Please use this identifier to cite or link to this item:
Type: Artigo
Title: Optical classification of quartz lascas by artificial neural networks
Author: Fujiwara, Eric
Santos, Murilo Ferreira Marques dos
Schenkel, Egont Alexandre
Ono, Eduardo
Suzuki, Carlos Kenichi
Abstract: A gradation method based on quartz lascas (lumps) transparency level is proposed. The samples were irradiated by transmitting light, and the images histograms were processed by artificial neural networks. Additionally, the results were compared to conventional classification methods, including density and visual analysis. The network designed with backpropagation architecture using 4 hidden layers of 10 neurons yielded to a relative error <24% in relation to manual classification, indicating a good agreement to the miners criteria. Furthermore, the implementation of competitive learning with 5 neurons resulted in correct discrimination of samples regarding their optical characteristics with a completely non-subjective approach
Subject: Redes neurais (Computação)
Country: Estados Unidos
Editor: Taylor & Francis
Rights: Fechado
Identifier DOI: 10.1080/08827508.2014.978315
Date Issue: 2015
Appears in Collections:FEM - Artigos e Outros Documentos

Files in This Item:
File Description SizeFormat 
2-s2.0-84929328163.pdf1.37 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.