A tensor-based Bayesian probabilistic model for citywide personalized travel time estimation

Abstract Urban travel time information is of great importance for many levels of traffic management and operation. This paper develops a tensor-based Bayesian probabilistic model for citywide and personalized travel time estimation, using the large-scale and sparse GPS trajectories generated by taxicabs. Combined with the knowledge learned from historical trajectories, travel times of different drivers on all road segments in some time slots are modeled with a 3-order tensor. This tensor-based modeling approach incorporates both the spatial correlation between different road segments and the person-specific variation between different drivers, as well as the coarse-grain temporal correlation between recent and historical traffic conditions and the fine-grain temporal correlation between different time slots. To account for the variability caused by the intrinsic uncertainties in urban road network, each travel time entry in the built tensor is treated as a variable following a log-normal distribution. With the help of the fully Bayesian treatment, the model achieves automatic hyper-parameter tuning and model complexity controlling, and therefore the problem of over-fitting is prevented even when the used data is large-scale and sparse. The proposed model is applied to a real case study on the citywide road network of Beijing, China, using the large-scale and sparse GPS trajectories collected from over 32,670 taxicabs for a period of two months. Empirical results of extensive experiments demonstrate that the proposed model provides an effective and robust approach for urban travel time estimation and outperforms the considered competing methods.

[1]  Mickael Beaud,et al.  The impact of travel time variability and travelers’ risk attitudes on the values of time and reliability , 2016 .

[2]  Kay W. Axhausen,et al.  Understanding urban mobility patterns with a probabilistic tensor factorization framework , 2016 .

[3]  Haris N. Koutsopoulos,et al.  Path inference from sparse floating car data for urban networks , 2013 .

[4]  John Hourdos,et al.  Probe vehicle based real-time traffic monitoring on urban roadways , 2014 .

[5]  Yu Zheng,et al.  Trajectory Data Mining , 2015, ACM Trans. Intell. Syst. Technol..

[6]  Lu Yu,et al.  TIIREC: A tensor approach for tag-driven item recommendation with sparse user generated content , 2017, Inf. Sci..

[7]  Toshiyuki Yamamoto,et al.  Development of map matching algorithm for low frequency probe data , 2012 .

[8]  Ruimin Li,et al.  Incorporating uncertainty into short-term travel time predictions , 2011 .

[9]  Guizhen Yu,et al.  Probe data-driven travel time forecasting for urban expressways by matching similar spatiotemporal traffic patterns , 2017 .

[10]  Liping Fu,et al.  Decomposing Travel Times Measured by Probe-based Traffic Monitoring Systems to Individual Road Segments , 2008 .

[11]  Min Chen,et al.  A copula-based approach for estimating the travel time reliability of urban arterial , 2017 .

[12]  Erik Jenelius,et al.  Travel time estimation from sparse floating car data with consistent path inference: A fixed point approach , 2017 .

[13]  Xing Xie,et al.  Learning travel recommendations from user-generated GPS traces , 2011, TIST.

[14]  Fangfang Zheng,et al.  Urban link travel time estimation based on sparse probe vehicle data , 2013 .

[15]  Tamara G. Kolda,et al.  Scalable Tensor Factorizations for Incomplete Data , 2010, ArXiv.

[16]  Ali Taylan Cemgil,et al.  Algorithms for probabilistic latent tensor factorization , 2012, Signal Process..

[17]  Samiul Hasan,et al.  Modeling of Travel Time Variations on Urban Links in London , 2011 .

[18]  Mahmoud Mesbah,et al.  Estimation of trip travel time distribution using a generalized Markov chain approach , 2017 .

[19]  Wen-Long Jin,et al.  A modified Cell Transmission Model with realistic queue discharge features at signalized intersections , 2015 .

[20]  S. C. Wirasinghe,et al.  Analysis of bus travel time distributions for varying horizons and real-time applications , 2018 .

[21]  Hilmi Berk Celikoglu,et al.  Flow-Based Freeway Travel-Time Estimation: A Comparative Evaluation Within Dynamic Path Loading , 2013, IEEE Transactions on Intelligent Transportation Systems.

[22]  Hongtao Wang,et al.  Context-aware personalized path inference from large-scale GPS snippets , 2018, Expert Syst. Appl..

[23]  Guangdong Feng,et al.  A Tensor Based Method for Missing Traffic Data Completion , 2013 .

[24]  Xin Wang,et al.  Personalized travel route recommendation using collaborative filtering based on GPS trajectories , 2018, Int. J. Digit. Earth.

[25]  Nikolas Geroliminis,et al.  Dynamics of heterogeneity in urban networks: aggregated traffic modeling and hierarchical control , 2015 .

[26]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[27]  Haris N. Koutsopoulos,et al.  Probe vehicle data sampled by time or space: Consistent travel time allocation and estimation , 2015 .

[28]  Bin Ran,et al.  Freeway Short-Term Travel Time Prediction Based on Dynamic Tensor Completion , 2015 .

[29]  Theo A. Arentze,et al.  Adaptive Personalized Travel Information Systems: A Bayesian Method to Learn Users' Personal Preferences in Multimodal Transport Networks , 2013, IEEE Transactions on Intelligent Transportation Systems.

[30]  Wen Wang,et al.  Link travel time inference using entry/exit information of trips on a network , 2015 .

[31]  Satish V. Ukkusuri,et al.  Urban Link Travel Time Estimation Using Large-scale Taxi Data with Partial Information , 2013 .

[32]  Fangfang Zheng,et al.  Modeling Variability of Urban Travel Times by Analyzing Delay Distribution for Multiple Signalized Intersections , 2011 .

[33]  Xuesong Zhou,et al.  Personalized real-time traffic information provision: Agent-based optimization model and solution framework , 2016 .

[34]  Eric Horvitz,et al.  Predicting Travel Time Reliability using Mobile Phone GPS Data , 2017 .

[35]  Mingming Jiang,et al.  A Time-Aware Personalized Point-of-Interest Recommendation via High-Order Tensor Factorization , 2017, ACM Trans. Inf. Syst..

[36]  A. Kibangou,et al.  Traffic data imputation via tensor completion based on soft thresholding of Tucker core , 2017 .

[37]  Haris N. Koutsopoulos,et al.  Travel time estimation for urban road networks using low frequency probe vehicle data , 2013, Transportation Research Part B: Methodological.

[38]  Fangfang Zheng,et al.  Model for Predicting Distribution of Link Travel Times for Urban Signalized Roads , 2012 .

[39]  Alexandre M. Bayen,et al.  The Path Inference Filter: Model-Based Low-Latency Map Matching of Probe Vehicle Data , 2014, WAFR.

[40]  Vikash V. Gayah,et al.  Continuum signalized junction model for dynamic traffic networks: Offset, spillback, and multiple signal phases , 2015 .

[41]  Fangfang Zheng,et al.  Uncertainty and Predictability of Urban Link Travel Time , 2010 .

[42]  Ruslan Salakhutdinov,et al.  Probabilistic Matrix Factorization , 2007, NIPS.

[43]  Henk J van Zuylen,et al.  A Methodological Framework of Travel Time Distribution Estimation for Urban Signalized Arterial Roads , 2017, Transp. Sci..