Activity-based travel demand generation using Bayesian networks

Abstract While activity-based travel demand generation has improved over the last few decades, the behavioural richness and intuitive interpretation remain challenging. This paper argues that it is essential to understand why people travel the way they do and not only be able to predict the overall activity patterns accurately. If one cannot understand the “why?” then a model’s ability to evaluate the impact of future interventions is severely diminished. Bayesian networks (BNs) provide the ability to investigate causality and is showing value in recent literature to generate synthetic populations. This paper is novel in extending the application of BNs to daily activity tours. Results show that BNs can synthesise both activity and trip chain structures accurately. It outperforms a frequentist approach and can cater for infrequently observed activity patterns, and patterns unobserved in small sample data. It can also account for temporal variables like activity duration.

[1]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[2]  L. Pritchett,et al.  Estimating Wealth Effects Without Expenditure Data—Or Tears: An Application To Educational Enrollments In States Of India* , 2001, Demography.

[3]  Lei Liu,et al.  A time-use activity-pattern recognition model for activity-based travel demand modeling , 2019 .

[4]  Matthew J. Roorda,et al.  Validation of TASHA: A 24-Hour Activity Scheduling Microsimulation Model , 2008 .

[5]  Abolfazl Mohammadian,et al.  Modeling Daily Activity–Travel Tour Patterns Incorporating Activity Scheduling Decision Rules , 2008 .

[6]  Jean-François Paiement,et al.  A Generative Model of Urban Activities from Cellular Data , 2018, IEEE Transactions on Intelligent Transportation Systems.

[7]  Ta Theo Arentze,et al.  Parametric Action Decision Trees: Incorporating Continuous Attribute Variables Into Rule-Based Models of Discrete Choice , 2007 .

[8]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[9]  Alexander Erath,et al.  A Bayesian network approach for population synthesis , 2015 .

[10]  Davy Janssens,et al.  Characterizing activity sequences using profile Hidden Markov Models , 2015, Expert Syst. Appl..

[11]  J. Bromley,et al.  The use of Hugin® to develop Bayesian networks as an aid to integrated water resource planning , 2005, Environ. Model. Softw..

[12]  Kevin B. Korb,et al.  Bayesian Artificial Intelligence , 2004, Computer science and data analysis series.

[13]  Lijun Sun,et al.  A hierarchical mixture modeling framework for population synthesis , 2018, Transportation Research Part B: Methodological.

[14]  Alexei Pozdnoukhov,et al.  Peer pressure enables actuation of mobility lifestyles , 2018 .

[15]  J. Joubert.  Synthetic populations of South African urban areas , 2018, Data in brief.

[16]  Christopher Gandrud,et al.  D3 JavaScript Network Graphs from R , 2015 .

[17]  Alexei Pozdnoukhov,et al.  Connected Population Synthesis for Transportation Simulation , 2019, Transportation Research Part C: Emerging Technologies.

[18]  Mark E. Borsuk,et al.  A Bayesian network of eutrophication models for synthesis, prediction, and uncertainty analysis , 2004 .

[19]  Tai-Yu Ma,et al.  Bayesian Networks for Multimodal Mode Choice Behavior Modelling: A Case Study for the Cross Border Workers of Luxembourg , 2015 .

[20]  Luis A. Guzman,et al.  A Strategic Tour Generation Modeling within a Dynamic Land-Use and Transport Framework: A Case Study of Bogota, Colombia , 2017 .

[21]  David Maxwell Chickering,et al.  A Bayesian Approach to Learning Bayesian Networks with Local Structure , 1997, UAI.

[22]  Jeppe Rich,et al.  How to generate micro-agents? A deep generative modeling approach to population synthesis , 2019, Transportation Research Part C: Emerging Technologies.

[23]  Finn Verner Jensen,et al.  Introduction to Bayesian Networks , 2008, Innovations in Bayesian Networks.

[24]  Mario Cools,et al.  Forecasting travel behavior using Markov Chains-based approaches , 2016 .

[25]  Daphne Koller,et al.  Ordering-Based Search: A Simple and Effective Algorithm for Learning Bayesian Networks , 2005, UAI.

[26]  Soora Rasouli,et al.  Activity-based models of travel demand: promises, progress and prospects , 2014 .

[27]  Sina K. Frank,et al.  A Review of Bayesian Networks as a Participatory Modeling Approach in Support of Sustainable Environmental Management , 2012 .

[28]  Joseph Y. J. Chow,et al.  Causal structure learning for travel mode choice using structural restrictions and model averaging algorithm , 2017 .