Queue Length Estimation at Signalized Intersection Based on Ensemble Learning

doi:10.11908/j.issn.0253-374x.22011

Home > Archive>Volume 51, Issue 3, 2023 >405-415. DOI:10.11908/j.issn.0253-374x.22011

Queue Length Estimation at Signalized Intersection Based on Ensemble Learning
DOI:
                        10.11908/j.issn.0253-374x.22011
                    
CSTR:
                        [cstr]
                    
Author:
                        WU Hao1WU Hao
Key Laboratory of Road and Traffic Engineering of the Ministry of Education，Tongji University， Shanghai 201804， China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
LIU Lei2LIU Lei
Organization Department of CPC Xingping Municipal Committee， Xingping 713100， China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
TANG Keshuang1TANG Keshuang
Key Laboratory of Road and Traffic Engineering of the Ministry of Education，Tongji University， Shanghai 201804， China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site

                    
Affiliation:1.Key Laboratory of Road and Traffic Engineering of the Ministry of Education，Tongji University， Shanghai 201804， China;2.Organization Department of CPC Xingping Municipal Committee， Xingping 713100， China
Clc Number:U491.4
Fund Project:

Article

Figures

Metrics

Reference [41]

Related [20]

Cited by

Materials

Comments

Abstract:

Based on license plate recognition （LPR） data and connected vehicle trajectory data， an ensemble learning method was deployed to estimate the intersection queue length. By analyzing the applicability and accuracy of different queue length estimation methods， the random forest method was applied to design a base ensemble learner and formulize the nonlinear mapping relationship among the LPR data， connected vehicle trajectory data， estimation results of the existing queue length methods and real queue length values. Simulation results show that the proposed method overperforms the existing queue length methods， with a mean absolute error of 1.3 m?cycle^-1?lane^-1 and a mean absolute percent error of 1.4%.

Key words:signalized intersections;queue length;license plate recognition (LPR) data;connected vehicle trajectory data;ensemble learning;random forest

Reference

[1] 杨晓光, 赵靖, 马万经, 等. 信号控制交叉口通行能力计算方法研究综述[J]. 中国公路学报, 2014, 27(5): 148.YANG Xiaoguang, ZHAO Jing, MA Wanjing, et al. Review on calculation method for signalized intersection capacity[J]. China Journal of Highway and Transport, 2014, 27(5): 148.

[2] SHARMA A, BULLOCK D M, BONNESON J A. Input-output and hybrid techniques for real-time prediction of delay and maximum queue length at signalized intersections[J]. Transportation Research Record: Journal of the Transportation Research Board, 2007, 2035(1): 690.

[3] VIGOS G, PAPAGEORGIOU M. A simplified estimation scheme for the number of vehicles in signalized links[J]. IEEE Transactions on Intelligent Transportation Systems, 2010, 11(2): 312.

[4] LEE S, WONG S C, LI Y C. Real-time estimation of lane-based queue lengths at isolated signalized junctions[J]. Transportation Research, Part C: Emerging Technologies, 2015, 56: 1.

[5] ZHAN X, LI R, UKKUSURI S. Lane-based real-time queue length estimation using license plate recognition data[J]. Transportation Research, Part C: Emerging Technologies, 2015, 57: 85.

[6] ZHAN X, LI R, UKKUSURI S V. Link-based traffic state estimation and prediction for arterial networks using license-plate recognition data[J]. Transportation Research, Part C: Emerging Technologies, 2020, 117: 102660.

[7] SKABARDONIS A, GEROLIMINIS N. Real-time monitoring and control on signalized arterials[J]. Journal of Intelligent Transportation Systems, 2008, 12(2): 64.

[8] 姚荣涵, 王殿海. 拥挤交通流当量排队长度变化率模型[J]. 交通运输工程学报, 2009, 9(2): 93.YAO Ronghan, WANG Dianhai. Change rate models of equivalent queue length for congested traffic flow[J]. Journal of Traffic and Transportation Engineering, 2009, 9(2): 93.

[9] LIU H X, WU X, MA W, et al. Real-time queue length estimation for congested signalized intersection[J]. Transportation Research, Part C: Emerging Technologies, 2009, 17(4): 412.

[10] 贾利民, 陈娜, 李海舰, 等. 基于单个地磁传感器的交叉口排队长度估计[J]. 吉林大学学报(工学版), 2016, 46(3): 8.JIA Limin, CHEN Na, LI Haijian, et al. Intersection queue length estimation with single magnetic sensor[J]. Journal of Jilin University (Engineering and Technology Edition), 2016, 46(3): 8.

[11] 李爱杰, 唐克双, 董可然. 基于单截面低频检测数据的信号交叉口排队长度估计[J]. 交通信息与安全, 2018, 36(1): 57.LI Aijie, TANG Keshuang, DONG Keran. Estimation of queuing length at signalized intersections using low-frequency point detector data[J]. Journal of Transport Information and Safety, 2018, 36(1): 57.

[12] YAO J, TANG K. Cycle-based queue length estimation considering spillover conditions based on low-resolution point detector data[J]. Transportation Research, Part C: Emerging Technologies, 2019, 109: 1.

[13] CHANG T H, LIN J T. Optimal signal timing for an oversaturated intersection[J]. Transportation Research, Part B: Methodological, 2000, 34(6): 471.

[14] BAN X J, HAO P, SUN Z. Real time queue length estimation for signalized intersections using travel times from mobile sensors[J]. Transportation Research, Part C: Emerging Technologies, 2011, 19(6): 1133.

[15] RAMEZANI M, GEROLIMINIS N. Queue profile estimation in congested urban networks with probe data[J]. Computer-Aided Civil and Infrastructure Engineering, 2015, 30(6): 414.

[16] LI F, TANG K, YAO J, et al. Real-time queue length estimation for signalized intersections using vehicle trajectory data[J]. Transportation Research Record: Journal of the Transportation Research Board, 2017, 2623(1): 49.

[17] YIN J, SUN J, TANG K. A Kalman filter-based queue length estimation method with low-penetration mobile sensor data at signalized intersections[J]. Transportation Research Record: Journal of the Transportation Research Board, 2018, 2672(45): 253.

[18] ZHANG H, LIU H, CHEN P, et al. Cycle-by-cycle maximum queue length estimation at signalized intersections in connected vehicle environment[C]// 97th Annual Meeting of the Transportation Research Board. Washington DC: Transportation Research Board, 2018:1-9.

[19] COMERT G, CETIN M. Queue length estimation from probe vehicle location and the impacts of sample size[J]. European Journal of Operational Research, 2009, 197(1): 196.

[20] HAO P, BAN X, GUO D, et al. Cycle-by-cycle intersection queue length distribution estimation using sample travel times[J]. Transportation Research, Part B: Methodological, 2014, 68: 185.

[21] TIAPRASERT K, ZHANG Y, WANG X, et al. Queue length estimation using connected vehicle technology for adaptive signal control[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(4): 2129.

[22] TAN C, YAO J, TANG K, et al. Cycle-based queue length estimation for signalized intersections using sparse vehicle trajectory data[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(1): 91.

[23] 谈超鹏, 姚佳蓉, 唐克双. 基于抽样车辆轨迹数据的信号控制交叉口排队长度分布估计[J]. 中国公路学报, 2021, 34(11): 282.TAN Chaopeng, YAO Jiarong, TANG Keshuang. Queue length distribution estimation at signalized intersections based on sampled vehicle trajectory data[J]. China Journal of Highway and Transport, 2021, 34(11): 282.

[24] TANG K, WU H, YAO J, et al. Lane-based queue length estimation at signalized intersections using single-section license plate recognition data[J]. Transportmetrica B: Transport Dynamics, 2022, 10(1): 293.

[25] TAN C, LIU L, WU H, et al. Fuzing license plate recognition data and vehicle trajectory data for lane-based queue length estimation at signalized intersections[J]. Journal of Intelligent Transportation Systems, 2020, 24(5): 449.

[26] MA D, LUO X, JIN S, et al. Estimating maximum queue length for traffic lane groups using travel times from video-imaging data[J]. IEEE Intelligent Transportation Systems Magazine, 2018, 10(3): 123.

[27] LUO X, MA D, JIN S, et al. Queue length estimation for signalized intersections using license plate recognition data[J]. IEEE Intelligent Transportation Systems Magazine, 2019, 11(3): 209.

[28] BADILLO B, RAKHA H, RIOUX T, et al. Queue length estimation using conventional vehicle detector and probe vehicle data[C]//International IEEE Conference on Intelligent Transportation Systems. Anchorage: IEEE, 2012: 1674-1681.

[29] CAI Q, WANG Z, ZHENG L, et al. Shock wave approach for estimating queue length at signalized intersections by fusing data from point and mobile sensors[J]. Transportation Research Record: Journal of the Transportation Research Board, 2014, 2422(1): 79.

[30] BHASKAR A, QU M, CHUNG E. Bluetooth vehicle trajectory by fusing bluetooth and loops: motorway travel time statistics[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(1): 113.

[31] 吴翱翔. 基于多源数据的信号控制信号交叉口排队状态感知方法研究[D]. 上海: 同济大学, 2014.WU Aoxiang. Research on the queue status sense of signalized intersections based on multi-source data[D]. Shanghai: Tongji University, 2014.

[32] 陶晶晶. 基于多源数据融合的单点信号控制交叉口排放估计与优化[D]. 上海: 同济大学, 2017.TAO Jingjing. Emission estimation and optimization of signalized intersection based on multi-source data[D]. Shanghai: Tongji University, 2017.

[33] QOM S, HADI M, XIAO Y, et al. Queue length estimation for freeway facilities: based on combination of point traffic detector and automatic vehicle identification data[J]. Transportation Research Record: Journal of the Transportation Research Board, 2017, 2616(1): 19.

[34] 李爱杰. 基于路段定点检测器与电警数据融合的交叉口排队长度估计与预测[D]. 上海: 同济大学, 2018.LI Aijie. Queue length estimation and prediction based on e-police and point detector data at signalized intersections[D]. Shanghai: Tongji University, 2018.

[35] XIAO J, XIAO Z, WANG D, et al. Short-term traffic volume prediction by ensemble learning in concept drifting environments[J]. Knowledge-Based Systems, 2019, 164: 213.

[36] CHEN X, CAI X, LIANG J, et al. Ensemble learning multiple LSSVR with improved harmony search algorithm for short-term traffic flow forecasting[J]. IEEE Access, 2018, 6: 9347.

[37] ZHANG C, MA Y. Ensemble machine learning: methods and applications[M]. Berlin: Springer Science & Business Media, 2012.

[38] LIU Y, WU H. Prediction of road traffic congestion based on random forest[C]//2017 10th International Symposium on Computational Intelligence and Design (ISCID). Hangzhou:IEEE, 2017, 2: 361-364.

[39] DOGRU N, SUBASI A. Traffic accident detection using random forest classifier[C]// 15th Learning and Technology Conference (L&T). Jeddah: IEEE, 2018: 40-45.

[40] LOH W Y. Classification and regression tree methods[M]// Encyclopedia of Statistics in Quality and Reliability. New York: Wiley, 2008.

[41] ABNEY S. Bootstrapping[C]//Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics. Groningen: Association for Computational Linguistics, 2002: 360-367.

Get Citation

WU Hao, LIU Lei, TANG Keshuang. Queue Length Estimation at Signalized Intersection Based on Ensemble Learning[J].同济大学学报(自然科学版),2023,51(3):405~415

Copy

Article Metrics

Abstract:190
PDF: 626
HTML: 114
Cited by: 0

History

Received:January 07,2022
Revised:
Adopted:
Online: March 29,2023
Published:

Get Citation

Share

Article Metrics

History

Article QR Code