[1]陈永恒,陶楚青,白乔文,等.基于SVM的快速路合流区车辆间隙选择模型[J].东南大学学报(自然科学版),2018,48(4):752-758.[doi:10.3969/j.issn.1001-0505.2018.04.023]
　Chen Yongheng,Tao Chuqing,Bai Qiaowen,et al.Gap choice model at urban expressway merging sections based on SVM[J].Journal of Southeast University (Natural Science Edition),2018,48(4):752-758.[doi:10.3969/j.issn.1001-0505.2018.04.023]
点击复制

基于SVM的快速路合流区车辆间隙选择模型()
分享到：

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
48
期数:
2018年第4期
页码:
752-758
栏目:
交通运输工程
出版日期:
2018-07-20

文章信息/Info

Title:
Gap choice model at urban expressway merging sections based on SVM
作者:
陈永恒; 陶楚青; 白乔文; 熊帅; 刘芳宏; 奇兴族
吉林大学交通学院, 长春 130022
Author(s):
Chen Yongheng;  Tao Chuqing;  Bai Qiaowen;  Xiong Shuai;  Liu Fanghong;  Qi Xingzu
College of Transportation, Jilin University, Changchun 130022, China
关键词:
交通运输系统工程;  快速路合流区;  间隙选择;  机器学习;  支持向量机
Keywords:
communications and transportation system engineering;  expressway merging sections;  gap choice;  machine learning;  support vector machine(SVM)
分类号:
U491
DOI:
10.3969/j.issn.1001-0505.2018.04.023
摘要:
通过2种典型快速路合流区车辆行为观测,发现匝道车辆在选择间隙时存在多次超车行为,表明其汇入过程是一个多次决策的动态过程.根据合流过程中车辆速度的变化特性,判定车辆在选择间隙时的决策点并采集决策点处的微观交通流参数.在此基础上比较了2种不同渠化设计下入口匝道车辆汇入行为的差异.考虑到合流车辆不同行为判别所需的关键参数不同,使用2个支持向量机模型(SVM)进行分类,建立了合流区车辆多次决策的间隙选择模型.通过对采集的交通流参数进行训练,SVM模型的预测精度能够达到91%以上,实现预测车辆间隙选择的目的.最后与Logistic回归模型进行比较,结果证明所提出的模型能够获得较高精度.
Abstract:
Through the observation of the vehicle behaviors at the merging sections of two typical expressways, multiple overtaking behaviors are found to exist when the vehicle chooses the gap. It shows that the merging process is a dynamic process of multiple decisions. According to the variation of vehicle speed during the merging process, the decision point of the vehicle is determined. Then the video processing software is used to collect the microscopic traffic flow parameters at the decision point. Then a comparison analysis is conducted to discuss merging behaviors on different channelized on-ramps based on the survey data. Considering different key parameters required for different behaviors of merging vehicles, two support vector machine(SVM)models are used for behavior classification. Finally, a gap choice model for vehicle multiple decision-making in a merging section is established. The model can predict gap choice maneuver through the traffic parameters for training and the accuracy of the SVM model is over 91%. The proposed model is proved to obtain higher accuracy compared with the logistic regression model.

参考文献/References:

[1] Huang S Y. Modeling of the gap acceptance behavior at a merging section of urban freeway [J]. Proceedings of the Eastern Asia Society for Transportation Studies, 2005, 5: 1641-1656.
[2] 谭云龙.快速路合流区微观交通仿真车道变换模型研究[D]. 长春:吉林大学交通学院, 2014.
[3] Chu T D, Nakamura H, Asano M. Modeling gap choice behavior at urban expressway merging sections[J]. Journal of Japan Society of Civil Engineers, Ser. D3(Infrastructure Planning and Management), 2013, 69(5):I_881-I_891. DOI:10.2208/jscejipm.69.i_881.[4] Wang E G, Sun J, Jiang S, et al. Modeling the various merging behaviors at expressway on-ramp bottlenecks using support vector machine models [J]. Transportation Research Procedia, 2017, 25: 1327-1341. DOI:10.1016/j.trpro.2017.05.157.
[5] Chu T D, Miwa T, Morikawa T. An analysis of merging maneuvers at urban expressway merging sections[J]. Procedia—Social and Behavioral Sciences, 2014, 138: 105-115. DOI:10.1016/j.sbspro.2014.07.186.
[6] Chu T D, Miwa T, Morikawa T. Discrete choice models for gap acceptance at urban expressway merge sections considering safety, road geometry, and traffic conditions[J]. Journal of Transportation Engineering, Part A: Systems, 2017, 143(7): 04017025. DOI:10.1061/jtepbs.0000053.
[7] Wan X, Jin P J, Gu H Y, et al. Modeling freeway merging in a weaving section as a sequential decision-making process[J]. Journal of Transportation Engineering, Part A: Systems, 2017, 143(5): 05017002. DOI:10.1061/jtepbs.0000048.
[8] Liu M M, Lu G Q, Wang Y P, et al. Preempt or yield? An analysis of driver’s dynamic decision making at unsignalized intersections by classification tree[J]. Safety Science, 2014, 65: 36-44. DOI:10.1016/j.ssci.2013.12.009.
[9] Yang X B, Zhang N. An improved method of determining car-following state[J]. Journal of Transportation Systems Engineering & Information Technology, 2006, 6(2):14-17.
[10] Suzuki K, Imada K, Matsumura Y. A study of collision risk estimation and users evaluation at merging section of urban expressway in Japan[J]. Transportation Research Procedia, 2016, 15: 783-793. DOI:10.1016/j.trpro.2016.06.065.
[11] Harrington P. Machine learning in action[M]. Connecticut,USA:Manning Publications Co., 2012:83-127.

相似文献/References:

[1]李婷婷,宋瑞.国家层面综合客运枢纽分层布局鲁棒优化模型[J].东南大学学报(自然科学版),2015,45(1):189.[doi:10.3969/j.issn.1001-0505.2015.01.033]
　Li Tingting,Song Rui.Hierarchical layout robust optimization model for integrated passenger hub at national level[J].Journal of Southeast University (Natural Science Edition),2015,45(4):189.[doi:10.3969/j.issn.1001-0505.2015.01.033]
[2]李林超,张健,杨帆,等.基于核函数切换和支持向量回归的交通量短时预测模型[J].东南大学学报(自然科学版),2017,47(5):1032.[doi:10.3969/j.issn.1001-0505.2017.05.030]
　Li Linchao,Zhang Jian,Yang Fan,et al.Traffic volume prediction based on support vector regression with switch kernel functions[J].Journal of Southeast University (Natural Science Edition),2017,47(4):1032.[doi:10.3969/j.issn.1001-0505.2017.05.030]

备注/Memo

备注/Memo:
收稿日期: 2018-01-10.
作者简介: 陈永恒(1978—),男,博士,副教授,cyh@jlu.edu.cn.
基金项目: 国家自然科学基金资助项目(51278220)、吉林省自然科学基金资助项目(20180101063JC).
引用本文: 陈永恒,陶楚青,白乔文,等.基于SVM的快速路合流区车辆间隙选择模型[J].东南大学学报(自然科学版),2018,48(4):752-758. DOI:10.3969/j.issn.1001-0505.2018.04.023.
更新日期/Last Update: 2018-07-20