Clustering Smart Card Data for Urban Mobility Analysis

Smart card data gathered by automated fare collection (AFC) systems are valuable resources for studying urban mobility. In this paper, we propose two approaches to cluster smart card data, which can be used to extract mobility patterns in a public transportation system. Two complementary standpoints are considered: a station-oriented operational point of view and a passenger-focused one. The first approach clusters stations based on when their activity occurs, i.e., how trips made at the stations are distributed over time. The second approach makes it possible to identify groups of passengers that have similar boarding times aggregated into weekly profiles. By applying our approaches to a real data set issued from the metropolitan area of Rennes, France, we illustrate how they can help reveal valuable insights about urban mobility, such as the presence of different station key roles, including residential stations used mostly in the mornings and work stations used only in the evening and almost exclusively during weekdays, as well as different passenger behaviors ranging from the sporadic and diffuse usage to typical commute practices. By cross comparing passenger clusters with fare types, we also highlight how certain usages are more specific to particular types of passengers.

[1]  Joydeep Ghosh,et al.  A Unified Framework for Model-based Clustering , 2003, J. Mach. Learn. Res..

[2]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[3]  Chris Smith,et al.  Avoiding the crowds: understanding Tube station congestion patterns from trip data , 2012, UrbComp '12.

[4]  Ka Kee Alfred Chu,et al.  Augmenting Transit Trip Characterization and Travel Behavior Comprehension , 2010 .

[5]  Yasuo Asakura,et al.  Behavioural data mining of transit smart card data: A data fusion approach , 2014 .

[6]  Craig R. Rindt,et al.  The Activity-Based Approach , 2008 .

[7]  Nigel H. M. Wilson,et al.  Potential Uses of Transit Smart Card Registration and Transaction Data to Improve Transit Planning , 2006 .

[8]  M. Trépanier,et al.  Detection of Activities of Public Transport Users by Analyzing Smart Card Data , 2012 .

[9]  P. Massart,et al.  Minimal Penalties for Gaussian Model Selection , 2007 .

[10]  Mahmoud Mesbah,et al.  Use of Smart Card Fare Data to Estimate Public Transport Origin–Destination Matrix , 2015 .

[11]  Daniele Quercia,et al.  The Hidden Image of the City: Sensing Community Well-Being from Urban Mobility , 2012, Pervasive.

[12]  Nicholas Jing Yuan,et al.  Reconstructing individual mobility from smart card transactions: a collaborative space alignment approach , 2014, Knowledge and Information Systems.

[13]  Le Minh Kieu,et al.  Mining temporal and spatial travel regularity for transit planning , 2013 .

[14]  M. Batty,et al.  Variability in Regularity: Mining Temporal Mobility Patterns in London, Singapore and Beijing Using Smart-Card Data , 2016, PloS one.

[15]  Licia Capra,et al.  Individuals among commuters: Building personalised transport information services from fare collection systems , 2013, Pervasive Mob. Comput..

[16]  Come Etienne,et al.  Model-Based Count Series Clustering for Bike Sharing System Usage Mining: A Case Study with the Vélib’ System of Paris , 2014 .

[17]  Haris N. Koutsopoulos,et al.  Inferring patterns in the multi-week activity sequences of public transport users , 2016 .

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

[19]  Christian Schneider,et al.  Spatiotemporal Patterns of Urban Human Mobility , 2012, Journal of Statistical Physics.

[20]  Peter White,et al.  The Potential of Public Transport Smart Card Data , 2005 .

[21]  Licia Capra,et al.  How smart is your smartcard?: measuring travel behaviours, perceptions, and incentives , 2011, UbiComp '11.

[23]  Jonathan Corcoran,et al.  Examining the spatial–temporal dynamics of bus passenger travel behaviour using smart card data and the flow-comap , 2014 .

[24]  Zhaohui Wu,et al.  Container Port Performance Measurement and Comparison Leveraging Ship GPS Traces and Maritime Open Data , 2016, IEEE Transactions on Intelligent Transportation Systems.

[25]  Ka Kee Alfred Chu,et al.  Enriching Archived Smart Card Transaction Data for Transit Demand Modeling , 2008 .

[26]  Gerd Kortuem,et al.  Predictability of Public Transport Usage: A Study of Bus Rides in Lisbon, Portugal , 2015, IEEE Transactions on Intelligent Transportation Systems.

[27]  Nigel H. M. Wilson,et al.  Analyzing Multimodal Public Transport Journeys in London with Smart Card Fare Payment Data , 2009 .

[28]  Michael G. McNally,et al.  The Four Step Model , 2007 .

[29]  Bruno Agard,et al.  Analysing the Variability of Transit Users Behaviour with Smart Card Data , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[30]  Catherine Morency,et al.  Smart card data use in public transit: A literature review , 2011 .

[31]  Martin Trépanier,et al.  Individual Trip Destination Estimation in a Transit Smart Card Automated Fare Collection System , 2007, J. Intell. Transp. Syst..

[32]  E. Nasiboglu,et al.  Origin-destination matrix generation using smart card data: Case study for Izmir , 2012, 2012 IV International Conference "Problems of Cybernetics and Informatics" (PCI).

[33]  Bruno Agard,et al.  MINING PUBLIC TRANSPORT USER BEHAVIOUR FROM SMART CARD DATA , 2006 .

[34]  Jinhua Zhao,et al.  Estimating a Rail Passenger Trip Origin‐Destination Matrix Using Automatic Data Collection Systems , 2007, Comput. Aided Civ. Infrastructure Eng..

[35]  Xiaolei Ma,et al.  Mining smart card data for transit riders’ travel patterns , 2013 .

[36]  Mark Hickman,et al.  Validating and calibrating a destination estimation algorithm for public transport smart card fare collection systems , 2015 .

[37]  Harilaos N. Koutsopoulos,et al.  Automated Inference of Linked Transit Journeys in London Using Fare-Transaction and Vehicle Location Data , 2013 .

[38]  TrépanierMartin,et al.  Are transit users loyal? Revelations from a hazard model based on smart card data , 2012 .

[39]  Marcela Munizaga,et al.  Estimation of a disaggregate multimodal public transport Origin-Destination matrix from passive smartcard data from Santiago, Chile , 2012 .

[40]  Bertrand Michel,et al.  Slope heuristics: overview and implementation , 2011, Statistics and Computing.

[41]  Etienne Côme,et al.  Model-Based Count Series Clustering for Bike Sharing System Usage Mining: A Case Study with the Vélib’ System of Paris , 2014, TIST.

[42]  Keemin Sohn,et al.  Activity imputation for trip-chains elicited from smart-card data using a continuous hidden Markov model , 2016 .

[43]  Zhipeng Li,et al.  An Approach to Urban Traffic State Estimation by Fusing Multisource Information , 2009, IEEE Transactions on Intelligent Transportation Systems.

[44]  Sebastian Thrun,et al.  Text Classification from Labeled and Unlabeled Documents using EM , 2000, Machine Learning.

[45]  Peter White,et al.  What role for smart-card data from bus systems? , 2004 .

[46]  M. Hofmann,et al.  Transfer journey identification and analyses from electronic fare collection data , 2005, Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005..

[47]  Romain Billot,et al.  Spatiotemporal Analysis of Bluetooth Data: Application to a Large Urban Network , 2015, IEEE Transactions on Intelligent Transportation Systems.

[48]  Patrick Gallinari,et al.  Mining Ticketing Logs for Usage Characterization with Nonnegative Matrix Factorization , 2014, MSM/MUSE/SenseML.

[49]  Wei Wu,et al.  Predicting Home and Work Locations Using Public Transport Smart Card Data by Spectral Analysis , 2015, 2015 IEEE 18th International Conference on Intelligent Transportation Systems.

[50]  Licia Capra,et al.  Urban Computing: Concepts, Methodologies, and Applications , 2014, TIST.