A machine-learning approach to a mobility policy proposal
The objective of the URBANITE project is to design an open-data, open-source, smart-city framework to enhance the decision-making processes in European cities. The framework's basis is a robust and user-friendly simulation tool that is supplemented with several innovative service modules. One o...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-10-01
|
Series: | Heliyon |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023076016 |
_version_ | 1797646574948450304 |
---|---|
author | Miljana Shulajkovska Maj Smerkol Erik Dovgan Matjaž Gams |
author_facet | Miljana Shulajkovska Maj Smerkol Erik Dovgan Matjaž Gams |
author_sort | Miljana Shulajkovska |
collection | DOAJ |
description | The objective of the URBANITE project is to design an open-data, open-source, smart-city framework to enhance the decision-making processes in European cities. The framework's basis is a robust and user-friendly simulation tool that is supplemented with several innovative service modules. One of the modules, a multi-output, machine-learning unit, is deployed on the simulation results, enabling city officials to more effectively analyse vast quantities of data, discern patterns and trends, and so facilitate advanced policy decisions. The city's decision makers define potential city scenarios, key performance indicators, and a utility function, while the module assists in identifying the policy that is best aligned with the stipulated constraints and preferences. One of the main improvements is a speeding up of the policy testing for the decision makers, reducing the time needed for one policy verification from 3 hours to around 10 seconds. The system was evaluated for Bilbao's Moyua area, where it suggested strategies that could result in a decrease in emissions of more than 5% CO2, NOx, PM in the selected area and a broader part of the city with a machine-learning accuracy of 91%. The system was therefore able to provide valuable insights into effective policies for restricting private traffic in specific districts and identifying the most advantageous times for these restrictions. |
first_indexed | 2024-03-11T15:03:34Z |
format | Article |
id | doaj.art-3d17a8a31e904b9eab680238ebe7b6a9 |
institution | Directory Open Access Journal |
issn | 2405-8440 |
language | English |
last_indexed | 2024-03-11T15:03:34Z |
publishDate | 2023-10-01 |
publisher | Elsevier |
record_format | Article |
series | Heliyon |
spelling | doaj.art-3d17a8a31e904b9eab680238ebe7b6a92023-10-30T06:05:55ZengElsevierHeliyon2405-84402023-10-01910e20393A machine-learning approach to a mobility policy proposalMiljana Shulajkovska0Maj Smerkol1Erik Dovgan2Matjaž Gams3Corresponding author.; Jožef Stefan Institute, Jamova cesta 39, SI-1000 Ljubljana, SloveniaJožef Stefan Institute, Jamova cesta 39, SI-1000 Ljubljana, SloveniaJožef Stefan Institute, Jamova cesta 39, SI-1000 Ljubljana, SloveniaJožef Stefan Institute, Jamova cesta 39, SI-1000 Ljubljana, SloveniaThe objective of the URBANITE project is to design an open-data, open-source, smart-city framework to enhance the decision-making processes in European cities. The framework's basis is a robust and user-friendly simulation tool that is supplemented with several innovative service modules. One of the modules, a multi-output, machine-learning unit, is deployed on the simulation results, enabling city officials to more effectively analyse vast quantities of data, discern patterns and trends, and so facilitate advanced policy decisions. The city's decision makers define potential city scenarios, key performance indicators, and a utility function, while the module assists in identifying the policy that is best aligned with the stipulated constraints and preferences. One of the main improvements is a speeding up of the policy testing for the decision makers, reducing the time needed for one policy verification from 3 hours to around 10 seconds. The system was evaluated for Bilbao's Moyua area, where it suggested strategies that could result in a decrease in emissions of more than 5% CO2, NOx, PM in the selected area and a broader part of the city with a machine-learning accuracy of 91%. The system was therefore able to provide valuable insights into effective policies for restricting private traffic in specific districts and identifying the most advantageous times for these restrictions.http://www.sciencedirect.com/science/article/pii/S2405844023076016Machine learningSmart citiesMobility policy |
spellingShingle | Miljana Shulajkovska Maj Smerkol Erik Dovgan Matjaž Gams A machine-learning approach to a mobility policy proposal Heliyon Machine learning Smart cities Mobility policy |
title | A machine-learning approach to a mobility policy proposal |
title_full | A machine-learning approach to a mobility policy proposal |
title_fullStr | A machine-learning approach to a mobility policy proposal |
title_full_unstemmed | A machine-learning approach to a mobility policy proposal |
title_short | A machine-learning approach to a mobility policy proposal |
title_sort | machine learning approach to a mobility policy proposal |
topic | Machine learning Smart cities Mobility policy |
url | http://www.sciencedirect.com/science/article/pii/S2405844023076016 |
work_keys_str_mv | AT miljanashulajkovska amachinelearningapproachtoamobilitypolicyproposal AT majsmerkol amachinelearningapproachtoamobilitypolicyproposal AT erikdovgan amachinelearningapproachtoamobilitypolicyproposal AT matjazgams amachinelearningapproachtoamobilitypolicyproposal AT miljanashulajkovska machinelearningapproachtoamobilitypolicyproposal AT majsmerkol machinelearningapproachtoamobilitypolicyproposal AT erikdovgan machinelearningapproachtoamobilitypolicyproposal AT matjazgams machinelearningapproachtoamobilitypolicyproposal |