Please use this identifier to cite or link to this item: http://repositorio.unicamp.br/jspui/handle/REPOSIP/241830
Type: Artigo
Title: Application of self-organising maps towards segmentation of soybean samples by determination of inorganic compounds content
Author: Cremasco, Hágata
Borsato, Dionísio
Angilelli, Karina Gomes
Galão, Olívio Fernandes
Bona, Evandro
Valle, Marcos Eduardo
Abstract: BACKGROUND: In this study, 20 samples of soybean, both transgenic and conventional cultivars, which were planted in two different regions, Londrina and Ponta Grossa, both located at Parana, Brazil, were analysed. In order to verify whether the inorganic compound levels in soybeans varied with the region of planting, K, P, Ca, Mg, S, Zn, Mn, Fe, Cu and B contents were analysed by an artificial neural network self-organising map. RESULTS: It was observed that with a topology 10 x 10, 8000 epochs, initial learning rate of 0.1 and initial neighbourhood ratio of 4.5, the network was able to differentiate samples according to region of origin. Among all of the variables analysed by the artificial neural network, the elements Zn, Ca and Mn were those which most contributed to the classification of the samples. CONCLUSION: The results indicated that samples planted in these two regions differ in their mineral content; however, conventional and transgenic samples grown in the same region show no difference in mineral contents in the grain. (C) 2015 Society of Chemical Industry
In this study, 20 samples of soybean, both transgenic and conventional cultivars, which were planted in two different regions, Londrina and Ponta Grossa, both located at Parana, Brazil, were analysed. In order to verify whether the inorganic compound levels in soybeans varied with the region of planting, K, P, Ca, Mg, S, Zn, Mn, Fe, Cu and B contents were analysed by an artificial neural network self-organising map. It was observed that with a topology 10 x 10, 8000 epochs, initial learning rate of 0.1 and initial neighbourhood ratio of 4.5, the network was able to differentiate samples according to region of origin. Among all of the variables analysed by the artificial neural network, the elements Zn, Ca and Mn were those which most contributed to the classification of the samples. The results indicated that samples planted in these two regions differ in their mineral content; however, conventional and transgenic samples grown in the same region show no difference in mineral contents in the grain.
Subject: Redes neurais (Computação)
Inteligência artificial
Mapas auto-organizáveis
Soja
Compostos inorgânicos - Análise
Country: Reino Unido
Editor: John Wiley & Sons
Citation: Application Of Self-organising Maps Towards Segmentation Of Soybean Samples By Determination Of Inorganic Compounds Content. Wiley-blackwell, v. 96, p. 306-310 Jan-2016.
Rights: fechado
Identifier DOI: 10.1002/jsfa.7094
Address: https://onlinelibrary.wiley.com/doi/full/10.1002/jsfa.7094
Date Issue: 2015
Appears in Collections:IMECC - Artigos e Outros Documentos

Files in This Item:
File SizeFormat 
000367222400035.pdf721.55 kBAdobe PDFView/Open


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