28
views
0
recommends
+1 Recommend
1 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      High-efficiency phenotyping for vitamin A in banana using artificial neural networks and colorimetric data Translated title: Fenotipagem de alta eficiência para vitamina A em banana utilizando redes neurais artificiais e dados colorimétricos

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          ABSTRACT Banana is one of the most consumed fruits in Brazil and an important source of minerals, vitamins and carbohydrates for human diet. The characterization of banana superior genotypes allows identifying those with nutritional quality for cultivation and to integrate genetic improvement programs. However, identification and quantification of the provitamin carotenoids are hampered by the instruments and reagents cost for chemical analyzes, and it may become unworkable if the number of samples to be analyzed is high. Thus, the objective was to verify the potential of indirect phenotyping of the vitamin A content in banana through artificial neural networks (ANNs) using colorimetric data. Fifteen banana cultivars with four replications were evaluated, totaling 60 samples. For each sample, colorimetric data were obtained and the vitamin A content was estimated in the ripe banana pulp. For the prediction of the vitamin A content by colorimetric data, multilayer perceptron ANNs were used. Ten network architectures were tested with a single hidden layer. The network selected by the best fit (least mean square error) had four neurons in the hidden layer, enabling high efficiency in prediction of vitamin A (r2 = 0.98). The colorimetric parameters a* and Hue angle were the most important in this study. High-scale indirect phenotyping of vitamin A by ANNs on banana pulp is possible and feasible.

          Translated abstract

          RESUMO A banana é uma das frutas mais consumidas no Brasil, sendo importante fonte de minerais, vitaminas e carboidratos na dieta humana. A caracterização de genótipos superiores de banana permite identificar aqueles com qualidade nutricional para cultivo e para integrar programas de melhoramento genético. Porém, a identificação e quantificação dos carotenoides provitamínicos são dificultadas pelo custo instrumental e dos reagentes químicos para as análises, podendo se tornar inviável caso o número de amostras a serem analisadas seja elevado. Assim, objetivou-se verificar o potencial da fenotipagem indireta do teor de vitamina A em banana por redes neurais artificiais (RNAs) utilizando-se dados colorimétricos. Foram avaliadas 15 cultivares de bananeira com quatro repetições, totalizando 60 amostras. Para cada amostra, foram obtidos dados colorimétricos, estimando-se o teor de vitamina A na polpa dos frutos maduros. Para a predição do teor de vitamina A por dados colorimétricos, utilizaram-se RNAs do tipo perceptron multicamadas. Foram testadas dez arquiteturas de rede com uma única camada intermediária. A rede selecionada pelo melhor ajuste (menor erro quadrático médio) teve quatro neurônios na camada intermediária, possibilitando alta eficiência na predição de vitamina A (r2 = 0,98). Os parâmetros colorimétricos a* e ângulo Hue foram os mais importantes neste estudo. A fenotipagem indireta em alta escala da vitamina A por meio de RNAs na polpa de banana é possível e viável.

          Related collections

          Most cited references28

          • Record: found
          • Abstract: not found
          • Article: not found

          Interaction of paclobutrazol and other growth regulators in the process of rhizogenesis in Ligustrum vulgare L.

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Interpreting neural‐network connection weights.

              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Neural Networks inRUsing the Stuttgart Neural Network Simulator:RSNNS

                Bookmark

                Author and article information

                Contributors
                Role: ND
                Role: ND
                Role: ND
                Journal
                brag
                Bragantia
                Bragantia
                Instituto Agronômico de Campinas
                1678-4499
                September 2016
                : 75
                : 3
                : 268-274
                Affiliations
                [1 ] Universidade Federal de Viçosa Brazil
                [2 ] Universidade Federal de Minas Gerais Brazil
                Article
                S0006-87052016000300268
                10.1590/1678-4499.467
                e971dae6-3ce2-4871-abec-0b97988461ee

                This work is licensed under a Creative Commons Attribution 4.0 International License.

                History
                Product

                SciELO Brazil

                Self URI (journal page): http://www.scielo.br/scielo.php?script=sci_serial&pid=0006-8705&lng=en
                Categories
                AGRICULTURE, MULTIDISCIPLINARY

                General agriculture
                Musa spp.,parâmetros colorimétricos,inteligência computacional,perceptron multicamadas,fenômica,colorimetric parameters,computational intelligence,multilayer perceptro,phenomic

                Comments

                Comment on this article