Similar articles

Abstract: The prediction of regional traffic flows is important for traffic control and management in an intelligent traffic system. With the help of deep neural networks, the convolutional neural network or residual neural network, which can be applied only to regular grids, is adopted to capture the spatial dependence for flow prediction. However, the obtained regions are always irregular considering the road network and administrative boundaries; thus, dividing the city into grids is inaccurate for prediction. In this paper, we propose a new model based on multi-graph convolutional network and gated recurrent unit (MGCN-GRU) to predict traffic flows for irregular regions. Specifically, we first construct heterogeneous inter-region graphs for a city to reflect the relationships among regions. In each graph, nodes represent the irregular regions and edges represent the relationship types between regions. Then, we propose a multi-graph convolutional network to fuse different inter-region graphs and additional attributes. The GRU is further used to capture the temporal dependence and to predict future traffic flows. Experimental results based on three real-world large-scale datasets (public bicycle system dataset, taxi dataset, and dockless bike-sharing dataset) show that our MGCN-GRU model outperforms a variety of existing methods.

基于多图卷积网络和门控循环单元的不规则区域交通流量预测

[1]Box GEP, Jenkins GM, Reinsel GC, 2015. Time Series Analysis: Forecasting and Control. John Wiley & Sons, New York, USA.

[2]Bruna J, Zaremba W, Szlam A, et al., 2014. Spectral networks and locally connected networks on graphs. Proc Int Conf on Learning Representations, p.1-14.

[3]Chai D, Wang LY, Yang Q, 2018. Bike flow prediction with multi-graph convolutional networks. Proc 26^th ACM SIGSPATIAL Int Conf on Advances in Geographic Information Systems, p.397-400.

[4]Chandra SR, Al-Deek H, 2009. Predictions of freeway traffic speeds and volumes using vector autoregressive models. J Intell Transp Syst, 13(2):53-72.

[5]Defferrard M, Bresson X, Vandergheynst P, 2016. Convolutional neural networks on graphs with fast localized spectral filtering. Proc 30^th Int Conf on Neural Information Processing Systems, p.3844-3852.

[6]Fu R, Zhang Z, Li L, 2016. Using LSTM and GRU neural network methods for traffic flow prediction. Proc 31^st Youth Academic Annual Conf of Chinese Association of Automation, p.324-328.

[7]Kaltenbrunner A, Meza R, Grivolla J, et al., 2010. Urban cycles and mobility patterns: exploring and predicting trends in a bicycle-based public transport system. Perv Mob Comput, 6(4):455-466.

[8]Kim Y, Wang P, Mihaylova L, 2019. Scalable learning with a structural recurrent neural network for short-term traffic prediction. IEEE Sens J, 19(23):11359-11366.

[9]Kipf TN, Welling M, 2017. Semi-supervised classification with graph convolutional networks. Proc 5^th Int Conf on Learning Representations, p.1-10.

[10]Li YG, Yu R, Shahabi C, et al., 2018. Diffusion convolutional recurrent neural network: data-driven traffic forecasting. Proc 6^th Int Conf on Learning Representations, p.1-10.

[11]Monti F, Bronstein MM, Bresson X, 2017. Geometric matrix completion with recurrent multi-graph neural networks. Proc 31^st Int Conf on Neural Information Processing Systems, p.3697-3707.

[12]Moreira-Matias L, Gama J, Ferreira M, et al., 2013. Predicting taxi–passenger demand using streaming data. IEEE Trans Intell Transp Syst, 14(3):1393-1402.

[13]Seo Y, Defferrard M, Vandergheynst P, et al., 2018. Structured sequence modeling with graph convolutional recurrent networks. Proc 25^th Int Conf on Neural Information, p.362-373.

[14]Tian YX, Pan L, 2015. Predicting short-term traffic flow by long short-term memory recurrent neural network. IEEE Int Conf on Smart City/SocialCom/SustainCom, p.153-158.

[15]Wang P, Kim Y, Vaci L, et al., 2018. Short-term traffic prediction with vicinity Gaussian process in the presence of missing data. Sensor Data Fusion: Trends, Solutions, Applications, p.1-6.

[16]Williams BM, Hoel LA, 2003. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results. J Transp Eng, 129(6):664-672.

[17]Yao HX, Wu F, Ke JT, et al., 2018. Deep multi-view spatial-temporal network for taxi demand prediction. Proc 32^nd AAAI Conf on Artificial Intelligence, p.2588-2595.

[18]Ying R, He RN, Chen KF, et al., 2018. Graph convolutional neural networks for web-scale recommender systems. Proc 24^th ACM SIGKDD Int Conf on Knowledge Discovery & Data Mining, p.974-983.

[19]Yoon JW, Pinelli F, Calabrese F, 2012. Cityride: a predictive bike sharing journey advisor. Proc 13^th Int Conf on Mobile Data Management, p.306-311.

[20]Yu B, Yin HT, Zhu ZX, 2018. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. Proc 27^th Int Joint Conf on Artificial Intelligence, p.1-7.

[21]Yu R, Li YG, Shahabi C, et al., 2017. Deep learning: a generic approach for extreme condition traffic forecasting. Proc SIAM Int Conf on Data Mining. p.777-785.

[22]Yuan NJ, Zheng Y, Xie X, et al., 2015. Discovering urban functional zones using latent activity trajectories. IEEE Trans Knowl Data Eng, 27(3):712-725.

[23]Zhang JB, Zheng Y, Qi DK, et al., 2016. DNN-based prediction model for spatio-temporal data. Proc 24^th ACM SIGSPATIAL Int Conf on Advances in Geographic Information Systems, p.92.

[24]Zhang JB, Zheng Y, Qi DK, et al., 2018. Predicting citywide crowd flows using deep spatio-temporal residual networks. Artif Intell, 259:147-166.

[25]Zhao L, Song YJ, Zhang C, et al., 2020. T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans Intell Transp Syst, 21(9):3848-3858.

[26]Zhu L, Yu FR, Wang YG, et al., 2019. Big data analytics in intelligent transportation systems: a survey. IEEE Trans Intell Transp Syst, 20(1):383-398.