Page 87 - 《软件学报》2020年第12期

软件学报 ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscas.ac.cn
Journal of Software,2020,31(12):3753−3771 [doi: 10.13328/j.cnki.jos.005875] http://www.jos.org.cn
©中国科学院软件研究所版权所有. Tel: +86-10-62562563

∗
行程时间预测方法研究

1
1
2
柏梦婷 , 林杨欣 , 马 萌 , 王 平 1,2,3
1
(北京大学 软件与微电子学院,北京 102600)
2 (软件工程国家工程研究中心(北京大学),北京 100871)
3 (高可信软件技术教育部重点实验室(北京大学),北京 100871)
通讯作者: 马萌, E-mail: mameng@pku.edu.cn; 王平, E-mail: pwang@pku.edu.cn

摘 要: 行程时间预测,有助于实施高级旅行者信息系统.自 20 世纪 90 年代起,已经有多种行程时间预测方法被研
发出来.将行程时间预测方法分为模型驱动方法和数据驱动方法两大类.介绍了两种常见的模型驱动方法,即排队论
模型和细胞传输模型.数据驱动方法被分类为参数方法和非参数方法:参数方法包括线性回归、自回归集成移动平
均和卡尔曼滤波,非参数方法包括神经网络、支持向量回归、最近邻和集成学习方法.对现有行程时间预测方法从
源数据、预测范围、准确率、优缺点和适用范围等方面进行了分析总结.针对现有方法的一些缺点,提出了可能的
解决方案.给出了一种新颖的数据预处理框架和一个行程时间预测模型,最后指出了未来的研究方向.
关键词: 行程时间预测;模型驱动;数据驱动;参数方法;非参数方法
中图法分类号: TP391

中文引用格式: 柏梦婷,林杨欣,马萌,王平.行程时间预测方法研究.软件学报,2020,31(12):3753−3771. http://www.jos.org.cn/
1000-9825/5875.htm
英文引用格式: Bai MT, Lin YX, Ma M, Wang P. Survey of traffic travel-time prediction methods. Ruan Jian Xue Bao/Journal of
Software, 2020,31(12):3753−3771 (in Chinese). http://www.jos.org.cn/1000-9825/5875.htm

Survey of Traffic Travel-time Prediction Methods
1
2
1
BAI Meng-Ting , LIN Yang-Xin , MA Meng , WANG Ping 1,2,3
1 (School of Software and Microelectronics, Peking University, Beijing 102600, China)
2 (National Engineering Research Center for Software Engineering (Peking University), Beijing 100871, China)
3 (Key Laboratory of High Confidence Software Technologies of Ministry of Education (Peking University), Beijing 100871, China)
Abstract: Travel-time prediction can help implement advanced traveler information systems. In recent years, a variety of travel-time
prediction methods have been developed. In this study, travel-time prediction methods are classified into two categories: model-driven and
data-driven methods. Two common model-driven approaches are elaborated, namely queuing theory and cell transmission model. The
data-driven methods are classified into parametric and non-parametric methods. Parametric methods include linear regression,
autoregressive integrated moving average, and Kalman filtering. Non-parametric methods contain neural networks, support vector
regression, nearest neighbors, and ensemble learning methods. Existing travel-time prediction methods are analyzed and concluded from
source data, prediction range, accuracy, advantages, disadvantages, and application scenarios. Several solutions are proposed for some
shortcomings of existing methods. A novel data preprocessing framework and a travel-time prediction model are presented, and future
research challenges are highlighted.
Key words: travel-time prediction; model-driven; data-driven; parametric methods; non-parametric methods

∗ 基金项目: 国家重点研发计划(2017YFB1200700); 国家自然科学基金(61701007)
Foundation item: National Key Research and Development Program of China (2017YFB1200700); National Natural Science
Foundation of China (61701007)
收稿时间: 2018-11-03; 修改时间: 2019-05-08; 采用时间: 2019-07-10