Neural Network-Based Train Identification in Railway Switches and Crossings Using Accelerometer Data

Simple item page
dc.contributor.authorKrč, Rostislavcs
dc.contributor.authorPodroužek, Jancs
dc.contributor.authorFloriánová, Martinacs
dc.contributor.authorVukušič, Ivancs
dc.contributor.authorPlášek, Ottocs
dc.coverage.issue1cs
dc.coverage.volume2020cs
dc.date.issued2020-11-24cs
dc.description.abstractThis paper aims to analyse possibilities of train type identification in railway switches and crossings (S&C) based on accelerometer data by using contemporary machine learning methods such as neural networks. That is a unique approach since trains have been only identified in a straight track. Accelerometer sensors placed around the S&C structure were the source of input data for subsequent models. Data from four S&C at different locations were considered and various neural network architectures evaluated. The research indicated the feasibility to identify trains in S&C using neural networks from accelerometer data. Models trained at one location are generally transferable to another location despite differences in geometrical parameters, substructure, and direction of passing trains. Other challenges include small dataset and speed variation of the trains that must be considered for accurate identification. Results are obtained using statistical bootstrapping and are presented in a form of confusion matrices.en
dc.formattextcs
dc.format.extent1-10cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationJOURNAL OF ADVANCED TRANSPORTATION. 2020, vol. 2020, issue 1, p. 1-10.en
dc.identifier.doi10.1155/2020/8841810cs
dc.identifier.issn0197-6729cs
dc.identifier.orcid0000-0001-6772-2575cs
dc.identifier.orcid0000-0003-0493-5922cs
dc.identifier.orcid0000-0002-8001-6349cs
dc.identifier.orcid0000-0002-6713-7146cs
dc.identifier.orcid0000-0003-2799-1521cs
dc.identifier.other168007cs
dc.identifier.scopus57205731839cs
dc.identifier.scopus25121877100cs
dc.identifier.scopus56301300500cs
dc.identifier.urihttp://hdl.handle.net/11012/196564
dc.language.isoencs
dc.publisherHindawics
dc.relation.ispartofJOURNAL OF ADVANCED TRANSPORTATIONcs
dc.relation.urihttps://www.hindawi.com/journals/jat/2020/8841810/cs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/0197-6729/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectNeural Network-Based Train Identificationen
dc.subjectRailway Switches and Crossingsen
dc.subjectAccelerometer Dataen
dc.titleNeural Network-Based Train Identification in Railway Switches and Crossings Using Accelerometer Dataen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-168007en
sync.item.dbtypeVAVen
sync.item.insts2025.02.03 15:44:13en
sync.item.modts2025.01.17 18:35:28en
thesis.grantorVysoké učení technické v Brně. Fakulta stavební. Ústav železničních konstrukcí a stavebcs
thesis.grantorVysoké učení technické v Brně. Fakulta stavební. Ústav automatizace inženýrských úloh a informatikycs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
8841810.pdf
Size:
2.02 MB
Format:
Adobe Portable Document Format
Description:
8841810.pdf
Download
Collections
Ústav železničních konstrukcí a staveb
Ústav automatizace inženýrských úloh a informatiky