Two-Stream Multi-Channel Convolutional Neural Network for Multi-Lane Traffic Speed Prediction Considering Traffic Volume Impact

Ke, Ruimin; Li, Wan; Cui, Zhiyong; Wang, Yinhai

doi:10.1177/0361198120911052

Title: Two-Stream Multi-Channel Convolutional Neural Network for Multi-Lane Traffic Speed Prediction Considering Traffic Volume Impact

Journal Article · Sat Mar 07 00:00:00 EST 2020 · Transportation Research Record

DOI:https://doi.org/10.1177/0361198120911052· OSTI ID:1648914

Ke, Ruimin ^[1];

^[2]; Cui, Zhiyong ^[1]; Wang, Yinhai ^[3]

Univ. of Washington, Seattle, WA (United States)
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Univ. of Washington, Seattle, WA (United States); Pacific U.S. DOT Univ. Transportation Center for Federal Region 10, Seattle, WA (United States)

Traffic speed prediction is a critically important component of intelligent transportation systems. Recently, with the rapid development of deep learning and transportation data science, a growing body of new traffic speed prediction models have been designed that achieved high accuracy and large-scale prediction. However, existing studies have two major limitations. First, they predict aggregated traffic speed rather than lane-level traffic speed; second, most studies ignore the impact of other traffic flow parameters in speed prediction. To address these issues, the authors propose a two-stream multi-channel convolutional neural network (TM-CNN) model for multi-lane traffic speed prediction considering traffic volume impact. In this model, the authors first introduce a new data conversion method that converts raw traffic speed data and volume data into spatial–temporal multi-channel matrices. Then the authors carefully design a two-stream deep neural network to effectively learn the features and correlations between individual lanes, in the spatial–temporal dimensions, and between speed and volume. Accordingly, a new loss function that considers the volume impact in speed prediction is developed. A case study using 1-year data validates the TM-CNN model and demonstrates its superiority. This paper contributes to two research areas: (1) traffic speed prediction, and (2) multi-lane traffic flow study.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 1648914

Journal Information:: Transportation Research Record, Vol. 2674, Issue 4; ISSN 0361-1981

Publisher:: National Academy of Sciences, Engineering and MedicineCopyright Statement

Country of Publication:: United States

Language:: English

Citation Metrics:

Cited by: 31 works

Citation information provided by
Web of Science

References (18)

A behavioral theory of multi-lane traffic flow. Part II: Merges and the onset of congestion Daganzo, Carlos F. Transportation Research Part B: Methodological, Vol. 36, Issue 2 https://doi.org/10.1016/S0191-2615(00)00043-6	journal	February 2002
Multilane traffic flow dynamics: Some macroscopic considerations Michalopoulos, Panos G.; Beskos, Dimitrios E.; Yamauchi, Yasuji Transportation Research Part B: Methodological, Vol. 18, Issue 4-5 https://doi.org/10.1016/0191-2615(84)90019-5	journal	August 1984
Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
A Hierarchy of Models for Multilane Vehicular Traffic I: Modeling Klar, Axel; Wegener, Raimund SIAM Journal on Applied Mathematics, Vol. 59, Issue 3 https://doi.org/10.1137/S0036139997326946	journal	January 1998
Short-term inter-urban traffic forecasts using neural networks Dougherty, Mark S.; Cobbett, Mark R. International Journal of Forecasting, Vol. 13, Issue 1 https://doi.org/10.1016/S0169-2070(96)00697-8	journal	March 1997
Multilane first-order traffic flow model with endogenous representation of lane-flow equilibrium Shiomi, Yasuhiro; Taniguchi, Tomoki; Uno, Nobuhiro Transportation Research Part C: Emerging Technologies, Vol. 59 https://doi.org/10.1016/j.trc.2015.07.002	journal	October 2015
A Cost-Effective Framework for Automated Vehicle-Pedestrian Near-Miss Detection Through Onboard Monocular Vision Ke, Ruimin; Lutin, Jerome; Spears, Jerry 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) https://doi.org/10.1109/CVPRW.2017.124	conference	July 2017
Traffic Prediction Using Multivariate Nonparametric Regression Clark, Stephen Journal of Transportation Engineering, Vol. 129, Issue 2 https://doi.org/10.1061/(ASCE)0733-947X(2003)129:2(161)	journal	March 2003
Macroscopic dynamics of multilane traffic Shvetsov, Vladimir; Helbing, Dirk Physical Review E, Vol. 59, Issue 6 https://doi.org/10.1103/PhysRevE.59.6328	journal	June 1999
Real-Time Bidirectional Traffic Flow Parameter Estimation From Aerial Videos Ke, Ruimin; Li, Zhibin; Kim, Sung IEEE Transactions on Intelligent Transportation Systems, Vol. 18, Issue 4 https://doi.org/10.1109/TITS.2016.2595526	journal	April 2017
Flexible and Robust Method for Missing Loop Detector Data Imputation Henrickson, Kristian; Zou, Yajie; Wang, Yinhai Transportation Research Record: Journal of the Transportation Research Board, Vol. 2527, Issue 1 https://doi.org/10.3141/2527-04	journal	January 2015
Traffic flow data compression considering burst components Feng, Shuo; Ke, Ruimin; Wang, Xingmin IET Intelligent Transport Systems, Vol. 11, Issue 9 https://doi.org/10.1049/iet-its.2016.0328	journal	November 2017
Innovative method for traffic data imputation based on convolutional neural network Zhuang, Yifan; Ke, Ruimin; Wang, Yinhai IET Intelligent Transport Systems, Vol. 13, Issue 4 https://doi.org/10.1049/iet-its.2018.5114	journal	April 2019
A comparison of the performance of artificial. neural networks and support vector machines for the prediction of traffic speed Vanajakshi, L.; Rilett, L. R. IEEE Intelligent Vehicles Symposium, 2004 https://doi.org/10.1109/IVS.2004.1336380	conference	January 2004
Short Term Prediction of Traffic Parameters Using Support Vector Machines Technique Theja, P. V. V. K.; Vanajakshi, L. Third International Conference on Emerging Trends in Engineering and Technology (ICETET 2010), 2010 3rd International Conference on Emerging Trends in Engineering and Technology https://doi.org/10.1109/ICETET.2010.37	conference	November 2010
Traffic Flow Prediction using Kalman Filtering Technique Kumar, Selvaraj Vasantha Procedia Engineering, Vol. 187 https://doi.org/10.1016/j.proeng.2017.04.417	journal	January 2017
Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks Yu, Haiyang; Wu, Zhihai; Wang, Shuqin Sensors, Vol. 17, Issue 7 https://doi.org/10.3390/s17071501	journal	June 2017
Traffic speed prediction for urban transportation network: A path based deep learning approach Wang, Jiawei; Chen, Ruixiang; He, Zhaocheng Transportation Research Part C: Emerging Technologies, Vol. 100 https://doi.org/10.1016/j.trc.2019.02.002	journal	March 2019

Similar Records

Real-Time Movement-Based Traffic Volume Prediction at Signalized Intersections

Journal Article · Sat Aug 01 00:00:00 EDT 2020 · Journal of Transportation Engineering, Part A: Systems · OSTI ID:1648914

Li, Wan; Ban, Xuegang “Jeff”; Zheng, Jianfeng; +3 more

MSASGCN : Multi-Head Self-Attention Spatiotemporal Graph Convolutional Network for Traffic Flow Forecasting

Journal Article · Fri Jun 17 00:00:00 EDT 2022 · Journal of Advanced Transportation · OSTI ID:1648914

Cao, Yang; Liu, Detian; Yin, Qizheng; +3 more

Real-time Intrusion Detection for High-bandwidth Research Networks using Unsupervised Deep Learning

Conference · Wed Jan 01 00:00:00 EST 2020 · OSTI ID:1648914

Gong, Qian

Related Subjects

97 MATHEMATICS AND COMPUTING

Title: Two-Stream Multi-Channel Convolutional Neural Network for Multi-Lane Traffic Speed Prediction Considering Traffic Volume Impact

Citation Formats

References (18)

Similar Records

Related Subjects