CNN Architecture for Posture Classification on Small Data

Simple item page
dc.contributor.authorMesárošová, Michaelacs
dc.contributor.authorMihálik, Ondrejcs
dc.contributor.authorJirgl, Miroslavcs
dc.coverage.issue9cs
dc.coverage.volume58cs
dc.date.issued2024-08-14cs
dc.description.abstractA convolutional neural network is often mentioned as one of the deep learning methods that requires a large amount of training data. Questioning this belief, this paper explores the applicability of classification based on a shallow net structure trained on a small data set in the~context of patient posture classification based on data from a pressure mattress. Designing a CNN often presents a complex problem, especially without a universally applicable approach, allowing many diverse structural possibilities and training settings. We tested various training options and layer configurations to provide an overview of influential parameters for posture classification. Experiments show encouraging results with the leave-one-out cross-validation accuracy of 93.1% of one of the evaluated CNN structures and its hyperparameter settings.en
dc.formattextcs
dc.format.extent299-304cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationIFAC-PapersOnLine (ELSEVIER). 2024, vol. 58, issue 9, p. 299-304.en
dc.identifier.doi10.1016/j.ifacol.2024.07.413cs
dc.identifier.issn2405-8963cs
dc.identifier.orcid0009-0005-1276-8388cs
dc.identifier.orcid0000-0001-7433-9275cs
dc.identifier.orcid0000-0002-1037-0641cs
dc.identifier.other189141cs
dc.identifier.urihttp://hdl.handle.net/11012/249472
dc.language.isoencs
dc.publisherElseviercs
dc.relation.ispartofIFAC-PapersOnLine (ELSEVIER)cs
dc.relation.urihttps://doi.org/10.1016/j.ifacol.2024.07.413cs
dc.rightsCreative Commons Attribution-NonCommercial-NoDerivatives 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/2405-8963/cs
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/cs
dc.subjectCNNen
dc.subjectfine tuningen
dc.subjectnetwork structureen
dc.subjectoptimizationen
dc.subjectposture classificationen
dc.titleCNN Architecture for Posture Classification on Small Dataen
dc.type.driverconferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-189141en
sync.item.dbtypeVAVen
sync.item.insts2025.02.03 15:39:36en
sync.item.modts2025.01.17 15:29:28en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav automatizace a měřicí technikycs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
CNN Architecture for Posture Classification on Small Data.pdf
Size:
1.04 MB
Format:
Adobe Portable Document Format
Description:
file CNN Architecture for Posture Classification on Small Data.pdf
Download
Collections
Ústav automatizace a měřicí techniky