Origin-destination Flow Prediction with Vehicle Trajectory Data and Semi-supervised Recurrent Neural Network

Origin-Destination (OD) flow data is an important instrument for traffic study and management. So far traditional ways like surveys or detectors are costly and only give limited availability of OD flows. Various statistical and stochastic models for OD flow estimation and prediction based on limited link volume data or automatic vehicle identification (AVI) data have been developed. However, smartphone-generated trajectory data has not been as much leveraged in this field, though the usage of smartphones in traveling is emerging in recent years. In this paper, we propose a semi-supervised deep learning based model that appropriately combines both AVI and smartphone trajectory data during training and is able to generate predictions of OD flows in an urban network solely based on the smartphone trajectory data at inference time. Our model can provide OD estimation and prediction services on larger spatial areas beyond the limited spatial coverage of AVI data. Tests of our model using real data have shown promising results, compared with an AVI input-dependent Kalman filter model. Potentially, our model can easily be embedded to a trajectory collecting platform and generate continuous real-time OD flow predictions online.

[1]  Enrique Castillo,et al.  Trip matrix and path flow reconstruction and estimation based on plate scanning and link observations , 2008 .

[2]  Kalidas Ashok,et al.  DYNAMIC ORIGIN-DESTINATION MATRIX ESTIMATION AND PREDICTION FOR REAL- TIME TRAFFIC MANAGEMENT SYSTEMS , 1993 .

[3]  Henk J van Zuylen,et al.  The most likely trip matrix estimated from traffic counts , 1980 .

[4]  Yang Lu,et al.  Origin-Destination Estimation Using Probe Vehicle Trajectory and Link Counts , 2017 .

[5]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[6]  Carlos Canudas de Wit,et al.  Adaptive Kalman filtering for multi-step ahead traffic flow prediction , 2013, 2013 American Control Conference.

[7]  Liang Liu,et al.  Estimating Origin-Destination Flows Using Mobile Phone Location Data , 2011, IEEE Pervasive Computing.

[8]  Anthony Chen,et al.  Norm approximation method for handling traffic count inconsistencies in path flow estimator , 2009 .

[9]  Melvin J. Hinich,et al.  Time Series Analysis by State Space Methods , 2001 .

[10]  Limin Jia,et al.  Real-time road traffic state prediction based on ARIMA and Kalman filter , 2017, Frontiers of Information Technology & Electronic Engineering.

[11]  Qiang Meng,et al.  Short-time traffic flow prediction with ARIMA-GARCH model , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[12]  Zhenbo Lu,et al.  A Kalman filter approach to dynamic OD flow estimation for urban road networks using multi‐sensor data , 2015 .

[13]  M. Kendall.  A NEW MEASURE OF RANK CORRELATION , 1938 .

[14]  Yan Yang,et al.  DeepSTCL: A Deep Spatio-temporal ConvLSTM for Travel Demand Prediction , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

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

[16]  Jian Sun,et al.  Examples of Validating an Adaptive Kalman Filter Model for Short-Term Traffic Flow Prediction , 2012 .

[17]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[18]  Hao Yang,et al.  A hybrid model based on Kalman Filter and neutral network for traffic prediction , 2012, 2012 IEEE 2nd International Conference on Cloud Computing and Intelligence Systems.

[19]  M. Bell.  THE ESTIMATION OF ORIGIN-DESTINATION MATRICES BY CONSTRAINED GENERALISED LEAST SQUARES , 1991 .

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

[21]  Xiaohui Yu,et al.  A Plane Moving Average Algorithm for Short-Term Traffic Flow Prediction , 2015, PAKDD.

[22]  Haris N. Koutsopoulos,et al.  Incorporating Automated Vehicle Identification Data into Origin-Destination Estimation , 2004 .

[23]  Hani S. Mahmassani,et al.  Dynamic origin-destination demand estimation using automatic vehicle identification data , 2006, IEEE Transactions on Intelligent Transportation Systems.

[24]  Pu Wang,et al.  Development of origin–destination matrices using mobile phone call data , 2014 .

[25]  Michel Bierlaire,et al.  An Efficient Algorithm for Real-Time Estimation and Prediction of Dynamic OD Tables , 2004, Oper. Res..

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

[27]  W. Kruskal.  Ordinal Measures of Association , 1958 .

[28]  Hai Yang,et al.  The equilibrium-based origin-destination matrix estimation problem , 1994 .

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

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

[31]  Zoubin Ghahramani,et al.  Learning from labeled and unlabeled data with label propagation , 2002 .

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

[33]  Hai Yang.  Heuristic algorithms for the bilevel origin-destination matrix estimation problem , 1995 .

[34]  Toshiyuki Yamamoto,et al.  Bilevel Generalized Least Squares Estimation of Dynamic Origin–Destination Matrix for Urban Network with Probe Vehicle Data , 2013 .

[35]  Hui Zhao,et al.  Estimation of Time-Varying OD Demands Incorporating FCD and RTMS Data , 2010 .

[36]  S. Eisenman,et al.  Using probe data to estimate OD matrices , 2004, Proceedings. The 7th International IEEE Conference on Intelligent Transportation Systems (IEEE Cat. No.04TH8749).

[37]  Wei Xu,et al.  DeepTransport: Learning Spatial-Temporal Dependency for Traffic Condition Forecasting , 2017, 2018 International Joint Conference on Neural Networks (IJCNN).

[38]  Lorenzo Mussone,et al.  A Neural Network Approach to Motorway OD Matrix Estimation from Loop Counts , 2010 .