作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (10): 164-167. doi: 10.3969/j.issn.1000-3428.2012.10.050

• 人工智能及识别技术 • 上一篇    下一篇

基于影响模型的短时交通流预测方法

丁 栋 1,2,朱云龙 1,库 涛 1,王 亮 1,2   

  1. (1. 中国科学院沈阳自动化研究所工业信息学实验室,沈阳 110016;2. 中国科学院研究生院,北京 100049)
  • 收稿日期:2011-09-28 出版日期:2012-05-20 发布日期:2012-05-20
  • 作者简介:丁 栋(1985-),男,硕士研究生,主研方向:时空数据挖掘,智能交通;朱云龙,研究员、博士生导师;库 涛,副研究员;王 亮,博士研究生
  • 基金资助:
    国家自然科学基金资助项目“面向感应网络的移动数据挖掘及复杂行为模式分析研究”(61003208);国家自然科学基金资助项目“基于细菌行为模式的复杂系统建模与优化方法研究”(6117 4164);国家自然科学基金资助项目“基于生物行为的RFID系统优化模型与算法研究”(61105067)

Short-term Traffic Flow Forecasting Method Based on Influence Model

DING Dong 1,2, ZHU Yun-long 1, KU Tao 1, WANG Liang 1,2   

  1. (1. Laboratory of Industrial Informatics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China; 2. Graduate University of Chinese Academy of Sciences, Beijing 100049, China)
  • Received:2011-09-28 Online:2012-05-20 Published:2012-05-20

摘要: 根据复杂交通网络中多个节点之间交通流相互影响的特性,提出一种基于影响模型的短时交通流预测方法。分析交通网络中交通流预测的难点,引入随机过程中影响模型的理论对其进行建模。将每个节点的交通流处理为一个隐马尔科夫过程,整个网络由多个相互交互的隐马尔科夫过程组成,采用EM算法对模型参数进行训练。实验结果表明,该方法具有较高的预测精度,可较好地显示交通网络中多个节点之间交通流的交互规律以及动态演化规律。

关键词: 影响模型, 交通流预测, 隐马尔科夫过程, 神经网络, 智能交通, 交通网络

Abstract: Aiming at the characteristic that traffic flow of different nodes influences each other in complex traffic network, this paper presents a novel short-term traffic flow forecasting method based on influence model. Based on the analysis of the difficulties of the traffic flow forecasting problem, this method introduces the theory of influence model to model. As the traffic flow of each node is considered as a hidden Markov process, the whole traffic network is composed of many interactive hidden Markov processes. This method uses the EM algorithm to learn parameters in the forecasting model. Experimental results show that the method not only has higher prediction accuracy, but also presents the interactive influence and dynamic evolution of the traffic flow of different nodes in traffic network.

Key words: influence model, traffic flow forecasting, hidden Markov process, neural network, intelligent traffic, traffic network

中图分类号: