Print Email Facebook Twitter Automated Setting of Bus Schedule Coverage Using Unsupervised Machine Learning Title Automated Setting of Bus Schedule Coverage Using Unsupervised Machine Learning Author Khiari, J (NEC Laboratories Europe) Moreira-Matias, L (NEC Laboratories Europe) Cerqueira, Vitor (NEC Laboratories Europe) Cats, O. (TU Delft Transport and Planning) Contributor Bailey, J. (editor) Khan, L. (editor) Washio, T. (editor) Dobbie, G. (editor) Huang, J. (editor) Wang, R. (editor) Date 2016 Abstract The efficiency of Public Transportation (PT) Networks is a major goal of any urban area authority. Advances on both location and communication devices drastically increased the availability of the data generated by their operations. Adequate Machine Learning methods can thus be applied to identify patterns useful to improve the Schedule Plan. In this paper, the authors propose a fully automated learning framework to determine the best Schedule Coverage to be assigned to a given PT network based on Automatic Vehicle location (AVL) and Automatic Passenger Counting (APC) data. We formulate this problem as a clustering one, where the best number of clusters is selected through an ad-hoc metric. This metric takes into account multiple domain constraints, computed using Sequence Mining and Probabilistic Reasoning. A case study from a large operator in Sweden was selected to validate our methodology. Experimental results suggest necessary changes on the Schedule coverage. Moreover, an impact study was conducted through a large-scale simulation over the affected time period. Its results uncovered potential improvements of the schedule reliability on a large scale. Subject Unsupervised learningPublic transportationBig dataSchedule planSchedule coverageSequence miningProbabilistic reasoning To reference this document use: http://resolver.tudelft.nl/uuid:b7ec5d96-f18f-4d3d-a845-a97f018423a1 DOI https://doi.org/10.1007/978-3-319-31753-3_44 Publisher Springer Embargo date 2018-02-01 ISBN 978-3-319-31752-6 Source Advances in Knowledge Discovery and Data Mining, 9651 Event The 20th Pacific Asia Conference on Knowledge Discovery and Data Mining, 2016-04-19 → 2016-04-22, Auckland, New Zealand Series Lecture Notes in Computer Science (LNCS), 0302-9743, 9651 Part of collection Institutional Repository Document type conference paper Rights © 2016 J Khiari, L Moreira-Matias, Vitor Cerqueira, O. Cats Files PDF bus_schedule_coverage2.pdf 526.07 KB Close viewer /islandora/object/uuid:b7ec5d96-f18f-4d3d-a845-a97f018423a1/datastream/OBJ/view