Influence of hidden neuron number on the performance of ANN models applied to deinking flotation data

Balanović, Katarina; Trumić, Maja; Gavrilović, Tamara

doi:10.5937/IOC25229B

Conference Object Open access M33

Balanovic et al. - IOC 2025.pdf (2.30MB)

2025

Balanović, Katarina
Trumić, Maja
Gavrilović, Tamara

University of Belgrade - Technical Faculty in Bor

Proceedings [Elektronski izvor] - 56th International October Conference on Mining and Metallurgy - IOC 2025, 22-25 October, 2025, Bor Lake, Serbia

229

232

English

M33 - Conference paper at an international conference, printed in full

In this paper, the influence of the optimal number of neurons in an artificial neural network model, applied to data obtained from deinking flotation is presented and analyzed. The results indicate that when a wellperforming model is selected, it is not necessary to search for the optimal number of hidden neurons. However, when the applied model does not yield satisfactory results, determining the optimal number of neurons becomes essential.

Artificial neural networks, Hidden neurons, Flotation, Deinking

DOI

10.5937/IOC25229B

ISBN

978-86-6305-164-5

URI

https://ioc.tfbor.bg.ac.rs/public/2025/Proce...
https://repozitorijum.tfbor.bg.ac.rs/handle/...

Scopus

OpenCitations

dc.rights.license	CC-BY-NC-ND
dc.identifier.doi	10.5937/IOC25229B
dc.identifier.uri	https://ioc.tfbor.bg.ac.rs/public/2025/Proceedings_IOC_2025.pdf
dc.identifier.uri	https://repozitorijum.tfbor.bg.ac.rs/handle/123456789/6053
dc.description.abstract	In this paper, the influence of the optimal number of neurons in an artificial neural network model, applied to data obtained from deinking flotation is presented and analyzed. The results indicate that when a wellperforming model is selected, it is not necessary to search for the optimal number of hidden neurons. However, when the applied model does not yield satisfactory results, determining the optimal number of neurons becomes essential.
dc.language.iso	en
dc.publisher	University of Belgrade - Technical Faculty in Bor
dc.source	Proceedings [Elektronski izvor] - 56th International October Conference on Mining and Metallurgy - IOC 2025, 22-25 October, 2025, Bor Lake, Serbia
dc.subject	Artificial neural networks
dc.subject	Hidden neurons
dc.subject	Flotation
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject	Deinking
dc.title	Influence of hidden neuron number on the performance of ANN models applied to deinking flotation data
dc.type	conferenceObject
dc.type.version	publishedVersion
dc.citation.spage	229
dc.citation.epage	232
dc.citation.rank	M33
dc.creator	Balanović, Katarina
dc.creator	Trumić, Maja
dc.creator	Gavrilović, Tamara
dc.date.accessioned	2025-12-12T12:20:30Z
dc.date.available	2025-12-12T12:20:30Z
dc.date.issued	2025
dc.identifier.isbn	978-86-6305-164-5


Influence of hidden neuron number on the performance of ANN models applied to deinking flotation data	1


Balanovic et al. - IOC 2025.pdf	0