Research on Traffic Flow Prediction Method Based on Gated Recurrent
Unit Recurrent Neural Network

doi:10.3969/j.issn.1674-0696.2018.11.13

Journal of Chongqing Jiaotong University(Natural Science) ›› 2018, Vol. 37 ›› Issue (11): 76-82.DOI: 10.3969/j.issn.1674-0696.2018.11.13

• Traffic & Transportation Engineering • Previous Articles Next Articles

Research on Traffic Flow Prediction Method Based on Gated Recurrent Unit Recurrent Neural Network

WANG Tiying1，SHI Pengchao1，LIU Jiangqiong2，LIU Boyi3，SHI Tianhao4

(1. Mechanical and Electrical College，Hainan University，Haikou 570228，Hainan，P. R. China； 2. Institute of Tropical Agriculture and Forestry，Hainan University，Haikou 570228，Hainan，P. R. China； 3. College of Information Science & Technology，Hainan University，Haikou 570228，Hainan，P. R. China； 4. College of Transportation，Shandong University of Science and Technology，Qingdao 266590，Shandong，P. R. China)

Received:2017-02-15 Revised:2017-12-10 Online:2018-11-19 Published:2018-11-19

基于门限递归单元循环神经网络的交通流预测方法研究

王体迎1，时鹏超1，刘蒋琼2，刘博艺3，时天昊4

(1. 海南大学机电工程学院，海南海口 570228； 2. 海南大学热带农林学院，海南海口 570228; 3. 海南大学信息科学技术学院，海南海口 570228； 4. 山东科技大学交通学院，山东青岛 266590)

作者简介:王体迎(1966—)，女，贵州贵阳人，副教授，主要从事交通运输规划与管理方面的研究。E-mail:wty@hainu.edu.cn。通信作者：时鹏超(1995—)，男，山东菏泽人，主要从事智能交通方面的研究。E-mail:1377197849@qq.com。
基金资助:
海南省自然科学基金项目(20155212)

Abstract

Abstract: In order to effectively implement the intelligent traffic management system, it is necessary to improve the accuracy of traffic flow prediction. A short-term traffic flow prediction method was proposed based on the gated recurrent unit recurrent neural network. The new method can effectively model the “sequence information” without relying on the prior knowledge. By adopting this method, the real traffic flow data of British Columbia in Canada was modeled and analyzed, and the predicted effects by inputting data under different lag time were compared. In the meantime, the predicted results were compared with the ones of ARIMA and SVR. The study also demonstrated the predicted effect of new method in weekdays and weekends. The comparison results show that the new method performs well, and the mean absolute percentage errors reduced 74.72% and 12.15% respectively comparing with ARIMA and SVR. This new method achieves a high conformity between the predicted and actual traffic flow, which is effective and accurate for the future traffic flow prediction.

Key words: traffic and transportation engineering, intelligent transportation system, traffic flow prediction, gated recurrent unit, recurrent neural network

摘要： 为了有效地实施智能交通管理系统，需要进一步提高交通流量预测的准确率。提出了一种基于门限递归单元循环神经网络的短时交通流量预测方法，该方法可以不依靠先验知识，有效地利用“序列信息”建模。通过使用该方法对加拿大大不列颠哥伦比亚省的真实交通流量数据进行建模分析，并对比了在不同滞后时间的输入数据下该方法的预测效果，然后将其与ARIMA和SVR的预测结果进行了对比，同时也展示了该方法在工作日和周末的实际预测效果。结果表明：该方法预测效果良好，其平均绝对百分误差比ARIMA与SVR分别平均降低了74.72%和12.15%，预测值和实际交通流量吻合度高，是一种预测精度高且有效的交通流量预测方法。

关键词: 交通运输工程, 智能交通系统, 交通流量预测, 门限递归单元, 递归神经网络

CLC Number:

U491

WANG Tiying1，SHI Pengchao1，LIU Jiangqiong2，LIU Boyi3，SHI Tianhao4. Research on Traffic Flow Prediction Method Based on Gated Recurrent Unit Recurrent Neural Network[J]. Journal of Chongqing Jiaotong University(Natural Science), 2018, 37(11): 76-82.

王体迎1，时鹏超1，刘蒋琼2，刘博艺3，时天昊4. 基于门限递归单元循环神经网络的交通流预测方法研究[J]. 重庆交通大学学报（自然科学版）, 2018, 37(11): 76-82.

References

［1］ LV Y, DUAN Y, KANG W. Traffic flow prediction with big data: a deep learning approach［J］. IEEE Transactions on Intelligent
Transportation Systems, 2015, 16(2): 865-873.
［2］ MA X, TAO Z, WANG Y. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data［
J］. Transportation Research Part C Emerging Technologies, 2015, 54: 187-197.
［3］ HOU Y, EDARA P, SUN C. Traffic flow forecasting for urban work zones［J］. IEEE Transactions on Intelligent Transportation
Systems, 2015, 16(4): 1761-1770.
［4］ ROMERO D, RICO N, GARCIA-ARENAS M I. Modellation and forecast of traffic series by a stochastic process［M］// Time Series
Analysis and Forecasting. Berlin:Springer International Publishing, 2016.
［5］ FAN N, ZHAO X M, DAI M, et al. Short-term traffic flow prediction model［J］. Journal of Traffic & Transportation
Engineering, 2012,12:114-119.
［6］ KUMARS V, VANAJAKSHI L. Short-term traffic flow prediction using seasonal ARIMA model with limited input data［J］. European
Transport Research Review, 2015, 7(3):21.
［7］ OKUTANI I, STEPHANEDES Y J. Dynamic prediction of traffic volume through Kalman filtering theory［J］. Transportation
Research Part B: Methodological, 1984, 18(1): 1-11.
［8］ STEPHANEDES Y J, MICHALOPOULOS P G, PLUM R A. Improved estimation of traffic flow for real time control［J］. Journal of the
Transportation Research Board, 1981,795:28-39.
［9］ DAVISG A, NIHAN N L. Nonparametric regression and short-term freeway traffic forecasting［J］. Journal of Transportation
Engineering, 1991, 117(2): 178-188.
［10］许岩岩, 翟希, 孔庆杰. 高速路交通流量短时预测方法［J］. 交通运输工程学报, 2013, 13(2): 114-119.
XU Yanyan, ZHAI xi, KONG Qingjie. Short-term prediction method of freeway traffic flow［J］. Journal of Traffic and Transportation
Engineering, 2013, 13(2):114-119.
［11］ CHAI Y, HUANG D, ZHAO L. A short-term traffic flow prediction method based on wavelet analysis and neural network［C］//
Control and Decision Conference.Piscataway, N J: IEEE, 2016:7030-1034.
［12］ BAI C, PENG Z R, LU Q C, et al. Dynamic bus travel time prediction models on road with multiple bus routes［J］.
Computational Intelligence & Neuroscience, 2015(3):1-9.
［13］康军, 段宗涛, 唐蕾. 高斯过程回归短时交通流量预测方法［J］. 交通运输系统工程与信息, 2015, 15(4):51-56.
KANG Jun, DUAN Zongtao, TANG Lei. A short term traffic flow prediction method based on gaussian processes regression［J］. Journal
of Transportation Systems Engineering and Information Technology, 2015, 15(4): 51-56
［14］ BENGIO Y. Learning deep architectures for AI［J］. Foundations and Trends  in Machine Learning, 2009, 2(1): 1-127.
［15］ HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks［J］. Science, 2006, 313(5786):
504.
［16］ COLLOBERT R, WESTON J. A unified architecture for natural language processing:deep neural networks with multitask learning
［C］// International Conference on Machine Learning. New York: ACM, 2008:160-167.
［17］ SCHMIDHUBER J. Deep learning in neural networks: An overview［J］. Neural Networks, 2015, 61: 85-117.
［18］ ZHOU X, XIE L, ZHANG P, et al. An ensemble of deep neural networks for object tracking［C］//IEEE International Conference
on Image Processing. Piscataway, NJ: IEEE, 2015:843-847.
［19］ SHIN H C, ORTON M R, COLLINS D J, et al. Stacked autoencoders for unsupervised feature learning and multiple organ
detection in a pilot study using 4D patient data［J］. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2013, 35
(8):1930-1943.
［20］ HOCHREITER S, SCHMIDHUBER J. Long short-term memory［J］.
Neural Computation, 1997, 9(8): 1735-1780.
［21］ KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classifica-
tion with deep convolutional neural networks［C］//Advances in Neural Information Processing Systems. New York : Curran Associates
Inc., 2012: 1097-1105.
［22］ LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition［J］. Proceedings of the IEEE,
1998, 86(11):2278-2324.
［23］ CHO K, VAN MERRIЁNBOER B, GULCEHRE C, et al. Learning Phrase Representations using RNN Encoder-Decoder for Statistical
Machine Translation［C］// Empirical Methods in Natural Language Processing. Stroudsburg,PA : ACL, 2014:1724-1734.
［24］ GOODFELLOW I, BENGIO Y, COURVILLE A, et al. Deep Learning［M］. Cambridge: MIT Press, 2016.

[1]	LI Jing1,2, ZHONG Peng1, LYU Jing1,2. Interaction between Land Port and Urban Economy Based on System Dynamics [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(07): 1-7.
[2]	LI Jun1, ZHU Yunsheng2. Application of Comprehensive Evaluation of Triangular Fuzzy Analytic Hierarchy Process in Ship Safety Assessment of the Yellow River Reservoir Area [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(07): 16-22.
[3]	DENG Ping1,2, SONG Lian1, HUANG Chengfeng1,2. Estimation of Congestion Costs for Lockage Ship in Three Gorges Dam Area and Its Impact on the Total Value of Goods in the Dam Area [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(07): 23-30.
[4]	CHENG Qian1, ZHU Xiaoning2, LU Wansheng3. Travel Mode Choice Behavior Model of Intercity Passengers with Medium and Long Haul — A Case Study of High-Speed Railway and Air Transport [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(07): 39-45.
[5]	LIAN Qicai1, LI Han1, SHI Xiaolin1, YAN Zhangcun2. Autonomous Driving Choice Behavior Based on Panel Data Mixed Logit Model [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(07): 46-52.
[6]	QI Chunhua, WANG Xiaonan, ZHU Shoulin, LI Hangtian. Traffic Engineering Facility Information Threshold Based on Drivers Visual Area of Interest [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(07): 53-60.
[7]	LI Shengchao, WU Yue, BAI Xuemeng, WANG Yue, ZHANG Hai. Violation Alarm of Dangerous Goods Vehicle Based on TOPSIS and Gray Correlation [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(07): 61-66.
[8]	YANG Qingfang1,2,3, WANG Liqiang2, ZHENG Lili1,2,3, MENG Fanyun2. Traffic Emission and Fuel Consumption Model of Roundabout [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(07): 67-73.
[9]	BAI Han, ZHANG Kangyu, WANG Xiuguang, YAN Xiang, FENG Qilong. Traffic Capacity of Urban Intersection under the Conditions of Mixed Release of Traffic Flow [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(06): 12-20.
[10]	WANG Tao1, XIE Sihong1, LI Wenhao1,2, LI Wenyong1. Short-Term Traffic Flow Adaptive Prediction Model Based on FFOS-ELM and PF [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(06): 21-27.
[11]	ZHANG Chongyang, HUANG Shuping. Seismic Reliability of Road Network and Route Selection of Post-Earthquake Transportation [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(06): 43-51.
[12]	GUO Wenwen1, JI Mingjun2, ZHU Huiling3, ZHOU Wenjie2. Optimization Model of Yard Crane Scheduling in a Container Terminal [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(06): 66-72.
[13]	LI Guangru, ZHANG Xin, ZHU Qinghui. Prediction Method of Port Throughput with Improved Elman Neural Network Based on Adaboost [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(05): 1-5.
[14]	SUN Yuanguang1, JIAN Min2, JIN Hua2, CHEN Shaokuan2. Calculation and Simulation of Delay during Train Failure Rescue of Urban Rail Transit [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(05): 6-12.
[15]	WANG Honggang1,2, BAI Peng1, ZOU Qingru2, ZHAO Ling1. Optimization Model of Track Application for Metro Depots [J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(05): 13-18.

Research on Traffic Flow Prediction Method Based on Gated Recurrent Unit Recurrent Neural Network

基于门限递归单元循环神经网络的交通流预测方法研究

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics