European transport policy, defined in the White Paper, supports shift from road to rail and waterborne transport. The hypothesis of the paper is that changes in the economic environment influence rail traffic volume. Therefore, a model for prediction of rail traffic volume applied in different economic contexts could be a valuable tool for the transport planners. The model was built using common Machine Learning techniques that learn from the past experience. In the model preparation, world development indicators defined by the World Bank were used as input parameters.
Keywords:
rail traffic / prediction / Machine Learning / World Bank / development indicators
Source:
Facta universitatis - series: Mechanical Engineering, 2015, 13, 2, 133-141
TY - JOUR
AU - Lazarević, Luka
AU - Kovačević, Miloš
AU - Popović, Zdenka
PY - 2015
UR - https://grafar.grf.bg.ac.rs/handle/123456789/713
AB - European transport policy, defined in the White Paper, supports shift from road to rail and waterborne transport. The hypothesis of the paper is that changes in the economic environment influence rail traffic volume. Therefore, a model for prediction of rail traffic volume applied in different economic contexts could be a valuable tool for the transport planners. The model was built using common Machine Learning techniques that learn from the past experience. In the model preparation, world development indicators defined by the World Bank were used as input parameters.
PB - Univerzitet u Nišu, Niš
T2 - Facta universitatis - series: Mechanical Engineering
T1 - Rail traffic volume estimation based on world development indicators
EP - 141
IS - 2
SP - 133
VL - 13
UR - https://hdl.handle.net/21.15107/rcub_grafar_713
ER -
@article{
author = "Lazarević, Luka and Kovačević, Miloš and Popović, Zdenka",
year = "2015",
abstract = "European transport policy, defined in the White Paper, supports shift from road to rail and waterborne transport. The hypothesis of the paper is that changes in the economic environment influence rail traffic volume. Therefore, a model for prediction of rail traffic volume applied in different economic contexts could be a valuable tool for the transport planners. The model was built using common Machine Learning techniques that learn from the past experience. In the model preparation, world development indicators defined by the World Bank were used as input parameters.",
publisher = "Univerzitet u Nišu, Niš",
journal = "Facta universitatis - series: Mechanical Engineering",
title = "Rail traffic volume estimation based on world development indicators",
pages = "141-133",
number = "2",
volume = "13",
url = "https://hdl.handle.net/21.15107/rcub_grafar_713"
}
Lazarević, L., Kovačević, M.,& Popović, Z.. (2015). Rail traffic volume estimation based on world development indicators. in Facta universitatis - series: Mechanical Engineering
Univerzitet u Nišu, Niš., 13(2), 133-141.
https://hdl.handle.net/21.15107/rcub_grafar_713
Lazarević L, Kovačević M, Popović Z. Rail traffic volume estimation based on world development indicators. in Facta universitatis - series: Mechanical Engineering. 2015;13(2):133-141.
https://hdl.handle.net/21.15107/rcub_grafar_713 .
Lazarević, Luka, Kovačević, Miloš, Popović, Zdenka, "Rail traffic volume estimation based on world development indicators" in Facta universitatis - series: Mechanical Engineering, 13, no. 2 (2015):133-141,
https://hdl.handle.net/21.15107/rcub_grafar_713 .
