Understanding spatio-temporal mobility patterns for seniors, child/student and adult using smart card data

Abstract. Commutes in urban areas create interesting travel patterns that are often stored in regional transportation databases. These patterns can vary based on the day of the week, the time of the day, and commuter type. This study proposes methods to detect underlying spatio-temporal variability among three groups of commuters (senior citizens, child/students, and adults) using data mining and spatial analytics. Data from over 36 million individual trip records collected over one week (March 2012) on the Singapore bus and Mass Rapid Transit (MRT) system by the fare collection system were used. Analyses of such data are important for transportation and landuse designers and contribute to a better understanding of urban dynamics. Specifically, descriptive statistics, network analysis, and spatial analysis methods are presented. Descriptive variables were proposed such as density and duration to detect temporal features of people. A directed weighted graph G ≡ (N , L, W) was defined to analyze the global network properties of every pair of the transportation link in the city during an average workday for all three categories. Besides, spatial interpolation and spatial statistic tools were used to transform the discrete network nodes into structured human movement landscape to understand the role of transportation systems in urban areas. The travel behaviour of the three categories follows a certain degree of temporal and spatial universality but also displays unique patterns within their own specialties. Each category is characterized by their different peak hours, commute distances, and specific locations for travel on weekdays.

[1]  Dong-Jun Kim,et al.  Use of Smart Card Data to Define Public Transit Use in Seoul, South Korea , 2008 .

[2]  Albert-László Barabási,et al.  Limits of Predictability in Human Mobility , 2010, Science.

[3]  Alexander Erath,et al.  Activity identification and primary location modelling based on smart card payment data for public transport , 2012 .

[4]  Pan Di,et al.  Weighted complex network analysis of travel routes on the Singapore public transportation system , 2010 .

[5]  Sergey Brin,et al.  The Anatomy of a Large-Scale Hypertextual Web Search Engine , 1998, Comput. Networks.

[6]  Xianfeng Huang,et al.  Identifying Spatial Structure of Urban Functional Centers Using Travel Survey Data: A Case Study of Singapore , 2013, COMP '13.

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

[8]  Liang Liu,et al.  Understanding individual and collective mobility patterns from smart card records: A case study in Shenzhen , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[9]  Xing Xie,et al.  Discovering regions of different functions in a city using human mobility and POIs , 2012, KDD.

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

[11]  Daniele Miorandi,et al.  Eigenvector Centrality in Highly Partitioned Mobile Networks: Principles and Applications , 2007, Advances in Biologically Inspired Information Systems.

[12]  Alexander Erath,et al.  Estimating Dynamic Workplace Capacities using Public Transport Smart Card Data and a Household Travel Survey , 2013 .