Modeling Merging Acceleration and Deceleration Behavior Based on Gradient-Boosting Decision Tree
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 146, Issue 7
Abstract
This paper aims to model the behavior of merging acceleration/deceleration when cars are running in a congested weaving section on a freeway during the merging implementation period by using a data-driven method called gradient-boosting decision tree (GBDT). Different from other black-box machine learning techniques, GBDT can provide abundant information about the nonlinear effects for independent variables by drawing the partial effects. Noise-filtered vehicle trajectory data collected on US Highway 101 are investigated in this study. The partial dependence plots show that the influence of independent variables on merging acceleration/deceleration is nonlinear and complicated and thus is different from the car-following behavior, which indicates that the adoption of traditional car-following models to merging execution behavior cannot reflect the distinctive behavior of merging vehicles. Evaluation of the performances in comparison with other state-of-the-art methods indicates that the proposed method can obtain more accurate results and thus is practical for simulating the merging execution behavior.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code generated or used during the study are available in a repository or online in accordance with funder data retention policies. The NGISM data used to support the findings of this study have been deposited at the website https://catalog.data.gov/dataset/next-generation-simulation-ngsim-vehicle-trajectories.
Acknowledgments
This work was supported by the Scientific Research Start-Up Funds of Nanjing Forestry University under Grant No. 163106100.
References
Ahmed, K. I. 1999. Modeling drivers’ acceleration and lane changing behavior. Cambridge, MA: Massachusetts Institute of Technology.
Ahmed, M., and M. Abdel-Aty. 2013. “Application of stochastic gradient boosting technique to enhance reliability of real-time risk assessment: Use of automatic vehicle identification and remote traffic microwave sensor data.” Transp. Res. Rec. 2386 (1): 26–34. https://doi.org/10.3141/2386-04.
Alexiadis, V., J. Colyar, J. Halkias, R. Hranac, and G. McHale. 2004. “The next generation simulation program.” Inst. Transp. Eng. ITE J. 74 (8): 22.
Arbis, D., and V. V. Dixit. 2019. “Game theoretic model for lane changing: Incorporating conflict risks.” Accid. Anal. Prev. 125 (Apr): 158–164. https://doi.org/10.1016/j.aap.2019.02.007.
Balal, E., R. L. Cheu, and T. Sarkodie-Gyan. 2016. “A binary decision model for discretionary lane changing move based on fuzzy inference system.” Transp. Res. Part C Emerging Technol. 67 (Jun): 47–61. https://doi.org/10.1016/j.trc.2016.02.009.
Bi, H., T. Mao, Z. Wang, and Z. Deng. 2016. “A data-driven model for lane-changing in traffic simulation.” In Proc., Symp. on Computer Animation, 149–158. Goslar, Germany: Eurographics Association.
Bloomberg, L., and J. Dale. 2000. “A comparison of the VISSIM and CORSIM traffic simulation models.” In Proc., Institute of Transportation Engineers Annual Meeting. Washington, DC: Institute of Transportation Engineers.
Cambridge Systematics. 2005. NGSIM US 101 data analysis: Summary report. Washington, DC: Federal Highway Administration.
Cheng, J., G. Li, and X. Chen. 2019. “Research on travel time prediction model of freeway based on gradient boosting decision tree.” IEEE Access 7: 7466–7480. https://doi.org/10.1109/ACCESS.2018.2886549.
Choudhury, C., V. Ramanujam, and M. Ben-Akiva. 2009. “Modeling acceleration decisions for freeway merges.” Transp. Res. Rec. 2124 (1): 45–57. https://doi.org/10.3141/2124-05.
Choudhury, C. F., M. E. Ben-Akiva, T. Toledo, G. Lee, and A. Rao. 2007. “Modeling cooperative lane changing and forced merging behavior.” In Proc., 86th Annual Meeting of the Transportation Research Board. Washington, DC: Transportation Research Board.
Chu, T. D. 2014. “A study on merging behavior at urban expressway merging sections.” Ph.D. dissertation, Dept. of Civil Engineering, Nagoya Univ.
Daamen, W., M. Loot, and S. P. Hoogendoorn. 2010. “Empirical analysis of merging behavior at freeway on-ramp.” Transp. Res. Rec. 2188 (1): 108–118. https://doi.org/10.3141/2188-12.
Ding, C., X. J. Cao, and P. Næss. 2018. “Applying gradient boosting decision trees to examine non-linear effects of the built environment on driving distance in Oslo.” Transp. Res. Part A Policy Pract. 110 (Apr): 107–117. https://doi.org/10.1016/j.tra.2018.02.009.
Drew, D., L. LaMotte, J. Buhr, and J. Wattleworth. 1967. “Gap acceptance in the freeway merging process.”. College Station, TX: Texas Transportation Institute.
Friedman, J. H. 2001. “Greedy function approximation: A gradient boosting machine.” Ann. Stat. 29 (5): 1189–1232. https://doi.org/10.1214/aos/1013203451.
Gipps, P. G. 1986. “A model for the structure of lane-changing decisions.” Transp. Res. Part B Methodol. 20 (5): 403–414. https://doi.org/10.1016/0191-2615(86)90012-3.
Herman, R., and G. Weiss. 1961. “Comments on the highway-crossing problem.” Oper. Res. 9 (6): 828–840. https://doi.org/10.1287/opre.9.6.828.
Hou, Y., P. Edara, and C. Sun. 2014. “Modeling mandatory lane changing using Bayes classifier and decision trees.” IEEE Trans. Intell. Transp. Syst. 15 (2): 647–655. https://doi.org/10.1109/TITS.2013.2285337.
Johnson, N. E., B. Bonczak, and C. E. Kontokosta. 2018. “Using a gradient boosting model to improve the performance of low-cost aerosol monitors in a dense, heterogeneous urban environment.” Atmos. Environ. 184 (Jul): 9–16. https://doi.org/10.1016/j.atmosenv.2018.04.019.
Kang, K., and H. A. Rakha. 2018. “Modeling driver merging behavior: A repeated game theoretical approach.” Transp. Res. Rec. 2672 (20): 144–153. https://doi.org/10.1177/0361198118792982.
Killat, M., T. Gaugel, and H. Hartenstein. 2008. “Enabling traffic safety assessment of VANETs by means of accident simulations.” In Proc., 2008 IEEE 19th Int. Symp. on Personal, Indoor and Mobile Radio Communications, 1–6. New York: IEEE.
Kita, H. 1993. “Effects of merging lane length on the merging behavior at expressway on-ramps.” In Proc., Transportation and Traffic Theory, 12th Int. Symp. on the Theory of Traffic Flow and Transportation, 37–51. New York: Elsevier.
Li, G. 2018. “Application of finite mixture of logistic regression for heterogeneous merging behavior analysis.” J. Adv. Transp. 2018: 1–9. https://doi.org/10.1155/2018/1436521.
Li, G., and J. Cheng. 2019. “Exploring the effects of traffic density on merging behavior.” IEEE Access 7: 51608–51619. https://doi.org/10.1109/ACCESS.2019.2911302.
Li, G., Y. Pan, Z. Yang, and J. J. I. A. Ma. 2019. “Modeling vehicle merging position selection behaviors based on a finite mixture of linear regression models.” IEEE Access 7: 158445–158458. https://doi.org/10.1109/ACCESS.2019.2950444.
Li, G., and L. Sun. 2018. “Characterizing heterogeneity in drivers’ merging maneuvers using two-step cluster analysis.” J. Adv. Transp. 2018: 1–15. https://doi.org/10.1155/2018/5604375.
Liu, M., Y. Wang, G. Lu, and Z. Zhang. 2014. “Logit-based merging behavior model for uncontrolled intersections in China.” J. Transp. Eng. 140 (12): 04014059. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000719.
Liu, P., B. Fu, and S. X. Yang. 2019. “HitBoost: Survival analysis via a multi-output gradient boosting decision tree method.” IEEE Access 7: 56785–56795. https://doi.org/10.1109/ACCESS.2019.2913428.
Lombardo, L., M. Cama, C. Conoscenti, M. Märker, and E. Rotigliano. 2015. “Binary logistic regression versus stochastic gradient boosted decision trees in assessing landslide susceptibility for multiple-occurring landslide events: Application to the 2009 storm event in Messina (Sicily, Southern Italy).” Nat. Hazard. 79 (3): 1621–1648. https://doi.org/10.1007/s11069-015-1915-3.
Ma, X., C. Ding, S. Luan, Y. Wang, and Y. Wang. 2017. “Prioritizing influential factors for freeway incident clearance time prediction using the gradient boosting decision trees method.” IEEE Trans. Intell. Transp. Syst. 18 (9): 2303–2310. https://doi.org/10.1109/TITS.2016.2635719.
Marczak, F., W. Daamen, and C. Buisson. 2013. “Merging behaviour: Empirical comparison between two sites and new theory development.” Transp. Res. Part C Emerging Technol. 36 (Nov): 530–546. https://doi.org/10.1016/j.trc.2013.07.007.
Maslekar, N., M. Boussedjra, J. Mouzna, and H. Labiod. 2011. “VANET based adaptive traffic signal control.” In Proc., Vehicular Technology Conf. Piscataway, NJ: IEEE.
Meng, Q., and J. Weng. 2012. “Classification and regression tree approach for predicting drivers’ merging behavior in short-term work zone merging areas.” J. Transp. Eng. 138 (8): 1062–1070. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000412.
Moridpour, S., M. Sarvi, and G. Rose. 2010. “Modeling the lane-changing execution of multiclass vehicles under heavy traffic conditions.” Transp. Res. Rec. 2161 (1): 11–19. https://doi.org/10.3141/2161-02.
Moridpour, S., M. Sarvi, G. Rose, and E. Mazloumi. 2012. “Lane-changing decision model for heavy vehicle drivers.” J. Intell. Transp. Syst. 16 (1): 24–35. https://doi.org/10.1080/15472450.2012.639640.
Pan, Y. 2019. “Lagrangian relaxation for the multiple constrained robust shortest path problem.” Math. Prob. Eng. 2019: 1–13. https://doi.org/10.1155/2019/3987278.
PTV-Vision. 2011. VISSIM 5.30-05 user manual. Düsseldorf, Germany: Planung Transport Verkehr AG.
Punzo, V., M. T. Borzacchiello, and B. Ciuffo. 2011. “On the assessment of vehicle trajectory data accuracy and application to the Next Generation SIMulation (NGSIM) program data.” Transp. Res. Part C Emerging Technol. 19 (6): 1243–1262. https://doi.org/10.1016/j.trc.2010.12.007.
Quadstone Paramics. 2009. The paramics manuals, version 6.6.1. Edinburgh, UK: Quastone Paramics.
Rahman, M., M. Chowdhury, Y. Xie, and Y. He. 2013. “Review of microscopic lane-changing models and future research opportunities.” IEEE Trans. Intell. Transp. Syst. 14 (4): 1942–1956. https://doi.org/10.1109/TITS.2013.2272074.
Sarvi, M., and M. Kuwahara. 2007. “Microsimulation of freeway ramp merging processes under congested traffic conditions.” IEEE Trans. Intell. Transp. Syst. 8 (3): 470–479. https://doi.org/10.1109/TITS.2007.895305.
Schapire, R. E. 1990. “The strength of weak learnability.” Mach. Learn. 5 (2): 197–227. https://doi.org/10.1007/BF00116037.
Sun, D., and L. Elefteriadou. 2012. “A driver behavior-based lane-changing model for urban arterial streets.” Transp. Sci. 48 (2): 184–205. https://doi.org/10.1287/trsc.1120.0435.
Sun, J., K. Zuo, S. Jiang, and Z. Zheng. 2018. “Modeling and predicting stochastic merging behaviors at freeway on-ramp bottlenecks.” J. Adv. Transp. 2018: 1–15. https://doi.org/10.1155/2018/9308580.
Tang, J., F. Liu, W. Zhang, R. Ke, and Y. Zou. 2018. “Lane-changes prediction based on adaptive fuzzy neural network.” Expert Syst. Appl. 91 (Jan): 452–463. https://doi.org/10.1016/j.eswa.2017.09.025.
Tang, W., and D. M. Levinson. 2018. “Deviation between actual and shortest travel time paths for commuters.” J. Transp. Eng. Part A Syst. 144 (8): 04018042. https://doi.org/10.1061/JTEPBS.0000161.
Thiemann, C., M. Treiber, and A. Kesting. 2008. “Estimating acceleration and lane-changing dynamics from next generation simulation trajectory data.” Transp. Res. Rec. 2088 (1): 90–101. https://doi.org/10.3141/2088-10.
Toledo, T., H. N. Koutsopoulos, and M. Ben-Akiva. 2007. “Integrated driving behavior modeling.” Transp. Res. Part C Emerging Technol. 15 (2): 96–112. https://doi.org/10.1016/j.trc.2007.02.002.
Touzani, S., J. Granderson, and S. Fernandes. 2018. “Gradient boosting machine for modeling the energy consumption of commercial buildings.” Energy Build. 158 (Jan): 1533–1543. https://doi.org/10.1016/j.enbuild.2017.11.039.
Wan, X., P. J. Jin, H. Gu, X. Chen, and B. Ran. 2017. “Modeling freeway merging in a weaving section as a sequential decision-making process.” J. Transp. Eng. Part A Syst. 143 (5): 05017002. https://doi.org/10.1061/JTEPBS.0000048.
Wan, X., P. J. Jin, F. Yang, and B. Ran. 2016. “Merging preparation behavior of drivers: How they choose and approach their merge positions at a congested weaving area.” J. Transp. Eng. 142 (9): 05016005. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000864.
Wan, X., P. J. Jin, F. Yang, J. Zhang, and B. Ran. 2014. “Modeling vehicle interactions during merge in congested weaving section of freeway ramp.” Transp. Res. Rec. 2421 (1): 82–92. https://doi.org/10.3141/2421-10.
Wang, E., and J. Sun. 2018. “Exploring freeway merging behavior using dynamic Bayesian network models.” In Proc., Int. Conf. on Transportation and Development 2018: Traffic and Freight Operations and Rail and Public Transit, 120–130. Reston, VA: ASCE.
Wang, Q., Z. Li, and L. Li. 2014. “Investigation of discretionary lane-change characteristics using next-generation simulation data sets.” J. Intell. Transp. Syst. 18 (3): 246–253. https://doi.org/10.1080/15472450.2013.810994.
Weng, J., G. Du, D. Li, and Y. Yu. 2018. “Time-varying mixed logit model for vehicle merging behavior in work zone merging areas.” Accid. Anal. Prev. 117 (Aug): 328–339. https://doi.org/10.1016/j.aap.2018.05.005.
Weng, J., and Q. Meng. 2011. “Modeling speed-flow relationship and merging behavior in work zone merging areas.” Transp. Res. Part C Emerging Technol. 19 (6): 985–996. https://doi.org/10.1016/j.trc.2011.05.001.
Weng, J., S. Xue, and X. Yan. 2016. “Modeling vehicle merging behavior in work zone merging areas during the merging implementation period.” IEEE Trans. Intell. Transp. Syst. 17 (4): 917–925. https://doi.org/10.1109/TITS.2015.2477335.
Weng, J., S. Xue, Y. Yang, X. Yan, and X. Qu. 2015. “In-depth analysis of drivers’ merging behavior and rear-end crash risks in work zone merging areas.” Accid. Anal. Prev. 77 (Apr): 51–61. https://doi.org/10.1016/j.aap.2015.02.002.
Wu, L., L. Yu, W. Wang, and J. Liu. 2019. “Prediction for the region disposition of Panama dry bulk fleet management.” IEEE Access 7: 136604–136615. https://doi.org/10.1109/ACCESS.2019.2939206.
Xu, L., J. Lu, B. Ran, F. Yang, and J. Zhang. 2019. “Cooperative merging strategy for connected vehicles at highway on-ramps.” J. Transp. Eng. Part A Syst. 145 (6): 04019022. https://doi.org/10.1061/JTEPBS.0000243.
Yang, S., J. Wu, Y. Du, Y. He, and X. Chen. 2017. “Ensemble learning for short-term traffic prediction based on gradient boosting machine.” J. Sens. 2017: 1–15. https://doi.org/10.1155/2017/7074143.
Yu, Q., and D. Liu. 2010. “Disseminate warning message in VANETs based on predicting the interval of vehicles.” In Proc., 2010 5th Int. Conf. on Frontier of Computer Science and Technology, 559–564. New York: IEEE.
Zhang, F., X. Zhu, T. Hu, W. Guo, C. Chen, and L. Liu. 2016. “Urban link travel time prediction based on a gradient boosting method considering spatiotemporal correlations.” ISPRS Int. J. Geo-Inf. 5 (11): 201. https://doi.org/10.3390/ijgi5110201.
Zhang, Y., and A. Haghani. 2015. “A gradient boosting method to improve travel time prediction.” Transp. Res. Part C Emerging Technol. 58 (Sep): 308–324. https://doi.org/10.1016/j.trc.2015.02.019.
Zheng, Z. 2014. “Recent developments and research needs in modeling lane changing.” Transp. Res. Part B Methodol. 60 (Feb): 16–32. https://doi.org/10.1016/j.trb.2013.11.009.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part A: Systems
Volume 146 • Issue 7 • July 2020
Copyright
©2020 American Society of Civil Engineers.
History
Received: Jul 31, 2019
Accepted: Feb 11, 2020
Published online: May 8, 2020
Published in print: Jul 1, 2020
Discussion open until: Oct 8, 2020
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.