Examinando por Materia "socioeconomics"

Mostrando 1 - 2 de 2
  • No hay miniatura disponible
    Ítem
    Remote sensing-based measurement of Living Environment Deprivation: Improving classical approaches with machine learning
    (Public Library of Science, 2017-05-02) Arribas-Bel D; Patino JE; Duque JC; Universidad EAFIT. Departamento de Economía y Finanzas; Research in Spatial Economics (RISE)
    This paper provides evidence on the usefulness of very high spatial resolution (VHR) imagery in gathering socioeconomic information in urban settlements. We use land cover, spectral, structure and texture features extracted from a Google Earth image of Liverpool (UK) to evaluate their potential to predict Living Environment Deprivation at a small statistical area level. We also contribute to the methodological literature on the estimation of socioeconomic indices with remote-sensing data by introducing elements from modern machine learning. In addition to classical approaches such as Ordinary Least Squares (OLS) regression and a spatial lag model, we explore the potential of the Gradient Boost Regressor and Random Forests to improve predictive performance and accuracy. In addition to novel predicting methods, we also introduce tools for model interpretation and evaluation such as feature importance and partial dependence plots, or cross-validation. Our results show that Random Forest proved to be the best model with an R2 of around 0.54, followed by Gradient Boost Regressor with 0.5. Both the spatial lag model and the OLS fall behind with significantly lower performances of 0.43 and 0.3, respectively. © 2017 Arribas-Bel et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
  • No hay miniatura disponible
    Ítem
    Simulación del nivel de eliminación de sarampión y rubéola según la estratificación e interacción social
    (Universidad Nacional de Colombia, 2010-01-01) Hincapié-Palacio, D.; Ospina-Giraldo, J.; Gómez-Arias, R.D.; Uyi-Afuwape, A.; Chowell-Puente, G.; Hincapié-Palacio, D.; Ospina-Giraldo, J.; Gómez-Arias, R.D.; Uyi-Afuwape, A.; Chowell-Puente, G.; Universidad EAFIT. Departamento de Ciencias; Lógica y Computación
    Objective The study was aimed at comparing measles and rubella disease elimination levels in a homogeneous and heterogeneous population according to socioeconomic status with interactions amongst low- and high-income individuals and diversity in the average number of contacts amongst them. Methods Effective reproductive rate simulations were deduced from a susceptibleinfected-recovered (SIR) mathematical model according to different immunization rates using measles (1980 and 2005) and rubella (1998 and 2005) incidence data from Latin-America and the Caribbean. Low- and high-income individuals' social interaction and their average number of contacts were analysed by bipartite random network analysis. MAPLE 12 (Maplesoft Inc, Ontario Canada) software was used for making the simulations. Results The progress made in eliminating both diseases between both periods of time was reproduced in the socially-homogeneous population. Measles (2005) would be eliminated in high- and low-income groups; however, it would only be achieved in rubella (2005) if there were a high immunity rate amongst the low-income group. If the average number of contacts were varied, then rubella would not be eliminated, even with a 95 % immunity rate. Conclusion Monitoring the elimination level in diseases like measles and rubella requires that socio-economic status be considered as well as the population's interaction pattern. Special attention should be paid to communities having diversity in their average number of contacts occurring in confined spaces such as displaced communities, prisons, educational establishments, or hospitals.