CNN Architecture for Posture Classification on Small Data

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F24%3APU151758" target="_blank" >RIV/00216305:26220/24:PU151758 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1016/j.ifacol.2024.07.413" target="_blank" >https://doi.org/10.1016/j.ifacol.2024.07.413</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.ifacol.2024.07.413" target="_blank" >10.1016/j.ifacol.2024.07.413</a>

Result language
angličtina
Original language name
CNN Architecture for Posture Classification on Small Data
Original language description
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.
Czech name
—
Czech description
—

Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
18th IFAC Conference on Programmable Devices and Embedded Systems – PDeS 2024.
ISBN
—
ISSN
2405-8963
e-ISSN
—
Number of pages
6
Pages from-to
299-304
Publisher name
Elsevier
Place of publication
Brno, Czechia
Event location
Brno
Event date
Jun 19, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)