Scipediacontent: Scipediacontent moved page Draft Content 488006251 to Fumeo et al 2016a

2021-01-21T12:46:44Z

Scipediacontent moved page Draft Content 488006251 to Fumeo et al 2016a

Scipediacontent: Created page with " == Abstract == State-of-the-art train delay prediction systems do not exploit historical train movements data collected by the railway information systems, but they rely on..."

2021-01-21T12:46:41Z

Created page with " == Abstract == State-of-the-art train delay prediction systems do not exploit historical train movements data collected by the railway information systems, but they rely on..."

New page

== Abstract ==

State-of-the-art train delay prediction systems do not exploit historical train movements data collected by the railway information systems, but they rely on static rules built by expert of the railway infrastructure based on classical univariate statistic. The purpose of this paper is to build a data-driven train delay prediction system for large-scale railway networks which exploits the most recent Big Data technologies and learning algorithms. In particular, we propose a fast learning algorithm for predicting train delays based on the Extreme Learning Machine that fully exploits the recent in-memory large-scale data processing technologies. Our system is able to rapidly extract nontrivial information from the large amount of data available in order to make accurate predictions about different future states of the railway network. Results on real world data coming from the Italian railway network show that our proposal is able to improve the current state-of-the-art train delay prediction systems.

== Original document ==

The different versions of the original document can be found in:

* [http://dx.doi.org/10.1007/978-3-319-47898-2_15 http://dx.doi.org/10.1007/978-3-319-47898-2_15] under the license http://www.springer.com/tdm

* [http://hdl.handle.net/11567/853032 http://hdl.handle.net/11567/853032]

* [https://iris.unige.it/bitstream/11567/853032/2/C045.pdf https://iris.unige.it/bitstream/11567/853032/2/C045.pdf]

* [http://link.springer.com/content/pdf/10.1007/978-3-319-47898-2_15 http://link.springer.com/content/pdf/10.1007/978-3-319-47898-2_15],
: [http://dx.doi.org/10.1007/978-3-319-47898-2_15 http://dx.doi.org/10.1007/978-3-319-47898-2_15] under the license http://www.springer.com/tdm

* [https://link.springer.com/chapter/10.1007/978-3-319-47898-2_15 https://link.springer.com/chapter/10.1007/978-3-319-47898-2_15],
: [https://core.ac.uk/display/80200250 https://core.ac.uk/display/80200250],
: [https://dblp.uni-trier.de/db/conf/inns/inns2016.html#OnetoFCCPDMA16 https://dblp.uni-trier.de/db/conf/inns/inns2016.html#OnetoFCCPDMA16],
: [https://doi.org/10.1007/978-3-319-47898-2_15 https://doi.org/10.1007/978-3-319-47898-2_15],
: [https://academic.microsoft.com/#/detail/2528685867 https://academic.microsoft.com/#/detail/2528685867]

← Older revision	Revision as of 12:46, 21 January 2021
(No difference)

Fumeo et al 2016a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 488006251 to Fumeo et al 2016a

Scipediacontent: Created page with " == Abstract == State-of-the-art train delay prediction systems do not exploit historical train movements data collected by the railway information systems, but they rely on..."