Examinando por Autor "Betancourt, Alejandro"
Mostrando 1 - 5 de 5
Resultados por página
Opciones de ordenación
Ítem An algorithmic approach for simulating realistic irregular lattices.(Universidad EAFIT, 2013-07-12) Duque, Juan C.; Betancourt, Alejandro; Marin, FreddyThere is a wide variety of computational experiments, or statistical simulations, in which regional scientists require regular and irregular lattices with a predefined number of polygons. While most commercial and free GIS software offer the possibility of generating regular lattices of any size, the generation of instances of irregular lattices is not a straightforward task. The most common strategy in this case is to find a real map that matches as closely as possible the required number of polygons. This practice is usually conducted without considering whether the topological characteristics of the selected map are close to those for an “average” map sampled in different parts of the world. In this paper, we propose an algorithm, RI-Maps, that combines fractal theory, stochastic calculus and computational geometry for simulating realistic irregular lattices with a predefined number of polygons. The irregular lattices generated with RI-Maps have guaranteed consistency in their topological characteristics, which reduces the potential distortions in the computational or statistical results due to an inappropriate selection of the lattices.Ítem Análisis de la distribución espacial de la reducción en la demanda de agua potable como efecto de políticas de ahorro en su consumo en el Área Metropolitana del Valle de Aburrá.(Universidad EAFIT, 2013-08-08) Duque, Juan C.; Gutiérrez, Diana C.; Betancourt, Alejandro; Patiño, JorgeEl presente estudio presenta un análisis, espacialmente desagregado, de la disminución en el consumo residencial de agua en el Área Metropolitana del Valle de Aburrá (AMVA) durante el periodo 2005 – 2010 e identificar las características socioeconómicas asociadas a estos patrones. Además, se analiza la forma cómo las políticas y campañas para incentivar la disminución del consumo de agua potable han sido acogidas en el AMVA. Los resultados obtenidos muestran claras diferencias espaciales (y por estrato) en los niveles de consumo de agua, así como en los niveles de reducción de dicho consumo en el período analizado. También, por medio de modelos de econometría espacial, se encuentra que las características socioeconómicas juegan un papel relevante a la hora de explicar los niveles de consumo de agua y que estos consumos presentan autocorrelación espacial sustantiva que indica que los niveles de consumo de agua potable en un área determinada no solo dependen de las características socioeconómicas del área, sino también de los niveles de consumo de las áreas vecinas. Por último, se encuentra que los impactos derivados del desincentivo económico al consumo excesivo, tiene un efecto inmediato que no perdura en el tiempoÍtem A computationally efficient method for delineating irregularly shaped spatial clusters(Springer Berlin Heidelberg, 2011-12-01) Duque, Juan C.; Aldstadt, Jared; Velasquez, Ermilson; Franco, Jose L.; Betancourt, Alejandro; Universidad EAFIT. Departamento de Economía y Finanzas; Research in Spatial Economics (RISE)In this paper, we present an efficiency improvement for the algorithm called AMOEBA, A Multidirectional Optimum Ecotope-Based Algorithm, devised by Aldstadt and Getis (Geogr Anal 38(4):327-343, 2006). AMOEBA embeds a local spatial autocorrelation statistic in an iterative procedure in order to identify spatial clusters (ecotopes) of related spatial units. We provide an analysis of the computational complexity of the original AMOEBA and develop an alternative formulation that reduces computational time without losing optimality. Empirical evidence is provided using georeferenced socio-demographic data in Accra, Ghana. © 2010 Springer-Verlag.Ítem Exploring the Potential of Machine Learning for Automatic Slum Identification from VHR Imagery(MDPI AG, 2017-09-01) Duque JC; Patiño, Jorge; Betancourt, Alejandro; Universidad EAFIT. Departamento de Economía y Finanzas; Research in Spatial Economics (RISE)Slum identification in urban settlements is a crucial step in the process of formulation of pro-poor policies. However, the use of conventional methods for slum detection such as field surveys can be time-consuming and costly. This paper explores the possibility of implementing a low-cost standardized method for slum detection. We use spectral, texture and structural features extracted from very high spatial resolution imagery as input data and evaluate the capability of three machine learning algorithms (Logistic Regression, Support Vector Machine and Random Forest) to classify urban areas as slum or no-slum. Using data from Buenos Aires (Argentina), Medellin (Colombia) and Recife (Brazil), we found that Support Vector Machine with radial basis kernel delivers the best performance (with F2-scores over 0.81). We also found that singularities within cities preclude the use of a unified classification model.Ítem Urban dynamics evaluation of Envigado city(Universidad EAFIT, 2012-06-15) Betancourt, Alejandro; Quintero, Luis Antonio