Data-driven approach for solving the route choice problem with traveling backward behavior in congested metro systems

This study proposes a data-driven approach to understand traveling backward (TB) behavior while making a route choice in congested metros. First, TB behavior during route choice in overcrowded metros is defined and analyzed. Second, a hybrid model comprising three hierarchical Bayesian models is developed to describe the TB behavior. Third, a novel sampling method based on Hamiltonian dynamics is introduced to estimate the model parameters. Finally, a case study of Beijing metro is discussed to illustrate the effectiveness and robustness of the proposed model. The contributions of application of the proposed model to accurate demand assignment and passenger flow control for metro managers are demonstrated.

[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]  C. Graham,et al.  Introduction to Magnetic Materials , 1972 .

[3]  Steffi Pohl,et al.  A hierarchical latent response model for inferences about examinee engagement in terms of guessing and item-level non-response. , 2019, The British journal of mathematical and statistical psychology.

[4]  Lai Tu,et al.  Estimation of Passenger Route Choice Pattern Using Smart Card Data for Complex Metro Systems , 2016, IEEE Transactions on Intelligent Transportation Systems.

[5]  Bi Yu Chen,et al.  Efficient algorithm for finding k shortest paths based on re-optimization technique , 2020 .

[6]  Jiandong Zhao,et al.  Data-driven model for passenger route choice in urban metro network , 2019, Physica A: Statistical Mechanics and its Applications.

[7]  Wei Zhu,et al.  Empirical Analysis of Traveling Backwards and Passenger Flows Reassignment on a Metro Network with Automatic Fare Collection (AFC) Data and Train Diagram , 2018, Transportation Research Record: Journal of the Transportation Research Board.

[8]  Jian Hu,et al.  A Data-Driven Functionally Robust Approach for Simultaneous Pricing and Order Quantity Decisions with Unknown Demand Function , 2019, Oper. Res..

[9]  W. K. Hastings,et al.  Monte Carlo Sampling Methods Using Markov Chains and Their Applications , 1970 .

[10]  Gah-Yi Ban,et al.  The Data-Driven (s, S) Policy: Why You Can Have Confidence in Censored Demand Data , 2015 .

[11]  Kangning Zheng,et al.  Estimating metro passengers’ path choices by combining self-reported revealed preference and smart card data , 2018, Transportation Research Part C: Emerging Technologies.

[12]  Paul Schonfeld,et al.  Schedule-Based Rail Transit Path-Choice Estimation using Automatic Fare Collection Data , 2016 .

[13]  Nigel H. M. Wilson,et al.  A behavioural comparison of route choice on metro networks: Time, transfers, crowding, topology and socio-demographics , 2014 .

[14]  G. Björklund,et al.  Estimating policy values for in-vehicle comfort and crowding reduction in local public transport☆ , 2017 .

[15]  Hai Yang,et al.  Day-to-day evolution of departure time choice in stochastic capacity bottleneck models with bounded rationality and various information perceptions , 2019, Transportation Research Part E: Logistics and Transportation Review.

[16]  Haris N. Koutsopoulos,et al.  Inferring left behind passengers in congested metro systems from automated data , 2017 .

[17]  Chuan Ding,et al.  Parallel Architecture of Convolutional Bi-Directional LSTM Neural Networks for Network-Wide Metro Ridership Prediction , 2019, IEEE Transactions on Intelligent Transportation Systems.

[18]  Pan Shang,et al.  Integrating Lagrangian and Eulerian observations for passenger flow state estimation in an urban rail transit network: A space-time-state hyper network-based assignment approach , 2019, Transportation Research Part B: Methodological.

[19]  Ricardo Silva,et al.  Predicting traffic volumes and estimating the effects of shocks in massive transportation systems , 2015, Proceedings of the National Academy of Sciences.

[20]  Jianxin Wang,et al.  An intelligent logistics service system for enhancing dispatching operations in an IoT environment , 2020 .

[21]  Liping Xie,et al.  Learning the route choice behavior of subway passengers from AFC data , 2018, Expert Syst. Appl..

[22]  Husain Aljazzar,et al.  K⁎: A heuristic search algorithm for finding the k shortest paths , 2011, Artif. Intell..

[23]  Peyman Noursalehi,et al.  Real time transit demand prediction capturing station interactions and impact of special events , 2018, Transportation Research Part C: Emerging Technologies.

[24]  Jun Liu,et al.  Passenger flow control with multi-station coordination in subway networks: algorithm development and real-world case study , 2019 .

[25]  Yu Liu,et al.  T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction , 2018, IEEE Transactions on Intelligent Transportation Systems.

[26]  Alejandro Tirachini,et al.  Valuation of sitting and standing in metro trains using revealed preferences , 2016 .

[27]  M. Wardman,et al.  Twenty Years of Rail Crowding Valuation Studies: Evidence and Lessons from British Experience , 2011 .

[28]  Yu Zhang,et al.  Aliasing In RTM 3D Angle Gathers , 2011 .

[29]  Alina A. von Davier,et al.  Estimating the DINA model parameters using the No‐U‐Turn Sampler , 2018, Biometrical journal. Biometrische Zeitschrift.

[30]  Roland J. Baddeley,et al.  Optimal foraging and the information theory of gambling , 2018, bioRxiv.

[31]  A. Kennedy,et al.  Hybrid Monte Carlo , 1988 .

[32]  Jie Zhang,et al.  A data-driven optimization of large-scale dry port location using the hybrid approach of data mining and complex network theory , 2020 .

[33]  J. Ortúzar,et al.  Valuing crowding in public transport: Implications for cost-benefit analysis , 2016 .

[34]  Gilbert Laporte,et al.  Integrated Railway Rapid Transit Network Design and Line Planning problem with maximum profit , 2019, Transportation Research Part E: Logistics and Transportation Review.

[35]  Anthony Chen,et al.  Bi-objective programming approach for solving the metro timetable optimization problem with dwell time uncertainty , 2017 .

[36]  Yang Liu,et al.  DeepPF: A deep learning based architecture for metro passenger flow prediction , 2019, Transportation Research Part C: Emerging Technologies.

[37]  Otto Anker Nielsen,et al.  Passenger arrival and waiting time distributions dependent on train service frequency and station characteristics: A smart card data analysis , 2018 .

[38]  Tao Tang,et al.  Analyzing crowd dynamic characteristics of boarding and alighting process in urban metro stations , 2019, Physica A: Statistical Mechanics and its Applications.

[39]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[40]  Xian Li,et al.  Modeling departure time choice of metro passengers with a smart corrected mixed logit model - A case study in Beijing , 2018, Transport Policy.

[41]  Sebastián Raveau,et al.  A topological route choice model for metro , 2011 .

[42]  Andrew Gelman,et al.  The No-U-turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo , 2011, J. Mach. Learn. Res..

[43]  Ricardo Giesen,et al.  How much can holding and/or limiting boarding improve transit performance? , 2012 .

[44]  Andrew Gelman,et al.  General methods for monitoring convergence of iterative simulations , 1998 .

[45]  Ahmad Tavassoli,et al.  Calibrating a Bayesian Transit Assignment Model Using Smart Card Data , 2019, IEEE Transactions on Intelligent Transportation Systems.

[46]  Qian Fu,et al.  Modelling route choice behaviour with incomplete data : an application to the London Underground , 2014 .

[47]  Pan Shang,et al.  Equity-oriented skip-stopping schedule optimization in an oversaturated urban rail transit network , 2018 .

[48]  Le Minh Kieu,et al.  Passenger Segmentation Using Smart Card Data , 2015, IEEE Transactions on Intelligent Transportation Systems.

[49]  Heng Wei,et al.  Constrained multinomial Probit route choice modeling for passengers in large-scaled metro networks in China , 2017 .

[50]  H. W. Ho,et al.  Schedule-based transit assignment model with vehicle capacity and seat availability , 2011 .

[51]  Shlomo Bekhor,et al.  A frequency based transit assignment model that considers online information , 2018 .

[52]  Keemin Sohn,et al.  Inferring the route-use patterns of metro passengers based only on travel-time data within a Bayesian framework using a reversible-jump Markov chain Monte Carlo (MCMC) simulation , 2015 .

[53]  Daniel J. Graham,et al.  Crowding cost estimation with large scale smart card and vehicle location data , 2017 .

[54]  Gah-Yi Ban,et al.  Confidence Intervals for Data-Driven Inventory Policies with Demand Censoring , 2020, Oper. Res..

[55]  Haris N. Koutsopoulos,et al.  A probabilistic Passenger-to-Train Assignment Model based on automated data , 2017 .

[56]  R. Chavez,et al.  Data-driven supply chain capabilities and performance: A resource-based view , 2017, Transportation Research Part E: Logistics and Transportation Review.

[57]  Kay W. Axhausen,et al.  An integrated Bayesian approach for passenger flow assignment in metro networks , 2015 .

[58]  Ying Cao,et al.  Quantile forecasting and data-driven inventory management under nonstationary demand , 2019, Oper. Res. Lett..

[59]  Seongil Shin,et al.  Data-driven stochastic transit assignment modeling using an automatic fare collection system , 2019, Transportation Research Part C: Emerging Technologies.

[60]  Ricardo A. Daziano,et al.  Estimation of crowding discomfort in public transport: Results from Santiago de Chile , 2017 .

[61]  A. Neal,et al.  An Integrated Approach to Testing Dynamic, Multilevel Theory: Using Computational Models to Connect Theory, Model, and Data , 2019, Organizational Research Methods.

[62]  W. Y. Szeto,et al.  Bike network design problem with a path-size logit-based equilibrium constraint: Formulation, global optimization, and matheuristic , 2019, Transportation Research Part E: Logistics and Transportation Review.

[63]  Baohua Mao,et al.  A bi-level model for single-line rail timetable design with consideration of demand and capacity , 2017 .

[64]  Rafael Becerril-Arreola,et al.  Estimating Demand with Substitution and Intraline Price Spillovers , 2020, Manuf. Serv. Oper. Manag..