Prediction Algorithm for Short-term Traffic Flow

文章编号:

1673-629X（2015)02-0103-05

作者:

 郭新

 广东交通职业技术学院 交通信息学院

Author(s):

 GUO Xin

关键词:

 ; 智能交通系统; 交通流; 在线学习; 支持向量回归模型

Keywords:

 ; intelligent transportation systems; traffic flow; online learning; support-vector regression model

分类号:

TP391

文献标志码:

A

摘要:

 短期交通流量预测已经成为智能交通系统的重要研究领域。为了进行流量动态分配，积极有效地运行交通管理系统，必须要准确估计交通流量。在预测短期流量时，近期流量信息显然对将来短期流量预测具有重要的预示作用，即应该考虑取决于交通流量数据时差的相对重要性。文中提出一种新的短期流量预测模型：基于在线学习的加权支持向量回归模型( OLWSVR)。 OLWSVR模型与多种知名预测模型(包括人工神经网络模型、局部加权回归模型、传统的支持向量回归模型，及在线学习支持向量模型)进行比较。结果表明，文中模型的性能优于其他当前模型的性能。

Abstract:

 Prediction of short-term traffic flow has become one of the major research fields in intelligent transportation systems. Accurate-ly estimating traffic flow are important for operating effectively and proactively traffic management systems in the context of dynamic traf-fic assignment. For predicting short-term traffic flows,recent traffic information is clearly a more significant indicator of the near-future traffic flow. In other words,the relative significance depending on the time difference between traffic flow data should be considered. It presents a novel prediction model for short-term traffic flow in this paper,called Online Learning Weighted Support-Vector Regression ( OLWSVR) . The OLWSVR model is compared with several well-known prediction models,including artificial neural network models, locally weighted regression,conventional support-vector regression,and online learning support-vector regression. The results show that the performance of the proposed model is superior to that of existing models.

常用功能

更新日期/Last Update: 2015-04-28