基于集成算法的路段短时行驶时间预测

doi:10.3976/j.issn.1002-4026.2018.04.018

山东科学 ›› 2018, Vol. 31 ›› Issue (4): 118-125.doi: 10.3976/j.issn.1002-4026.2018.04.018

基于集成算法的路段短时行驶时间预测

蒋怡玥¹，董蜀黔²，周淑敏¹

1. 北京交通大学交通运输学院，北京 100044；2. 北京邮电大学信息与通信工程学院，北京 100876

收稿日期:2017-11-10 出版日期:2018-08-20 发布日期:2018-08-20
作者简介:蒋怡玥（1994—），女，硕士研究生，研究方向为交通运输规划与管理。E-mail: 16120822@bjtu.edu.cn
基金资助:
创新研究群体项目(71621001)

Short term prediction of road travel time based on an ensemble algorithm

JIANG Yi-yue¹, DONG Shu-qian², ZHOU Shu-min¹

1.School of Traffic and Transportation,Beijing Jiaotong University,Beijing 100044, China; 2. School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2017-11-10 Online:2018-08-20 Published:2018-08-20

摘要/Abstract

摘要：

为了更好地解决路段行驶时间的短时预测问题，提出并改善了一种基于树的集成算法。针对小时间尺度下交通时变性强这一特性，构建更加鲁棒的梯度提升树（GBDT）以减少突变点的干扰。为了克服偏差方差窘境，将随机树（RF）与GBDT进行融合，提出RF-GBDT的集成算法，并考虑各种历史旅行时间数据的相关变量以提高模型的可解释性。预测结果表明，与单独的RF或GBDT相比，RF-GBDT具有更好的预测准确度与算法稳定性。

关键词: 短时预测, 集成, 随机森林, 行驶时间, 梯度提升树

Abstract:

In order to better solve the short term prediction problem of travel time on links, a tree based ensemble method was proposed and improved. First, a more robust GBDT was established to reduce the disturbance caused by bursts aiming at the strong upheavals of traffic in a small time scale. Then, the RF and GBDT were fused and a new method for RF-GBDT was proposed to overcome the problem of bias-variance dilemma. In addition, various relevant variables derived from historical travel time data were considered to improve the interpretability of the model. The results of predictions show that compared with the single RF or GBDT, the RF-GBDT method is preferable in the accuracy and the stability of algorithms.

Key words: short term prediction, gradient boosting decision tree(GBDT), random forest (RF), ensemble, travel time

中图分类号:

U213.2

蒋怡玥，董蜀黔，周淑敏. 基于集成算法的路段短时行驶时间预测[J]. 山东科学, 2018, 31(4): 118-125.

JIANG Yi-yue, DONG Shu-qian, ZHOU Shu-min. Short term prediction of road travel time based on an ensemble algorithm[J]. SHANDONG SCIENCE, 2018, 31(4): 118-125.

参考文献

［1］江周,张存保,许志达,等. 基于实时数据的城市道路行程时间预测方法和模型[EB/OL].[20170712]. http://www.wanfangdata.com.cn/details/detail.do?_type=conference&id=8056593.
［2］ZHANG X Y, RICE J A. Shortterm travel time prediction[J]. Transportation Research Part C Emerging Technologies, 2003, 11 (3/4): 187210.
［3］DION F, RAKHA H. Estimating dynamic roadway travel times using automatic vehicle identification data for low sampling rates[J]. Transportation Research Part B：Methodological, 2006, 40 (9): 745766.
［4］XIA J X, CHEN M, HUANG W. A multistep corridor traveltime prediction method using presencetype vehicle detector data[J]. Journal of Intelligent Transportation Systems, 2011, 15 (2): 104113.
［5］CHEN H B, GRANTMULLER S. Use of sequential learning for shortterm traffic flow forecasting[J]. Transportation Research Part C: Emerging Technologies, 2001, 9(5): 319336.
［6］MESSAI N, THOMAS P, LEFEBVRE D,et al. A neural network approach for freeway traffic flow prediction [M]// Proceedings of the International Conference on Control Applications.Glasgow.UK:IEEE, 2002.
［7］ZHOU Z H. Ensemble Methods: Foundations and Algorithms[M].Boca Raton,FL.:CRC Press， 2012.
［8］HAMNER B. Predicting travel times with contextdependent random forests by modeling local and aggregate traffic flow[M]// Proceedings of the 2010 IEEE International Conference on Data Mining Workshops.Sydney,Nsw,Australia:IEEE,2010: 13571359.
［9］ZHANG Y R, HAGHANI A. A gradient boosting method to improve travel time prediction[J].Transportation Research Part C Emerging Technologies. 2015, 58: 308324.
［10］丁闪闪. 基于路段的高速公路路径行程时间预测方法研究[D]. 南京：东南大学. 2013.
［11］BREIMAN L. Random forests[J]. Machine Learning. 2001, 45(1): 532.
［12］SCHAPIRE R E. The boosting approach to machine learning: An overview[EB/OL].[20170712]. http://www.yisongyue.com/courses/cs155/2015_winter/lectures/msri.pdf.
［13］FRIEDMAN J H. Greedy function approximation: a gradient boosting machine[J]. The Annals of Statistics. 2001, 29(5): 11891232.

[1]	杨安安, 韩星玉, 田旷, 刘泽远, 明玮. 基于Stacking集成学习的机场线短时客流预测研究[J]. 山东科学, 2024, 37(4): 112-120.
[2]	高梦琦, 昌锡铭, 王欢. 基于小波分解和长短时记忆网络的地铁进站量短时预测[J]. 山东科学, 2019, 32(4): 56-63.
[3]	刘野，丁圆强，赵环宇，柴辉，赵强，徐宇柘，姜峰. 大型海洋资料浮标波浪能供电装置数值模拟研究[J]. 山东科学, 2017, 30(6): 6-14.
[4]	马倩, 曹宝香, 马兆丰, 芦效峰. 基于构件的多源异构数据集成技术研究[J]. J4, 2011, 24(5): 63-66.

基于集成算法的路段短时行驶时间预测

Short term prediction of road travel time based on an ensemble algorithm

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

Metrics

本文评价

推荐阅读 0