Real-Time Movement-Based Traffic Volume Prediction at Signalized Intersections
Abstract
The traffic volume of each movement at signalized intersections can provide valuable information on real-time traffic conditions that enable traffic control systems to dynamically respond to the fluctuated traffic demands. Real-time movement-based traffic volume prediction is challenging due to various nonlinear spatial relationships at different locations/approaches and the complicated underlying temporal dependencies. In this study, a novel deep intersection spatial-temporal network (DISTN) is developed for real-time movement-based traffic volume prediction at signalized intersections, which considers both spatial and temporal features by the convolutional neural network (CNN) and long short-term memory (LSTM), respectively. In addition, the within-day, daily, and weekly periodic trends of traffic volume are also considered in the proposed model. This is the first time that a deep-learning method has been applied for movement-based traffic volume prediction at signalized intersections. In the numerical experiment, the proposed model is evaluated using real-world data and simulation data to demonstrate its effectiveness. The impacts of various structures of traffic networks on the proposed model are also discussed. Results show that the proposed model outperforms some of the state-of-the-art volume prediction methods currently in the literature.
- Authors:
-
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Univ. of Washington, Seattle, WA (United States)
- Didi Chuxing, Beijing (China)
- Univ. of Michigan, Ann Arbor, MI (United States)
- Jinan Public Security Bureau, Jinan (China)
- Publication Date:
- Research Org.:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1648915
- Grant/Contract Number:
- AC05-00OR22725
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Journal of Transportation Engineering, Part A: Systems
- Additional Journal Information:
- Journal Volume: 146; Journal Issue: 8; Journal ID: ISSN 2473-2907
- Publisher:
- American Society of Civil Engineers (ASCE)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 99 GENERAL AND MISCELLANEOUS
Citation Formats
Li, Wan, Ban, Xuegang “Jeff”, Zheng, Jianfeng, Liu, Henry X., Gong, Cheng, and Li, Yong. Real-Time Movement-Based Traffic Volume Prediction at Signalized Intersections. United States: N. p., 2020.
Web. doi:10.1061/jtepbs.0000384.
Li, Wan, Ban, Xuegang “Jeff”, Zheng, Jianfeng, Liu, Henry X., Gong, Cheng, & Li, Yong. Real-Time Movement-Based Traffic Volume Prediction at Signalized Intersections. United States. https://doi.org/10.1061/jtepbs.0000384
Li, Wan, Ban, Xuegang “Jeff”, Zheng, Jianfeng, Liu, Henry X., Gong, Cheng, and Li, Yong. Sat .
"Real-Time Movement-Based Traffic Volume Prediction at Signalized Intersections". United States. https://doi.org/10.1061/jtepbs.0000384. https://www.osti.gov/servlets/purl/1648915.
@article{osti_1648915,
title = {Real-Time Movement-Based Traffic Volume Prediction at Signalized Intersections},
author = {Li, Wan and Ban, Xuegang “Jeff” and Zheng, Jianfeng and Liu, Henry X. and Gong, Cheng and Li, Yong},
abstractNote = {The traffic volume of each movement at signalized intersections can provide valuable information on real-time traffic conditions that enable traffic control systems to dynamically respond to the fluctuated traffic demands. Real-time movement-based traffic volume prediction is challenging due to various nonlinear spatial relationships at different locations/approaches and the complicated underlying temporal dependencies. In this study, a novel deep intersection spatial-temporal network (DISTN) is developed for real-time movement-based traffic volume prediction at signalized intersections, which considers both spatial and temporal features by the convolutional neural network (CNN) and long short-term memory (LSTM), respectively. In addition, the within-day, daily, and weekly periodic trends of traffic volume are also considered in the proposed model. This is the first time that a deep-learning method has been applied for movement-based traffic volume prediction at signalized intersections. In the numerical experiment, the proposed model is evaluated using real-world data and simulation data to demonstrate its effectiveness. The impacts of various structures of traffic networks on the proposed model are also discussed. Results show that the proposed model outperforms some of the state-of-the-art volume prediction methods currently in the literature.},
doi = {10.1061/jtepbs.0000384},
journal = {Journal of Transportation Engineering, Part A: Systems},
number = 8,
volume = 146,
place = {United States},
year = {Sat Aug 01 00:00:00 EDT 2020},
month = {Sat Aug 01 00:00:00 EDT 2020}
}
Web of Science
Works referenced in this record:
Dynamic near-term traffic flow prediction: system-oriented approach based on past experiences
journal, January 2012
- Chang, H.; Lee, Y.; Yoon, B.
- IET Intelligent Transport Systems, Vol. 6, Issue 3
Traffic predictive control from low-rank structure
journal, March 2017
- Coogan, Samuel; Flores, Christopher; Varaiya, Pravin
- Transportation Research Part B: Methodological, Vol. 97
Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting
journal, November 2020
- Cui, Zhiyong; Henrickson, Kristian; Ke, Ruimin
- IEEE Transactions on Intelligent Transportation Systems, Vol. 21, Issue 11
Nonparametric Regression and Short‐Term Freeway Traffic Forecasting
journal, March 1991
- Davis, Gary A.; Nihan, Nancy L.
- Journal of Transportation Engineering, Vol. 117, Issue 2
Travel time prediction with LSTM neural network
conference, November 2016
- Duan, Yanjie; L. V., Yisheng; Wang, Fei-Yue
- 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC)
LSTM: A Search Space Odyssey
journal, October 2017
- Greff, Klaus; Srivastava, Rupesh K.; Koutnik, Jan
- IEEE Transactions on Neural Networks and Learning Systems, Vol. 28, Issue 10
Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification
journal, June 2014
- Guo, Jianhua; Huang, Wei; Williams, Billy M.
- Transportation Research Part C: Emerging Technologies, Vol. 43
Long Short-Term Memory
journal, November 1997
- Hochreiter, Sepp; Schmidhuber, Jürgen
- Neural Computation, Vol. 9, Issue 8
Supervised Weighting-Online Learning Algorithm for Short-Term Traffic Flow Prediction
journal, December 2013
- Jeong, Young-Seon; Byon, Young-Ji; Castro-Neto, Manoel Mendonca
- IEEE Transactions on Intelligent Transportation Systems, Vol. 14, Issue 4
Traffic Flow Prediction with Rainfall Impact Using a Deep Learning Method
journal, January 2017
- Jia, Yuhan; Wu, Jianping; Xu, Ming
- Journal of Advanced Transportation, Vol. 2017
Forecasting Traffic Flow Conditions in an Urban Network: Comparison of Multivariate and Univariate Approaches
journal, January 2003
- Kamarianakis, Yiannis; Prastacos, Poulicos
- Transportation Research Record: Journal of the Transportation Research Board, Vol. 1857, Issue 1
Two-Stream Multi-Channel Convolutional Neural Network for Multi-Lane Traffic Speed Prediction Considering Traffic Volume Impact
journal, March 2020
- Ke, Ruimin; Li, Wan; Cui, Zhiyong
- Transportation Research Record: Journal of the Transportation Research Board, Vol. 2674, Issue 4
Real-Time Traffic Flow Parameter Estimation From UAV Video Based on Ensemble Classifier and Optical Flow
journal, January 2019
- Ke, Ruimin; Li, Zhibin; Tang, Jinjun
- IEEE Transactions on Intelligent Transportation Systems, Vol. 20, Issue 1
Deep learning in fluid dynamics
journal, January 2017
- Kutz, J. Nathan
- Journal of Fluid Mechanics, Vol. 814
Application of Subset Autoregressive Integrated Moving Average Model for Short-Term Freeway Traffic Volume Forecasting
journal, January 1999
- Lee, Sangsoo; Fambro, Daniel B.
- Transportation Research Record: Journal of the Transportation Research Board, Vol. 1678, Issue 1
Traffic signal timing optimization in connected vehicles environment
conference, June 2017
- Li, Wan; Ban, Xuegang Jeff
- 2017 IEEE Intelligent Vehicles Symposium (IV)
Connected Vehicles Based Traffic Signal Timing Optimization
journal, December 2019
- Li, Wan; Ban, Xuegang
- IEEE Transactions on Intelligent Transportation Systems, Vol. 20, Issue 12
Short-term traffic state prediction from latent structures: Accuracy vs. efficiency
journal, February 2020
- Li, Wan; Wang, Jingxing; Fan, Rong
- Transportation Research Part C: Emerging Technologies, Vol. 111
Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction
journal, April 2017
- Ma, Xiaolei; Dai, Zhuang; He, Zhengbing
- Sensors, Vol. 17, Issue 4
Adaptive Kalman filtering for multi-step ahead traffic flow prediction
conference, June 2013
- Ojeda, Luis Leon; Kibangou, Alain Y.; de Wit, Carlos Canudas
- 2013 American Control Conference (ACC)
Deep learning for short-term traffic flow prediction
journal, June 2017
- Polson, Nicholas G.; Sokolov, Vadim O.
- Transportation Research Part C: Emerging Technologies, Vol. 79
A Bayesian Network Approach to Traffic Flow Forecasting
journal, March 2006
- Sun, S.; Zhang, C.; Yu, G.
- IEEE Transactions on Intelligent Transportation Systems, Vol. 7, Issue 1
Urban Freeway Traffic Flow Prediction: Application of Seasonal Autoregressive Integrated Moving Average and Exponential Smoothing Models
journal, January 1998
- Williams, Billy M.; Durvasula, Priya K.; Brown, Donald E.
- Transportation Research Record: Journal of the Transportation Research Board, Vol. 1644, Issue 1
A hybrid deep learning based traffic flow prediction method and its understanding
journal, May 2018
- Wu, Yuankai; Tan, Huachun; Qin, Lingqiao
- Transportation Research Part C: Emerging Technologies, Vol. 90
Short-Term Traffic Volume Forecasting Using Kalman Filter with Discrete Wavelet Decomposition
journal, July 2007
- Xie, Yuanchang; Zhang, Yunlong; Ye, Zhirui
- Computer-Aided Civil and Infrastructure Engineering, Vol. 22, Issue 5