Documento de trabajo de investigación
URI permanente para esta colección
Examinar
Examinando Documento de trabajo de investigación por Materia "Artificial Intelligence"
Mostrando 1 - 3 de 3
Resultados por página
Opciones de ordenación
Ítem Artificial Intelligence for Modelling Dengue Transmission in Bello(Universidad EAFIT, 2014) Lobo, Elisabet; Quintero, O.L.; Universidad EAFIT. Escuela de Ciencias. Grupo de Investigación Modelado MatemáticoÍtem Colombian Energy Market: An approach of Anfis and Clustering Techniques to an Optimal Portfolio(Universidad EAFIT, 2014) Palacios, Alejandro; Giraldo, Marcela; Quintero, O. L.; Universidad EAFIT. Escuela de Ciencias. Grupo de Investigación Modelado MatemáticoThis paper focuses on the study of a first approach to an optimal portfolio in the Colombian Energy Market using Artificial Intelligence. Specifically, ANFIS and Clustering techniques are applied. The methodology is implemented using the Matlab Toolboxes for clustering and FIS generation. Te results are presented, as well as the analysis of them. A first approximation to an optimal portfolio obtained with this methodology is shown. Consequently, some conclusions of the different techniques available for the same purpose are discussed. Finally the future work is proposed.Ítem Colombian Energy Market: Optimal Portfolio(Universidad EAFIT, 2014) Palacios, Alejandro; Giraldo, Marcela; Quintero, O. L.; Universidad EAFIT. Escuela de Ciencias. Grupo de Investigación Modelado MatemáticoThis paper focuses on the study of an optimal portfolio in the Colombian Energy Market using the Artificial Intelligence techniques specifically, Fuzzy Modeling and Neural Networks. The methodology at first, is implemented using the Matlab Fuzzy Logic Toolbox and with the help of a script the process is automatized. Secondly, a Neural Network is implemented in Matlab and its results are compared with the ones obtained in the Matlab Neural Network Toolbox. The results of the Fuzzy model and the Neural Network are presented and conclusions of both techniques are discussed. Finally possible future work are proposed.