Coupled application of deep learning model and quantile regression for travel time and its interval estimation using data in different dimensions

Abstract The rapid development of sensing and computing methods and their application to transportation engineering in recent years provide us data support to traffic flow prediction. However, the travel time prediction is still a complex and difficult task in the intelligent transportation system because of its nonlinear and nonstationary characteristics. In this study, a hybrid model coupling the deep learning model and the quantile regression (QR) has been proposed to achieve the deterministic and probabilistic travel time prediction. To consider multiple correlations of the traffic flow, a spatial–temporal state-space matrix has been developed. Then, a novel deep belief network stacked by several Gaussian Bernoulli Restricted Boltzmann Machine (GBRBM) to extract important features and a regression layer to finish the prediction were developed. Moreover, to strengthen the reliability of results, the QR was applied to generate a prediction interval. Using real-world data sets, the proposed hybrid model was evaluated and contrasted with several benchmark models. The results show the deep learning model outperform the shallow learning model. The prediction interval providing by QR is better than that provided by the traditional method. It indicates that our proposed hybrid model can obtain a more perfect and reliable prediction for travel time which is meaningful to the advanced traveler information system.

[1]  Haiying Li,et al.  Short-term passenger flow prediction under passenger flow control using a dynamic radial basis function network , 2019, Appl. Soft Comput..

[2]  Wenqi Lu,et al.  An Improved Bayesian Combination Model for Short-Term Traffic Prediction With Deep Learning , 2020, IEEE Transactions on Intelligent Transportation Systems.

[3]  Wanli Min,et al.  Real-time road traffic prediction with spatio-temporal correlations , 2011 .

[4]  Yitao Liu,et al.  Deep belief network based deterministic and probabilistic wind speed forecasting approach , 2016 .

[5]  Bin Ran,et al.  Short-to-medium Term Passenger Flow Forecasting for Metro Stations using a Hybrid Model , 2017, KSCE Journal of Civil Engineering.

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

[7]  Nikolay Laptev,et al.  Deep and Confident Prediction for Time Series at Uber , 2017, 2017 IEEE International Conference on Data Mining Workshops (ICDMW).

[8]  Yajie Zou,et al.  A space–time diurnal method for short-term freeway travel time prediction , 2014 .

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

[10]  Bin Ran,et al.  Short‐term highway traffic flow prediction based on a hybrid strategy considering temporal–spatial information , 2016 .

[11]  Eleni I. Vlahogianni,et al.  Statistical methods versus neural networks in transportation research: Differences, similarities and some insights , 2011 .

[12]  Yanru Zhang,et al.  A gradient boosting method to improve travel time prediction , 2015 .

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

[14]  Eleni I. Vlahogianni,et al.  Memory properties and fractional integration in transportation time-series , 2009 .

[15]  Haibo Chen,et al.  CHARACTERISING THE TEMPORAL VARIATIONS OF GROUND-LEVEL OZONE AND ITS RELATIONSHIP WITH TRAFFIC-RELATED AIR POLLUTANTS IN THE UNITED KINGDOM: A QUANTILE REGRESSION APPROACH , 2014 .

[16]  Asad J. Khattak,et al.  Modeling Traffic Incident Duration Using Quantile Regression , 2016 .

[17]  Chuan Ding,et al.  Prioritizing Influential Factors for Freeway Incident Clearance Time Prediction Using the Gradient Boosting Decision Trees Method , 2017, IEEE Transactions on Intelligent Transportation Systems.

[18]  Tapani Raiko,et al.  Gaussian-Bernoulli deep Boltzmann machine , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[19]  J. W. C. van Lint,et al.  Online Learning Solutions for Freeway Travel Time Prediction , 2008, IEEE Transactions on Intelligent Transportation Systems.

[20]  Kung-Sik Chan,et al.  Time Series Analysis: With Applications in R , 2010 .

[21]  Rung-Ching Chen,et al.  A novel passenger flow prediction model using deep learning methods , 2017 .

[22]  Xiaolei Ma,et al.  Probabilistic Prediction of Bus Headway Using Relevance Vector Machine Regression , 2017, IEEE Transactions on Intelligent Transportation Systems.

[23]  Bin Ran,et al.  Day-ahead traffic flow forecasting based on a deep belief network optimized by the multi-objective particle swarm algorithm , 2019, Knowl. Based Syst..

[24]  L. Vanajakshi,et al.  Support Vector Machine Technique for the Short Term Prediction of Travel Time , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[25]  Jianhua Guo,et al.  Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification , 2014 .

[26]  Jianping Wu,et al.  Rainfall-integrated traffic speed prediction using deep learning method , 2017 .

[27]  Simon Washington,et al.  Applying quantile regression for modeling equivalent property damage only crashes to identify accident blackspots. , 2014, Accident; analysis and prevention.

[28]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[29]  Rob J Hyndman,et al.  Automatic Time Series Forecasting: The forecast Package for R , 2008 .

[30]  Eleni I. Vlahogianni,et al.  Statistical methods for detecting nonlinearity and non-stationarity in univariate short-term time-series of traffic volume , 2006 .

[31]  Adel W. Sadek,et al.  Quantifying uncertainty in short-term traffic prediction and its application to optimal staffing plan development , 2018, Transportation Research Part C: Emerging Technologies.

[32]  Bin Ran,et al.  A hybrid deep learning based traffic flow prediction method and its understanding , 2018 .

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

[34]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

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

[36]  Yonggang Wang,et al.  Estimation of missing values in heterogeneous traffic data: Application of multimodal deep learning model , 2020, Knowl. Based Syst..

[37]  Bin Ran,et al.  Robust and flexible strategy for missing data imputation in intelligent transportation system , 2017 .

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

[39]  Bin Ran,et al.  Travel time prediction for highway network based on the ensemble empirical mode decomposition and random vector functional link network , 2018, Appl. Soft Comput..

[40]  Xiao Qin,et al.  Identifying crash-prone locations with quantile regression. , 2010, Accident; analysis and prevention.