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

      Evaluación del uso de Redes Bayesianas Dinámicas para la predicción del avance de la Sigatoka negra y la productividad en cultivos agrícolas Translated title: Evaluation of Dynamic Bayesians Networks for predicting the progress of the Black Sigatoka and the productivity in crops

      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

          Resumen Los Modelos Gráficos Probabilísticos (MGP) utilizan una representación basada en grafos para codificar de manera compacta distribuciones complejas en espacios de alta dimensionalidad. Un tipo de MGP son las Redes Bayesianas Dinámicas (RBDs) que se caracterizan por ser un sistema estacionario homogéneo, lo que permite que con ellas se pueden representar, de una manera compacta, grandes cantidades de información de muchas variables. En este trabajo se estudia la capacidad de predicción de las RBDs en cuanto al avance de la Sigatoka negra y la productividad del cultivo, utilizando los datos proporcionados por CORBANA. Estos datos tienen información histórica del clima y de dos fenómenos: el avance de la enfermedad denominada Sigatoka negra y la productividad del cultivo del banano. Para esto se comparó la capacidad de predicción de la RBDs con la de las Redes Bayesianas (RBs). Se diseñaron e implementaron una RBD y una RB que representan las relaciones encontradas en los datos, y con ellas se llevaron a cabo experimentos para identificar cómo los distintos factores inciden en la capacidad de predicción de las mismas. Los resultados obtenidos en los experimentos mostraron que la capacidad de predicción de las RBDs no supera la de las RBs utilizando los datos de la Corporación Nacional Bananera. De hecho, no se observó una diferencia significativa entre ambos tipos de red. Además, se observó gran diferencia en las ventajas teóricas del modelo de las RBDs frente a otros MGPs. Ya que en la práctica las limitaciones de las implementaciones disponibles hacen que no sea atractivo su uso.

          Translated abstract

          Abstract The Probabilistic Graphical Models (PGM) use a representation based on graphs to encode complex distributions in high dimensional spaces compactly. One type of PGM are the Dynamic Bayesian Networks (DBN) characterized for being a stationary and homogeneous system, allowing to represent huge amount of information of multiple variables in a compact way. In this paper the prediction capacity of the DBN on the evolution of the Black Sigatoka and the crops productivity, using the data from CORBANA is studied. This data contains historical information of the weather and of two phenomena: the evolution of the Black Sigatoka and the productivity of the crops. The prediction capacity of the DBN was compare with the Bayesian Networks (BN). A DBN and a BN were design and implemented representing the variables found on the data and their relations. Using them different experiments were done to determine the influence of the factors on their capacity of prediction. The obtained results on the experiments showed that the prediction capacity of the DBNs is not better that the prediction capacity of the BN using the data from CORBANA. In fact, there was not a significant difference when the network was changed. Although the DBN presented several theoretical advantages in comparison with other PGMs, in practice they were not observed. This happened because of the limitations of the available implementation of framework for using PGMs, making the DBNs not as attractive.

          Related collections

          Most cited references14

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

          The bayes net toolbox for matlab

            Bookmark
            • Record: found
            • Abstract: not found
            • Book: not found

            A language and environment for statistical computing

            (2017)
              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Mathematical modeling for active and dynamic diagnosis of crop diseases based on Bayesian networks and incremental learning

                Bookmark

                Author and article information

                Journal
                tem
                Revista Tecnología en Marcha
                Tecnología en Marcha
                Instituto Tecnológico de Costa Rica (Cartago, Cartago, Costa Rica, Costa Rica )
                0379-3982
                0379-3982
                December 2019
                : 32
                : 4
                : 158-170
                Affiliations
                [3] orgnameCorporación Bananera Nacional S.A. (CORBANA Costa Rica jguzman@ 123456corbana.co.cr
                [1] orgnameInstituto Tecnológico de Costa Rica orgdiv1Maestría en Computación. Programa Multidisciplinar eScience Costa Rica lcalvo@ 123456itcr.ac.cr
                [4] orgnameCorporación Bananera Nacional S.A. (CORBANA Costa Rica mguzman@ 123456corbana.co.cr
                [5] orgnameCorporación Bananera Nacional S.A. (CORBANA Costa Rica mgonzalez@ 123456corbana.co.cr
                [2] orgnameInstituto Tecnológico de Costa Rica orgdiv1Maestría en Computación Costa Rica sebastian.arguello@ 123456gmail.com
                Article
                S0379-39822019000400158 S0379-3982(19)03200400158
                10.18845/tm.v32i4.4800
                db7b5cda-460e-4c55-b4e5-33ba47237070

                This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 International License.

                History
                : 03 February 2019
                : 02 November 2018
                Page count
                Figures: 0, Tables: 0, Equations: 0, References: 14, Pages: 13
                Product

                SciELO Costa Rica

                Categories
                Artículo

                Redes Bayesianas,Modelos Gráficos Probabilísticos,Dynamic Bayesian Networks,Redes Bayesianas Dinámicas,Probabilistic graphical Models.,Bayesian Networks

                Comments

                Comment on this article

                scite_
                0
                0
                0
                0
                Smart Citations
                0
                0
                0
                0
                Citing PublicationsSupportingMentioningContrasting
                View Citations

                See how this article has been cited at scite.ai

                scite shows how a scientific paper has been cited by providing the context of the citation, a classification describing whether it supports, mentions, or contrasts the cited claim, and a label indicating in which section the citation was made.

                Similar content186

                Most referenced authors107