Optimized Graph Convolution Recurrent Neural Network for Traffic Prediction

Traffic prediction is a core problem in the intelligent transportation system and has broad applications in the transportation management and planning, and the main challenge of this field is how to efficiently explore the spatial and temporal information of traffic data. Recently, various deep learning methods, such as convolution neural network (CNN), have shown promising performance in traffic prediction. However, it samples traffic data in regular grids as the input of CNN, thus it destroys the spatial structure of the road network. In this paper, we introduce a graph network and propose an optimized graph convolution recurrent neural network for traffic prediction, in which the spatial information of the road network is represented as a graph. Additionally, distinguishing with most current methods using a simple and empirical spatial graph, the proposed method learns an optimized graph through a data-driven way in the training phase, which reveals the latent relationship among the road segments from the traffic data. Lastly, the proposed method is evaluated on three real-world case studies, and the experimental results show that the proposed method outperforms state-of-the-art traffic prediction methods.

[1]  Abien Fred Agarap.  A Neural Network Architecture Combining Gated Recurrent Unit (GRU) and Support Vector Machine (SVM) for Intrusion Detection in Network Traffic Data , 2017, ICMLC.

[2]  Alexandre M. Bayen,et al.  An ensemble Kalman filtering approach to highway traffic estimation using GPS enabled mobile devices , 2008, 2008 47th IEEE Conference on Decision and Control.

[3]  Serge P. Hoogendoorn,et al.  Real-Time Lagrangian Traffic State Estimator for Freeways , 2012, IEEE Transactions on Intelligent Transportation Systems.

[4]  Fusco Gaetano,et al.  A comparative analysis of implicit models for real-time short-term traffic predictions , 2015 .

[5]  Haris N. Koutsopoulos,et al.  Dynamic data-driven local traffic state estimation and prediction , 2013 .

[6]  Xavier Bresson,et al.  Structured Sequence Modeling with Graph Convolutional Recurrent Networks , 2016, ICONIP.

[7]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[8]  Eleni I. Vlahogianni,et al.  Short-term traffic forecasting: Where we are and where we’re going , 2014 .

[9]  Muhammad Tayyab Asif,et al.  Low-Dimensional Models for Compressed Sensing and Prediction of Large-Scale Traffic Data , 2015, IEEE Transactions on Intelligent Transportation Systems.

[10]  Yi Li,et al.  Instance-Sensitive Fully Convolutional Networks , 2016, ECCV.

[11]  L. H. Immers,et al.  An Extended Kalman Filter Application for Traffic State Estimation Using CTM with Implicit Mode Switching and Dynamic Parameters , 2007, 2007 IEEE Intelligent Transportation Systems Conference.

[12]  Lorenzo Mussone,et al.  NEURAL-NETWORK MODELS FOR CLASSIFICATION AND FORECASTING OF FREEWAY TRAFFIC FLOW STABILITY , 1994 .

[13]  Markos Papageorgiou,et al.  RENAISSANCE – A Unified Macroscopic Model-Based Approach to Real-Time Freeway Network Traffic Surveillance , 2006 .

[14]  Pravin Varaiya,et al.  Freeway Performance Measurement System: Mining Loop Detector Data , 2001 .

[15]  U. Feige,et al.  Spectral Graph Theory , 2015 .

[16]  Yunpeng Wang,et al.  A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting , 2016 .

[17]  Sunu Wibirama,et al.  Wart treatment method selection using AdaBoost with random forests as a weak learner , 2018 .

[18]  Edmund S. Yu,et al.  Traffic prediction using neural networks , 1993, Proceedings of GLOBECOM '93. IEEE Global Telecommunications Conference.

[19]  Markos Papageorgiou,et al.  Real-time freeway traffic state estimation based on extended Kalman filter: a general approach , 2005 .

[20]  Peter C. Nelson,et al.  PREDICTING TRAFFIC CONGESTION USING RECURRENT NEURAL NETWORKS , 2002 .

[21]  Bin Ran,et al.  Fuzzy-Neural Network Traffic Prediction Framework with Wavelet Decomposition , 2003 .

[22]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[23]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[24]  Ashish Bhaskar,et al.  Real-time traffic state estimation in urban corridors from heterogeneous data , 2016 .

[25]  Serge P. Hoogendoorn,et al.  Network-Wide Traffic State Estimation Using Loop Detector and Floating Car Data , 2014, J. Intell. Transp. Syst..

[26]  Yang Wen,et al.  A dynamic traffic assignment model for highly congested urban networks , 2012 .

[27]  Alex Fout,et al.  Protein Interface Prediction using Graph Convolutional Networks , 2017, NIPS.

[28]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[29]  Billy M. Williams,et al.  Comparison of parametric and nonparametric models for traffic flow forecasting , 2002 .

[30]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[31]  Yu Zheng,et al.  Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction , 2016, AAAI.

[32]  D. T. Lee,et al.  Travel-time prediction with support vector regression , 2004, IEEE Transactions on Intelligent Transportation Systems.

[33]  Michel Bierlaire,et al.  DynaMIT: a simulation-based system for traffic prediction and guidance generation , 1998 .

[34]  Yann LeCun,et al.  Spectral Networks and Deep Locally Connected Networks on Graphs , 2014 .

[35]  Cyrus Shahabi,et al.  Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting , 2017, ICLR.

[36]  A. R. Cook,et al.  ANALYSIS OF FREEWAY TRAFFIC TIME-SERIES DATA BY USING BOX-JENKINS TECHNIQUES , 1979 .

[37]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

[38]  Yunpeng Wang,et al.  Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks , 2017, Sensors.

[39]  Zhanxing Zhu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017, IJCAI.

[40]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[41]  Xiaolei Li,et al.  Traffic Flow Forecasting by a Least Squares Support Vector Machine with a Fruit Fly Optimization Algorithm , 2016 .

[42]  Pierre Vandergheynst,et al.  Wavelets on Graphs via Spectral Graph Theory , 2009, ArXiv.

[43]  S. Tsukahara,et al.  Short-term traffic prediction using fuzzy c-means and cellular automata in a wide-area road network , 2005, Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005..

[44]  Fei Wu,et al.  Spatio-Temporal Graph Routing for Skeleton-Based Action Recognition , 2019, AAAI.

[45]  A. Bayen,et al.  A traffic model for velocity data assimilation , 2010 .

[46]  Alexandre M. Bayen,et al.  Arterial travel time forecast with streaming data: A hybrid approach of flow modeling and machine learning , 2012 .

[47]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[48]  H. J. Van Zuylen,et al.  Accurate freeway travel time prediction with state-space neural networks under missing data , 2005 .

[49]  Henk J. van Zuylen,et al.  Localized Extended Kalman Filter for Scalable Real-Time Traffic State Estimation , 2012, IEEE Transactions on Intelligent Transportation Systems.

[50]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[51]  Heng Wei,et al.  A novel work zone short-term vehicle-type specific traffic speed prediction model through the hybrid EMD–ARIMA framework , 2016 .