Big data for public transportation: A DSS framework

Abstract

Big Data are having a great impact on the cities morphology and urban planning; actually, big data are used, for example, to predict the needs of the public transport system, by targeting investment and mobility policies within the main metropolis. Based on this assumption, this paper presents a Decision Support System (DSS) framework aimed at proposing travel strategies alternative to car use by elaborating a large amount of transportation systems data coming from different devices. The paper focalizes on the use of Big Data in public transportation and introduces a methodological framework for collecting, integrating, aggregating, fusing, managing and disseminating data coming from different sources. Data mining approaches are applied to allow the analysis of both open Big Data, that conforms to established standards such as SIRI and GTFS, and unstructured freely available Big Data. Experimental data was collected from both a sample of smartphones and AVL systems in a case study area. The application of the proposed DSS allowed analyzing spatial and temporal coverage of the public transport services, and suggesting policies to improve the modal split.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 20 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.