Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting

Traffic forecasting influences various intelligent transportation system (ITS) services and is of great significance for user experience as well as urban traffic control. It is challenging due to the fact that the road network contains complex and time-varying spatial-temporal dependencies. Recently, deep learning based methods have achieved promising results by adopting graph convolutional network (GCN) to extract the spatial correlations and recurrent neural network (RNN) to capture the temporal dependencies. However, the existing methods often construct the graph only based on road network connectivity, which limits the interaction between roads. In this work, we propose Geographic and Long term Temporal Graph Convolutional Recurrent Neural Network (GLT-GCRNN), a novel framework for traffic forecasting that learns the rich interactions between roads sharing similar geographic or longterm temporal patterns. Extensive experiments on a real-world traffic state dataset validate the effectiveness of our method by showing that GLT-GCRNN outperforms the state-of-the-art methods in terms of different metrics.

[1]  Mathias Niepert,et al.  Learning Convolutional Neural Networks for Graphs , 2016, ICML.

[2]  Joan Bruna,et al.  Deep Convolutional Networks on Graph-Structured Data , 2015, ArXiv.

[3]  Shengxue He Will a higher free-flow speed lead us to a less congested freeway? , 2016 .

[4]  Gary A. Davis,et al.  Nonparametric Regression and Short‐Term Freeway Traffic Forecasting , 1991 .

[5]  Zheng Wang,et al.  Learning to Estimate the Travel Time , 2018, KDD.

[6]  Zhaohui Wu,et al.  Intelligent Transportation Systems , 2006, IEEE Pervasive Computing.

[7]  Billy M. Williams,et al.  Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results , 2003, Journal of Transportation Engineering.

[8]  Tomaso A. Poggio,et al.  Regularization Networks and Support Vector Machines , 2000, Adv. Comput. Math..

[9]  Shane G. Henderson,et al.  Travel time estimation for ambulances using Bayesian data augmentation , 2013, 1312.1873.

[10]  Jianping Wu,et al.  Traffic speed prediction using deep learning method , 2016, 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC).

[11]  Mascha C. van der Voort,et al.  Combining kohonen maps with arima time series models to forecast traffic flow , 1996 .

[12]  Byoung-Jo Yoon,et al.  Dynamic near-term traffic flow prediction: system- oriented approach based on past experiences , 2012 .

[13]  C. Daganzo THE CELL TRANSMISSION MODEL.. , 1994 .

[14]  Jian Li,et al.  Big data‐driven machine learning‐enabled traffic flow prediction , 2018, Trans. Emerg. Telecommun. Technol..

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

[16]  Shijie Li,et al.  Deep Spatial–Temporal 3D Convolutional Neural Networks for Traffic Data Forecasting , 2019, IEEE Transactions on Intelligent Transportation Systems.

[17]  Yinhai Wang,et al.  Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting , 2018, IEEE Transactions on Intelligent Transportation Systems.

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

[19]  Yoshua Bengio,et al.  Exploring Strategies for Training Deep Neural Networks , 2009, J. Mach. Learn. Res..

[20]  Yang Du,et al.  Finding Fastest Paths on A Road Network with Speed Patterns , 2006, 22nd International Conference on Data Engineering (ICDE'06).

[21]  Hashem R Al-Masaeid,et al.  Short-Term Prediction of Traffic Volume in Urban Arterials , 1995 .

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

[23]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[24]  Yunpeng Wang,et al.  Long short-term memory neural network for traffic speed prediction using remote microwave sensor data , 2015 .

[25]  Xiaocheng Li,et al.  Graph Convolution: A High-Order and Adaptive Approach , 2017, 1706.09916.

[26]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

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

[28]  J.L. Martins de Carvalho,et al.  Towards the development of intelligent transportation systems , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

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

[30]  Ning Feng,et al.  Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting , 2019, AAAI.

[31]  Ugur Demiryurek,et al.  Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting , 2017, SDM.

[32]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[33]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[34]  Casper J. Albers,et al.  Multivariate forecasting of road traffic flows in the presence of heteroscedasticity and measurement errors , 2013 .

[35]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

[36]  Dafang Zhang,et al.  Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting , 2019, AAAI.

[37]  Yong Wang,et al.  Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction , 2017, Sensors.

[38]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[39]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[40]  Xianfeng Tang,et al.  Modeling Spatial-Temporal Dynamics for Traffic Prediction , 2018, ArXiv.

[41]  Zhanxing Zhu,et al.  3D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecasting , 2019, ArXiv.

[42]  Wei-Chiang Hong,et al.  Traffic flow forecasting by seasonal SVR with chaotic simulated annealing algorithm , 2011, Neurocomputing.

[43]  Fei-Yue Wang,et al.  Data-Driven Intelligent Transportation Systems: A Survey , 2011, IEEE Transactions on Intelligent Transportation Systems.

[44]  Jiahui Wang,et al.  Vector Autoregressive Models for Multivariate Time Series , 2003 .

[45]  Yu Liu,et al.  T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction , 2018, IEEE Transactions on Intelligent Transportation Systems.

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

[47]  Xuan Song,et al.  Learning Deep Representation from Big and Heterogeneous Data for Traffic Accident Inference , 2016, AAAI.

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

[49]  Wenhao Huang,et al.  Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning , 2014, IEEE Transactions on Intelligent Transportation Systems.