Classification of soybean cultivars by means of artificial neural networks
Abstract
The cultivation of soy has an economic importance for the Brazilian agricultural scenario. The aim of this study was to establish a network architecture for the classification of soybean genotypes, by means of morphological characters measured in the juvenile phase of the plant, and finally to compare the results obtained through Artificial Neural Network (ANN) and Anderson Discriminant Analysis. The study analyzed plants of 10 conventional cultivars in the initial stages of development (V1, V2 and V3 stages). The experiment was carried out in a randomized block design with 5 replications, and the experimental unit was represented by 9 plants. The data were submitted to the Anderson Discriminant Analysis and multilayer Perceptron ANN, with 1 or 2 hidden layers. To analyze the homogeneity of the variance and covariance matrix, the Box’s M-Test was adopted in the Program R, at 5% significance level. An input layer, one or two hidden layers, and an output layer formed the ANN architecture. The 5-fold cross validation was used to verify the efficiency of the discriminant functions and also in the ANN analysis. Subsequently, the apparent error rate (AER) was obtained. Box’s M-Test indicated inhomogeneity in the variance and covariance matrices, which indicated the need to perform Anderson's Quadratic Discriminant Analysis. The ANNs presented lower apparent error rate when compared to the Anderson's Quadratic Discriminant Analysis and the artificial neural network with 1 hidden layer was sufficient to perform the classification of soybean cultivars.
Downloads
References
Abraham, E. R., Reis, J. G. M., Toloi, R. C., Souza, A. E., & Colossetti, A. P. (2019). Estimativa da produção da soja brasileira utilizando redes neurais artificiais. Agrarian, 12(44), 261-271. doi: 10.30612/agrarian.v12i44.9209
Alves, G. F.; Nogueira, J. P. G.; Machado Junior, R.; Ferreira, S.C.; Nascimento, M.; & Matsuo, E. (2019). Stability of the hypocotyl length of soybean cultivars using neural networks and traditional methods. Ciência Rural, 49(3), e20180300, doi: 10.1590/0103-8478cr20180300
Anderson, T. W. (1958). An introduction to multivariate statistical analysis. New York: John Wiley & Sons.
Behrens, J. H., Roig, S. M., & Silva, M. A. A. P. (2001) Aspectos de Funcionalidade, de Rotulagem e de Aceitação de Extrato Hidrossolúvel de Soja Fermentado e Culturas Lácteas Probióticas. Boletim SBCTA, 34(2), 99-106.
Braga, A. P., Ludermir, T. B., & Carvalho, A. C. P. L. F. (2007). Redes neurais artificiais: teoria e aplicações. Rio de Janeiro: LTC.
Camargos, T. V. C., Campos, N. S, Alves, G. F., Ferreira, S. C., & Matsuo, E. (2019). The effect of soil volume, plant density and sowing depth on soybean seedlings characters. Agronomy Science and Biotechnology, 5(2), 47. doi: 10.33158/ASB.2019v5i2p47
CONAB - Companhia Nacional de Abastecimento. (2021). Soja. Perspectivas para a agropecuária. Safra 2021-2022, edição grãos verão, v. 9, p. 71-84. Brasília, DF: CONAB.
CONAB - Companhia Nacional de Abastecimento. (2022). Acompanhamento da Safra Brasileira de Grãos. Safra 2021/22, v. 9, n. 6, sexto levantamento, março 2022. Brasília, DF: CONAB.
Cruz, C. D. (2013). GENES - a software package for analysis in experimental statistics and quantitative genetics. Acta Scientiarum. Agronomy, 35(3), 271-276. doi: 10.4025/actasciagron.v35i3.21251
Cruz, C. D., Ferreira, F. M., & Pessoni, L. A. (2011). Biometria aplicada ao estudo de diversidade genética. Visconde do Rio Branco, MG: Suprema.
Fehr, W.R., & Caviness, C.E. (1977) Stages of soybean development. Ames: Iowa State University of Science and Technology.
Hanyu, J., Costa, S. C., Cecon, P. R., & Matsuo, E. (2020). Genetic parameters estimate and characters analysis in phenotypic phase of soybean during two evaluation periods. Agronomy Science and Biotechnology, 6, 1-12. doi: 10.33158/ASB.r104.v6.2020
Hebb, D. O. (1949). The organization of behavior: a neuropsychological theory. New York, USA: Wiley.
Khatchatourian, O., & Padilha, F. R. R. (2008). Reconhecimento de variedades de soja por meio do processamento de imagens digitais usando redes neurais artificiais. Engenharia Agrícola, 28(4), 759-769. doi: 10.1590/S0100-69162008000400016
Matsuo, É., Sediyama, T., Cruz, C. D., Oliveira, R. C. T., & Cadore, L. R. (2012). Estimates of the genetic parameters, optimum sample size and conversion of quantitative data in multiple categories for soybean genotypes. Acta Scientiarum. Agronomy, 34(3), p. 265-273. doi: 10.4025/actasciagron.v34i3.14015
Nascimento, M., & Cruz, C.D.; (2018). Inteligência Computacional Aplicada ao Melhoramento Genético. Viçosa, MG: Editora UFV.
Nogueira, A. P. O., Sediyama, T., Cruz, C. D., Reis, M. S.; Pereira, D. G., & Jangarelli, M. (2008). Novas características para diferenciação de cultivares de soja pela análise discriminante. Ciência Rural, 38(9), 2427-2433. doi: 10.1590/S0103-84782008005000025
Nogueira, J. P. G., Campos, N. S., Camargos, R. V. C., Bomtempo, G. L., Ferreira, S. C., Cecon, P. R., Matsuo, E. (2019). Análises do diâmetro do hipocótilo em plantas de soja. Nucleus, 16(1), 373-384. doi: 10.3738/1982.2278.3551
Oda, M. C., Sediyama, T., Cruz, C. D., Nascimento, M., & Matsuo, E. (2021). Adaptability and yield stability of soybean genotypes by mean Eberhart and Russell methods, artificial neural networks and centroid. Agronomy Science and Biotechnology, 8, 1-13. doi:10.33158/ASB.r142.v8.2022
R Core Team. (2022). R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. URL https://www.R-project.org/.
Sant´Anna, I. C., Carneiro, V. Q., Ferreira, R. A. D. C., Silva, G. N., Nascimento, M., & Cruz, C. D. (2018). RNA-Aplicação em Estudos Classificatórios. In: Cruz, C. D., & Nascimento, M. (Eds.). Inteligência computacional aplicada ao melhoramento genético. p. 189-213. Viçosa, MG: Editora UFV.
Sediyama, T. (2009). Tecnologias de produção e usos da soja. Londrina, PR: Editora Mecenas.
Silva, A.R. (2021). Biotools: Tools for Biometry and Applied Statistics in Agricultural Science. R package version 4.2. Disponível em: <https://cran.r-project.org/package=biotools>
Silva, I. N., Spatti, D. H., & Flauzino. R. A. (2010). Redes neurais artificiais para engenharia e ciências aplicadas - curso prático. São Paulo, SP: Artliber Editora.
Sousa, I. C., Nascimento M., Sant’Anna, I. C., Caixeta, E. T., Azevedo, C. F., Cruz, C. D., Silva, F. L., Alkimin, E. R., Nascimentos, A. C. C., & Serrão, N. V. L. (2022). Marker effects and heritability estimates using additive-dominance genomic architectures via artificial neural networks in Coffea canephora. PLoS ONE, 17(1): e0262055. doi: 10.1371/journal.pone.0262055
Copyright (c) 2023 Agronomy Science and Biotechnology
This work is licensed under a Creative Commons Attribution 4.0 International License.
doi.org/10.33158/ASB