A hybrid prediction approach for road tunnel traffic based on spatial-temporary data fusion

In this paper, we propose a hybrid prediction model based on spatial-temporal data fusion to predict future tunnel traffic. Our approach consists of a local predictor, a global predictor, an outlier predictor, and a prediction integrator. Firstly, the local predictor forecast tunnel traffic based on the collected local data. It is more concerned with the historical and future traffic conditions, that is, the temporal correlation. Then, the global predictor uses data collected from peripheral road segments to predict tunnel volume, which models the spatial correlation based on a deep learning network. Thirdly, the prediction integrator dynamically integrates the prediction results of local and global predictors on the basis of the current weather conditions. In addition, we detect the abnormal traffic volume for training an individual outlier predictor. Finally, we integrate it with the output of the prediction integrator and accumulate the current tunnel traffic volume to calculate final prediction results. In our experiments, we collected the multisource urban-awareness data from Shanghai to evaluate the proposed hybrid prediction model. Our approach is obviously superior to the baseline when dealing with the general condition. The MREs of 30 min and 60 min tunnel traffic volume prediction are less than 6.5%. In addition, the outlier predictor of the proposed model significantly enhances the ability to predict the abnormal tunnel traffic under extreme weather conditions or unexpected traffic accidents.

[1]  Dong Yu,et al.  Deep Learning: Methods and Applications , 2014, Found. Trends Signal Process..

[2]  Lei Shu,et al.  Traffic Flow Prediction with Big Data: A Deep Learning based Time Series Model , 2017, INFOCOM 2017.

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

[4]  Manoranjan Parida,et al.  Short Term Traffic Flow Prediction for a Non Urban Highway Using Artificial Neural Network , 2013 .

[5]  D. Massart,et al.  The Mahalanobis distance , 2000 .

[6]  Rasmus Berg Palm,et al.  Prediction as a candidate for learning deep hierarchical models of data , 2012 .

[7]  Xing Xie,et al.  Discovering spatio-temporal causal interactions in traffic data streams , 2011, KDD.

[8]  Sanghoon Bae,et al.  Deep Neural Networks for traffic flow prediction , 2017, 2017 IEEE International Conference on Big Data and Smart Computing (BigComp).

[9]  Lei Shu,et al.  Poster abstract: Traffic flow prediction with big data: A deep learning based time series model , 2017, 2017 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[10]  Tharam S. Dillon,et al.  Optimized Structure of the Traffic Flow Forecasting Model With a Deep Learning Approach , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[11]  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.

[12]  Ridha Soua,et al.  Improving Traffic Flow Prediction With Weather Information in Connected Cars: A Deep Learning Approach , 2016, IEEE Transactions on Vehicular Technology.

[13]  Bin Ran,et al.  Online Recursive Algorithm for Short-Term Traffic Prediction , 2004 .

[14]  Huachun Tan,et al.  Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework , 2016, ArXiv.

[15]  R. Lewis.  An Introduction to Classification and Regression Tree (CART) Analysis , 2000 .

[16]  Nicholas G. Polson,et al.  Deep learning for short-term traffic flow prediction , 2016, 1604.04527.

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

[18]  Yong Yu,et al.  Inferring gas consumption and pollution emission of vehicles throughout a city , 2014, KDD.

[19]  Thomas Hofmann,et al.  Greedy Layer-Wise Training of Deep Networks , 2007 .

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

[21]  Bin Ran,et al.  A Comparison of Traffic Flow Prediction Methods Based on DBN , 2016 .