Using Neural Networks for Bicycle Route Planning

This paper presents the usage of artificial neural networks (NNs) in bicycle route planning. This research aimed to check the possibility of NNs to transfer human expertise in bicycle route design by training the NN on an already established set of bicycle routes and then using the trained NN to des...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jurica Đerek, Marjan Sikora, Luka Kraljević, Mladen Russo
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
GIS
T
Acceso en línea:https://doaj.org/article/64571babd7cb4103a1a8c659f01c3e45
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:64571babd7cb4103a1a8c659f01c3e45
record_format dspace
spelling oai:doaj.org-article:64571babd7cb4103a1a8c659f01c3e452021-11-11T15:08:25ZUsing Neural Networks for Bicycle Route Planning10.3390/app1121100652076-3417https://doaj.org/article/64571babd7cb4103a1a8c659f01c3e452021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10065https://doaj.org/toc/2076-3417This paper presents the usage of artificial neural networks (NNs) in bicycle route planning. This research aimed to check the possibility of NNs to transfer human expertise in bicycle route design by training the NN on an already established set of bicycle routes and then using the trained NN to design the routes on the novel area. We created two NNs capable of choosing the best route among the given road network by training them on two different areas. The bicycle routes produced by NNs were the same at best and had 75% overlap at the worst compared to those produced by human experts. Furthermore, the mean square error for all of our NN models varied from 0.015 and 0.081. We compared this new approach to the traditional multicriteria GIS (geographic information system) analysis (MA) that requires the human expert to define the bicycle route selection criteria. The benefit of using NN over the MA was that the NN directly transfers the human expertise to a model. In contrast, the MA needs the expert to select multiple criteria and adjust their weights carefully.Jurica ĐerekMarjan SikoraLuka KraljevićMladen RussoMDPI AGarticleGISmultiple criteria analysisneural networksbicycleroutestouristsTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10065, p 10065 (2021)
institution DOAJ
collection DOAJ
language EN
topic GIS
multiple criteria analysis
neural networks
bicycle
routes
tourists
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
spellingShingle GIS
multiple criteria analysis
neural networks
bicycle
routes
tourists
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
Jurica Đerek
Marjan Sikora
Luka Kraljević
Mladen Russo
Using Neural Networks for Bicycle Route Planning
description This paper presents the usage of artificial neural networks (NNs) in bicycle route planning. This research aimed to check the possibility of NNs to transfer human expertise in bicycle route design by training the NN on an already established set of bicycle routes and then using the trained NN to design the routes on the novel area. We created two NNs capable of choosing the best route among the given road network by training them on two different areas. The bicycle routes produced by NNs were the same at best and had 75% overlap at the worst compared to those produced by human experts. Furthermore, the mean square error for all of our NN models varied from 0.015 and 0.081. We compared this new approach to the traditional multicriteria GIS (geographic information system) analysis (MA) that requires the human expert to define the bicycle route selection criteria. The benefit of using NN over the MA was that the NN directly transfers the human expertise to a model. In contrast, the MA needs the expert to select multiple criteria and adjust their weights carefully.
format article
author Jurica Đerek
Marjan Sikora
Luka Kraljević
Mladen Russo
author_facet Jurica Đerek
Marjan Sikora
Luka Kraljević
Mladen Russo
author_sort Jurica Đerek
title Using Neural Networks for Bicycle Route Planning
title_short Using Neural Networks for Bicycle Route Planning
title_full Using Neural Networks for Bicycle Route Planning
title_fullStr Using Neural Networks for Bicycle Route Planning
title_full_unstemmed Using Neural Networks for Bicycle Route Planning
title_sort using neural networks for bicycle route planning
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/64571babd7cb4103a1a8c659f01c3e45
work_keys_str_mv AT juricađerek usingneuralnetworksforbicyclerouteplanning
AT marjansikora usingneuralnetworksforbicyclerouteplanning
AT lukakraljevic usingneuralnetworksforbicyclerouteplanning
AT mladenrusso usingneuralnetworksforbicyclerouteplanning
_version_ 1718437143969267712