|Table of Contents|

[1] Cheng Juan, Chen Xianhua,. Travel time prediction model of freewaybased on gradient boosting decision tree [J]. Journal of Southeast University (English Edition), 2019, 35 (3): 393-398. [doi:10.3969/j.issn.1003-7985.2019.03.017]
Copy

Travel time prediction model of freewaybased on gradient boosting decision tree()
基于梯度提升决策树的高速公路行程时间预测模型
Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
35
Issue:
2019 3
Page:
393-398
Research Field:
Traffic and Transportation Engineering
Publishing date:
2019-09-30

Info

Title:
Travel time prediction model of freewaybased on gradient boosting decision tree
基于梯度提升决策树的高速公路行程时间预测模型
Author(s):
Cheng Juan;  Chen Xianhua
School of Transportation, Southeast University, Nanjing 211189, China
程娟;  陈先华
东南大学交通学院, 南京 211189
Keywords:
gradient boosting decision tree(GBDT);  travel time prediction;  freeway;  traffic state parameter
梯度提升决策树;  行程时间预测;  高速公路;  交通状态参数
PACS:
U491.2
DOI:
10.3969/j.issn.1003-7985.2019.03.017
Abstract:
To investigate the travel time prediction method of the freeway, a model based on the gradient boosting decision tree(GBDT)is proposed. Eleven variables(namely, travel time in current period Ti, traffic flow in current period Qi, speed in current period Vi, density in current period Ki, the number of vehicles in current period Ni, occupancy in current period Ri, traffic state parameter in current period Xi, travel time in previous time period Ti-1, etc.)are selected to predict the travel time for 10 min ahead in the proposed model. Data obtained from VISSIM simulation is used to train and test the model. The results demonstrate that the prediction error of the GBDT model is smaller than those of the back propagation(BP)neural network model and the support vector machine(SVM)model. Travel time in current period Ti is the most important variable among all variables in the GBDT model. The GBDT model can produce more accurate prediction results and mine the hidden nonlinear relationships deeply between variables and the predicted travel time.
为研究高速公路行程时间预测方法, 基于梯度提升决策树(GBDT)建立了行程时间预测模型.提出的模型中选用11个变量(当前时段行程时间Ti、当前时段流量Qi、当前时段速度Vi、当前时段密度Ki、当前时段车辆数Ni、当前时段占有率Ri、当前时段交通状态参数Xi、前一个时段行程时间Ti-1等)预测向前10 min的行程时间.利用VISSIM仿真得到的数据对模型进行训练和测试.结果表明, GBDT模型的预测误差小于BP神经网络模型和支持向量机模型;GBDT模型中当前时段行程时间Ti在所有变量中最重要.GBDT模型能够得到更准确的预测结果, 能深入挖掘变量与预测行程时间之间隐藏的非线性关系.

References:

[1] Lee W H, Tseng S S, Tsai S H. A knowledge based real-time travel time prediction system for urban network[J]. Expert Systems with Applications, 2009, 36(3): 4239-4247. DOI:10.1016/j.eswa.2008.03.018.
[2] Miranda D M, Concei�E7;�E3;o S V. The vehicle routing problem with hard time windows and stochastic travel and service time[J]. Expert Systems with Applications, 2016, 64: 104-116. DOI:10.1016/j.eswa.2016.07.022.
[3] Oh S, Byon Y J, Jang K, et al. Short-term travel-time prediction on highway: A review on model-based approach[J]. KSCE Journal of Civil Engineering, 2018, 22(1): 298-310. DOI:10.1007/s12205-017-0535-8.
[4] Farokhi Sadabadi K, Hamedi M, Haghani A. Evaluating moving average techniques in short-term travel time prediction using an AVI data set[C]//Transportation Research Board 89th Annual Meeting. Washington, DC, USA, 2010.
[5] Julio N, Giesen R, Lizana P. Real-time prediction of bus travel speeds using traffic shockwaves and machine learning algorithms[J]. Research in Transportation Economics, 2016, 59: 250-257. DOI:10.1016/j.retrec.2016.07.019.
[6] Liu W M, Li S S. Freeway travel time prediction simulation research based on big data[J]. Computer Simulation, 2017, 34(3): 395-399.(in Chinese)
[7] Cai H R, He L L. A combined offline travel time prediction model based on speed matrix and artificial neural network[J]. Journal of Zhejiang Sci-Tech University(Natural Sciences Edition), 2017(6): 851-858.(in Chinese)
[8] Yu B, Yang Z Z, Yao B Z. Bus arrival time prediction using support vector machines[J]. Journal of Intelligent Transportation Systems, 2006, 10(4): 151-158. DOI:10.1080/15472450600981009.
[9] Reddy K K, Anil Kumar B, Vanajakshi L. Bus travel time prediction under high variability conditions[J]. Current Science, 2016, 111(4): 700. DOI:10.18520/cs/v111/i4/700-711.
[10] Sun X Y, Zhang H, Tian F L, et al. The use of a machine learning method to predict the real-time link travel time of open-pit trucks[J]. Mathematical Problems in Engineering, 2018, 2018: 1-14. DOI:10.1155/2018/4368045.
[11] Kumar B A, Vanajakshi L, Subramanian S C. Bus travel time prediction using a time-space discretization approach[J]. Transportation Research Part C: Emerging Technologies, 2017, 79: 308-332. DOI:10.1016/j.trc.2017.04.002.
[12] Zhao J D, Guo Y J, Duan X H. Dynamic path planning of emergency vehicles based on travel time prediction[J]. Journal of Advanced Transportation, 2017, 2017: 1-14. DOI:10.1155/2017/9184891.
[13] Gal A, Mandelbaum A, Schnitzler F, et al. Traveling time prediction in scheduled transportation with journey segments[J]. Information Systems, 2017, 64: 266-280. DOI:10.1016/j.is.2015.12.001.
[14] Zhao J D, Gao Y, Tang J J, et al. Highway travel time prediction using sparse tensor completion tactics and K-nearest neighbor pattern matching method[J]. Journal of Advanced Transportation, 2018, 2018: 1-16. DOI:10.1155/2018/5721058.
[15] Ahmed M M, Abdel-Aty M. Application of stochastic gradient boosting technique to enhance reliability of real-time risk assessment[J]. Transportation Research Record: Journal of the Transportation Research Board, 2013, 2386: 26-34. DOI:10.3141/2386-04.
[16] Friedman J H. Stochastic gradient boosting[J]. Computational Statistics & Data Analysis, 2002, 38(4): 367-378. DOI:10.1016/s0167-9473(01)00065-2.
[17] Friedman J H, Meulman J J. Multiple additive regression trees with application in epidemiology[J]. Statistics in Medicine, 2003, 22(9): 1365-1381. DOI:10.1002/sim.1501.
[18] National Research Council. HCM2010: Highway capacity manual [M]. 5th ed. Washington, DC, USA: Transportation Research Board, 2010.
[19] Zhang Y R, Haghani A. A gradient boosting method to improve travel time prediction[J]. Transportation Research Part C: Emerging Technologies, 2015, 58: 308-324. DOI:10.1016/j.trc.2015.02.019.

Memo

Memo:
Biographies: Cheng Juan(1983—), female, Ph.D. candidate; Chen Xianhua(corresponding author), male, doctor, professor, chenxh@seu.edu.cn.
Foundation item: The National Natural Science Foundation of China(No.51478114, 51778136).
Citation: Cheng Juan, Chen Xianhua. Travel time prediction model of freeway based on gradient boosting decision tree[J].Journal of Southeast University(English Edition), 2019, 35(3):393-398.DOI:10.3969/j.issn.1003-7985.2019.03.017.
Last Update: 2019-09-20