Detail publikace

CNN Architecture for Posture Classification on Small Data

MESÁROŠOVÁ, M. MIHÁLIK, O. JIRGL, M.

Originální název

CNN Architecture for Posture Classification on Small Data

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

A 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.

Klíčová slova

CNN, fine tuning, network structure, optimization, posture classification

Autoři

MESÁROŠOVÁ, M.; MIHÁLIK, O.; JIRGL, M.

Vydáno

14. 8. 2024

Nakladatel

Elsevier

Místo

Brno, Czechia

ISSN

2405-8963

Periodikum

IFAC-PapersOnLine (ELSEVIER)

Ročník

58

Číslo

9

Stát

Nizozemsko

Strany od

299

Strany do

304

Strany počet

6

URL

https://doi.org/10.1016/j.ifacol.2024.07.413

Plný text v Digitální knihovně

http://hdl.handle.net/11012/249472

BibTex

@inproceedings{BUT189141,
  author="Michaela {Mesárošová} and Ondrej {Mihálik} and Miroslav {Jirgl}",
  title="CNN Architecture for Posture Classification on Small Data",
  booktitle="18th IFAC Conference on Programmable Devices and Embedded Systems – PDeS 2024.",
  year="2024",
  journal="IFAC-PapersOnLine (ELSEVIER)",
  volume="58",
  number="9",
  pages="299--304",
  publisher="Elsevier",
  address="Brno, Czechia",
  doi="10.1016/j.ifacol.2024.07.413",
  issn="2405-8963",
  url="https://doi.org/10.1016/j.ifacol.2024.07.413"
}