交通运输系统工程与信息 ›› 2017, Vol. 17 ›› Issue (1): 60-66.

• 智能交通系统与信息技术 • 上一篇    下一篇

基于GA-LSSVR 模型的路网短时交通流预测研究

陈小波*a,刘祥b,韦中杰b,梁军a,蔡英凤a,陈龙b   

  1. 江苏大学a. 汽车工程研究院; b. 汽车与交通工程学院,江苏镇江212013
  • 收稿日期:2016-06-30 修回日期:2016-08-28 出版日期:2017-02-25 发布日期:2017-02-27
  • 作者简介:陈小波(1982-),男,湖北仙桃人,副教授,博士后.
  • 基金资助:

    国家自然科学基金/ National Natural Science Foundation of China(51108209,61203244,61403172,61573171); 交通运输部信息化项目/Information Project of Ministry of Transport(2013-364-836-900);中国博士后科学基金/ China Postdoctoral Science Foundation(2015T80511,2014M561592);江苏大学高级人才科研启动基金/ Talent Foundation of Jiangsu University(14JDG066);福建省信息处理与智能控制重点实验室(闽江学院)/ Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University)(MJUKF201724).

Short-term Traffic Flow Forecasting of Road Network Based on GA-LSSVR Model

CHEN Xiao-boa, LIU Xiangb, WEI Zhong-jieb, LIANG Juna, CAI Ying-fenga, CHEN Longb   

  1. a. Automobile Engineering Research Institute; b. School of Automobile and Traffic Engineering, Jiangsu University, Zhenjiang 212013, Jiangsu, China
  • Received:2016-06-30 Revised:2016-08-28 Online:2017-02-25 Published:2017-02-27

摘要:

目前,很多短时交通流预测方法仅利用某一路段历史数据的时间相关性或者 道路上下游路段的时空相关性进行交通流预测,未充分考虑路网所有路段之间的时空相 关性.提出了一种基于稀疏混合遗传算法优化的最小二乘支持向量回归(LSSVR)模型,并 应用于路网短时交通流预测.该预测模型不仅可以自动优化LSSVR模型参数,而且可以 从高维路网交通流数据中选择有助于交通流预测的变量子集.实验结果表明,与LSSVR 模型相比,所提方法具有更好的预测能力;而且,少量时空变量被选择出来构建预测模 型,极大减少了信息冗余,改进了模型可解释性.

关键词: 智能交通, 变量选择, 稀疏混合遗传算法, 短时交通流预测, 最小二乘支持向量 回归

Abstract:

Currently, many short- term traffic flow forecasting methods just take into account either temporal correlation of historical data at the target road segment or spatiotemporal correlation between the upstream/downstream segments and the target one, thus ignoring complex spatiotemporal correlation from a more global viewpoint. Aiming at above problem, Least Squares Support Vector Regression (LSSVR) model optimized by a sparse hybrid Genetic Algorithm (GA) is put forward for short term traffic flow forecasting. This model not only automatically optimizes the involved parameters, but also selects from high-dimensional traffic data a subset of spatiotemporal variables contributing to traffic flow forecasting. The experimental results show that in comparison with LSSVR model, the proposed method can improve the performance of traffic flow forecasting. Moreover, only a few of spatiotemporal variables are selected by this method, not only reducing the information redundancy but also enhancing the interpretability of the resulting model.

Key words: intelligent transportation, variable selection, sparse hybrid Genetic Algorithm, short-term traffic flow forecasting, Least Squares Support Vector Regression (LSSVR)

中图分类号: