Applying Time-Dependent Attributes to Represent Demand in Road Mass Transit Systems

The development of efficient mass transit systems that provide quality of service is a major challenge for modern societies. To meet this challenge, it is essential to understand user demand. This article proposes using new time-dependent attributes to represent demand, attributes that differ from those that have traditionally been used in the design and planning of this type of transit system. Data mining was used to obtain these new attributes; they were created using clustering techniques, and their quality evaluated with the Shannon entropy function and with neural networks. The methodology was implemented on an intercity public transport company and the results demonstrate that the attributes obtained offer a more precise understanding of demand and enable predictions to be made with acceptable precision.

[1]  Jules White,et al.  Real-Time and Predictive Analytics for Smart Public Transportation Decision Support System , 2016, 2016 IEEE International Conference on Smart Computing (SMARTCOMP).

[2]  Bowen Du,et al.  Understand Group Travel Behaviors in an Urban Area Using Mobility Pattern Mining , 2013, 2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing.

[3]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[4]  Peter G Furth,et al.  Service Reliability and Optimal Running Time Schedules , 2007 .

[5]  Fernando Merchan,et al.  A Fuzzy Logic-Based Approach for Estimation of Dwelling Times of Panama Metro Stations , 2015, Entropy.

[6]  David M. Blei,et al.  Probabilistic topic models , 2012, Commun. ACM.

[7]  Licia Capra,et al.  Mining mobility data to minimise travellers' spending on public transport , 2011, KDD.

[8]  Rui Xu,et al.  Survey of clustering algorithms , 2005, IEEE Transactions on Neural Networks.

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

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

[11]  Ángel Fernando Kuri Morales,et al.  A Clustering Method Based on the Maximum Entropy Principle , 2015, Entropy.

[12]  André Hardy,et al.  An examination of procedures for determining the number of clusters in a data set , 1994 .

[13]  Alejandro Tirachini,et al.  Hybrid predictive control strategy for a public transport system with uncertain demand , 2012 .

[14]  P. Rousseeuw,et al.  Partitioning Around Medoids (Program PAM) , 2008 .

[15]  Oded Cats,et al.  Automated Setting of Bus Schedule Coverage Using Unsupervised Machine Learning , 2016, PAKDD.

[17]  Umberto Michelucci,et al.  Training Neural Networks , 2018 .

[18]  B. Efron.  Estimating the Error Rate of a Prediction Rule: Improvement on Cross-Validation , 1983 .

[19]  João Gama,et al.  Improving Mass Transit Operations by Using AVL-Based Systems: A Survey , 2015, IEEE Transactions on Intelligent Transportation Systems.

[20]  Shangyao Yan,et al.  A scheduling model and a solution algorithm for inter-city bus carriers , 2002 .

[21]  Wendy R. Fox,et al.  Finding Groups in Data: An Introduction to Cluster Analysis , 1991 .

[22]  Maged Dessouky,et al.  REAL-TIME CONTROL OF BUSES FOR SCHEDULE COORDINATION AT A TERMINAL , 2003 .

[23]  Jayakrishna Patnaik.  Using Data Mining Techniques on APC Data to Develop Effective Bus Scheduling Plans , 2013 .

[24]  Avishai Ceder,et al.  Optimal coordination of public transit vehicles using operational tactics examined by simulation , 2008 .

[25]  Eleni I. Vlahogianni,et al.  Statistical methods versus neural networks in transportation research: Differences, similarities and some insights , 2011 .

[26]  Kai Zhao,et al.  Automatic City Region Analysis for Urban Routing , 2015, 2015 IEEE International Conference on Data Mining Workshop (ICDMW).

[27]  Guy Desaulniers,et al.  Chapter 2 Public Transit , 2007, Transportation.

[28]  João Gama,et al.  Validating the coverage of bus schedules: A Machine Learning approach , 2015, Inf. Sci..

[29]  Shangyao Yan,et al.  Inter-city bus routing and timetable setting under stochastic demands , 2006 .

[30]  Stefan Fritsch,et al.  neuralnet: Training of Neural Networks , 2010, R J..

[31]  Bersam Bolat,et al.  Light rail passenger demand forecasting by artificial neural networks , 2009, 2009 International Conference on Computers & Industrial Engineering.