A Lane Changing Model Based on High Order Conservation Model and Support Vector Machine

doi:10.19596/j.cnki.1001-246x.8339

Abstract

Abstract:

A lane changing model for multi-lane traffic flow is proposed.It makes use of advantages of Support Vector Machine (SVM) in a binary classification problem with multi-dimensional features and combines with Conserved Higher-Order traffic flow model (CHO) in Lagrange coordinates.The original data is generated with a fully discrete car following model and preprocessed by Synthetic Minority Oversampling Technique (SMOTE) algorithm.The SVM is trained with two indexes evaluation.It shows that the lane changing model based on SVM and CHO simulates effectively real multi-lane driving behavior based on current driving environment on expressway.

Key words: SVM model, SMOTE algorithm, feature selection, CHO model, multi-lane traffic flow

Lican ZHANG, Mingmin GUO, Zhiyang LIN, Peng ZHANG, Yali DUAN. A Lane Changing Model Based on High Order Conservation Model and Support Vector Machine[J]. Chinese Journal of Computational Physics, 2022, 39(1): 83-95.

Figures/Tables 16

References 39

1	龙小强, 谭云龙. 微观仿真自主性车道变换模型[J]. 公路交通科技, 2012, 29 (11): 115- 119. DOI
2	刘运通, 石建军, 熊辉. 交通系统仿真技术[M]. 北京: 人民交通出版社, 2002: 6- 7.
3	AHMED K I. Modeling drivers'acceleration and lane changing behavior[D]. Massachusetts Institute of Technology, 1999.
4	ZHANG Y , OWEN L E , CLARK J E . Multiregime approach for microscopic traffic simulation[J]. Transportation Research Record, 1998, 1644 (1): 103- 114. DOI
5	WEI H , LEE J , LI Q . Observation-based lane-vehicle assignment hierarchy: Microscopic simulation on urban street network[J]. Transportation Research Record, 2000, 1710 (1): 96- 103. DOI
6	徐英俊. 城市微观交通仿真车道变换模型研究[D]. 长春: 吉林大学, 2005.
7	YANG Q , KOUTSOPOULOS H N . A microscopic traffic simulator for evaluation of dynamic traffic management systems[J]. Transportation Research Part C: Emerging Technologies, 1996, 4 (3): 113- 129. DOI
8	HIDAS P . Modelling vehicle interactions in microscopic simulation of merging and weaving[J]. Transportation Research Part C: Emerging Technologies, 2005, 13 (1): 37- 62. DOI
9	TOLEDO T , KOUTSOPOULOS H N , BEN-AKIVA M . Integrated driving behavior modeling[J]. Transportation Research Part C: Emerging Technologies, 2007, 15 (2): 96- 112. DOI
10	智永锋, 张骏, 史忠科. 高速公路加速车道长度设计与车辆汇入模型研究[J]. 中国公路学报, 2009, 22 (2): 93- 97. DOI
11	王荣本, 游峰, 崔高健. 车辆安全换道分析[J]. 吉林大学学报(工学版), 2005, 35 (2): 179- 182.
12	KASHANI A A, RAZIAN M R, FATHIAN M. The rise of big data on cloud IoT integration: A case study in Intelligent Transportation System (ITS)[C]. International Conference on New Research Achievements in Electrical and Computer Engineering (ICNRAECE), 2016.
13	苏刚, 王坚, 凌卫青. 基于大数据的智能交通分析系统的设计与实现[J]. 电脑知识与技术, 2015, 36: 44- 46.
14	GOU X Y , GUO L X , ZHANG L B . Support vector machine and neural network in inversion of rough surface parameters[J]. Chinese Journal of Computational Physics, 2014, 31 (1): 75- 84.
15	WANG L X , WANG A Q , HUANG Z X . Parameter inversion of rough surface optimization based on multiple algorithms for SVM[J]. Chinese Journal of Computational Physics, 2019, 36 (5): 577- 585.
16	傅贵, 韩国强, 逯峰. 基于支持向量机回归的短时交通流预测模型[J]. 华南理工大学学报(自然科学版), 2013, 41 (9): 71- 76. DOI
17	胡启洲, 高宁波, 叶茂. 基于支持向量机的道路交通事故数据统计模型研究[J]. 中国安全科学学报, 2013, 23 (6): 39- 44. DOI
18	邱小平, 刘亚龙. 基于支持向量机的车辆跟驰模型[J]. 重庆交通大学学报(自然科学版), 2015, 34 (6): 128- 132.
19	杨殿阁, 何长伟, 李满. 基于支持向量机的汽车转向与换道行为识别[J]. 清华大学学报(自然科学版), 2015, 55 (10): 1093- 1097.
20	吴伟, 沈益峰, 徐建军. 基于实时交通数据的路网展示系统的开发研究[J]. 交通标准化, 2009, (21): 122- 124.
21	谢嘉孟, 彭宏, 周兵. 基于数据挖掘技术的智能交通信息分析与决策研究[J]. 公路, 2004, (4): 154- 158. DOI
22	YAGAR S . Dynamic traffic assignment by individual path minimization and queueing[J]. Transportation Research, 1971, 5 (3): 179- 196. DOI
23	PIPES L A . An operational analysis of traffic dynamics[J]. Journal of Applied Physics, 1953, 24 (3): 274- 281. DOI
24	NAGELK , SCHRECKENBERG M . A cellular automaton model for freeway traffic[J]. Journal de Physique I, 1992, 2 (12): 2221- 2229. DOI
25	PRIGOGINE I , HERMAN R , SCHECHTER R S . Kinetic theory of vehicular traffic[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1972, (2): 295- 295.
26	ZHANG P , WONG S C , DAI S Q . A conserved higher-order anisotropic traffic flow model: Description of equilibrium and non-equilibrium flows[J]. Transportation Research Part B: Methodological, 2009, 43 (5): 562- 574. DOI
27	LIN Z Y, ZHANG P, DONG L Y. Physically bounded solution for a conserved higher-order traffic flow model[M]. Springer, 2015: 463-470.
28	LI H Y , LIN Z Y , ZHANG P , DUAN Y L . Modeling and simulation of dynamic traffic assignment based on conserved higher-order model[J]. Chinese Journal of Computational Physics, 2020, 37 (6): 687- 699.
29	ZHANG P , WU C X , WONG S C . A semi-discrete model and its approach to a solution for a wide moving jam in traffic flow[J]. Physica A: Statistical Mechanics and Its Applications, 2012, 391 (3): 456- 463. DOI
30	GUO M , ZHENG W , ZHU H . Empirical study of lane-changing behavior on three Chinese freeways[J]. PloS one, 2018, 13 (1): e0191466. DOI
31	吴春秀. 基于Lagrange坐标的交通流模型的稳态解与瓶颈效应[D]. 上海: 上海大学, 2012.
32	王永明, 周磊山, 吕永波. 基于元胞自动机交通流模型的车辆换道规则[J]. 中国公路学报, 2008, 21 (1): 89- 93. DOI
33	王江卓, 徐文聪, 李建勋. 基于支持向量机的雷达电子支援措施系统点迹-航迹关联算法[J]. 上海交通大学学报, 2019, 53 (9): 1091- 1099.
34	张莉, 卢星凝, 陆从林. 支持向量机在高考成绩预测分析中的应用[J]. 中国科学技术大学学报, 2017, 47 (1): 1- 9.
35	ZHANG L , ZHOU W , JIAO L . Hidden space support vector machines[J]. IEEE Transactions on Neural Networks, 2004, 15 (6): 1424- 1434. DOI
36	杨思琪. 高速公路交通拥堵状况预测模型的研究与应用[D]. 广州: 华南理工大学, 2017.
37	石京, 柳美玉. 基于驾驶模拟实验的驾驶风格对高速公路换道行为的影响[J]. 东南大学学报: 自然科学版, 2017, (5): 1037- 1041.
38	许伦辉, 倪艳明, 罗强. 基于最小安全距离的车辆换道模型研究[J]. 广西师范大学学报: 自然科学版, 2011, 29 (4): 1- 6.
39	楼晓俊, 孙雨轩, 刘海涛. 聚类边界过采样不平衡数据分类方法[J]. 浙江大学学报(工学版), 2013, (6): 944- 950. DOI

惩罚系数	训练时间/s	分类准确率/%	惩罚系数	训练时间/s	分类准确率/%	惩罚系数	训练时间/s	分类准确率/%
0.05	1 826	87	0.45	1 441	89	0.85	1 650	90
0.1	1 339	88	0.5	1 331	89	0.9	1 744	90
0.15	1 426	88	0.55	1 328	89	0.95	1 819	90
0.2	1 408	89	0.6	1 327	89	1.0	1 845	90
0.25	1 418	89	0.65	1 458	89	1.05	1 913	90
0.3	1 251	89	0.7	1 594	89	1.1	1 522	90
0.35	1 319	89	0.75	1 622	90	1.15	1 416	90
0.4	1 298	89	0.8	1 688	90	1.2	1 372	90

惩罚系数	训练时间/s	分类准确率/%	惩罚系数	训练时间/s	分类准确率/%	惩罚系数	训练时间/s	分类准确率/%
0.05	1 826	87	0.45	1 441	89	0.85	1 650	90
0.1	1 339	88	0.5	1 331	89	0.9	1 744	90
0.15	1 426	88	0.55	1 328	89	0.95	1 819	90
0.2	1 408	89	0.6	1 327	89	1.0	1 845	90
0.25	1 418	89	0.65	1 458	89	1.05	1 913	90
0.3	1 251	89	0.7	1 594	89	1.1	1 522	90
0.35	1 319	89	0.75	1 622	90	1.15	1 416	90
0.4	1 298	89	0.8	1 688	90	1.2	1 372	90

	X₁/次	X₂/次	X₃/次	${\bar X}$/次	$ \overset\frown{T r L C}$/(veh^-1·s^-1)	换道率相对误差/%
规则1	477	527	484	496	0.009 1	15.59
规则2	1 925	1 918	1 922	1 921	0.035 3	222.93
支持向量机	471	483	495	483	0.008 9	18.34

	X₁/次	X₂/次	X₃/次	${\bar X}$/次	$ \overset\frown{T r L C}$/(veh^-1·s^-1)	换道率相对误差/%
规则1	477	527	484	496	0.009 1	15.59
规则2	1 925	1 918	1 922	1 921	0.035 3	222.93
支持向量机	471	483	495	483	0.008 9	18.34

	X₁/次	X₂/次	X₃/次	${\bar X}$/次	$ \overset\frown{T r L C}$/(veh^-1·s^-1)	换道率相对误差/%
规则1	89	79	66	78	0.005 1	76.99
规则2	385	391	408	395	0.025 9	14.60
支持向量机	395	399	412	402	0.026 4	16.81