Examinando por Autor "Duque, J."

Mostrando 1 - 7 de 7
  • No hay miniatura disponible
    Ítem
    Automatic detection of building typology using deep learning methods on street level images
    (PERGAMON-ELSEVIER SCIENCE LTD, 2020-03-20) Duque, J.; Gonzalez, D.; Rueda Plata, Diego; Acevedo, A.; Ramos, R.; Betancourt, A.; García, S.; Universidad EAFIT. Departamento de Economía y Finanzas; Research in Spatial Economics (RISE)
    An exposure model is a key component for assessing potential human and economic losses from natural disasters. An exposure model consists of a spatially disaggregated description of the infrastructure and population of a region under study. Depending on the size of the settlement area, developing such models can be a costly and time-consuming task. In this paper we use a manually annotated dataset consisting of approximately 10,000 photos acquired at street level in the urban area of Medellín to explore the potential for using a convolutional neural network (CNN) to automatically detect building materials and types of lateral-load resisting systems, which are attributes that define a building's structural typology (which is a key issue in exposure models for seismic risk assessment). The results of the developed model achieved a precision of 93% and a recall of 95% when identifying nonductile buildings, which are the buildings most likely to be damaged in an earthquake. Identifying fine-grained material typology is more difficult, because many visual clues are physically hidden, but our model matches expert level performances, achieving a recall of 85% and accuracy scores ranging from 60% to 82% on the three most common building typologies, which account for 91% of the total building population in Medellín. Overall, this study shows that a CNN can make a substantial contribution to developing cost-effective exposure models. © 2020 Elsevier Ltd
  • No hay miniatura disponible
    Ítem
    Automatic detection of building typology using deep learning methods on street level images
    (PERGAMON-ELSEVIER SCIENCE LTD, 2020-03-20) Duque, J.; Gonzalez, D.; Rueda Plata, Diego; Acevedo, A.; Ramos, R.; Betancourt, A.; García, S.; Mecánica Aplicada
    An exposure model is a key component for assessing potential human and economic losses from natural disasters. An exposure model consists of a spatially disaggregated description of the infrastructure and population of a region under study. Depending on the size of the settlement area, developing such models can be a costly and time-consuming task. In this paper we use a manually annotated dataset consisting of approximately 10,000 photos acquired at street level in the urban area of Medellín to explore the potential for using a convolutional neural network (CNN) to automatically detect building materials and types of lateral-load resisting systems, which are attributes that define a building's structural typology (which is a key issue in exposure models for seismic risk assessment). The results of the developed model achieved a precision of 93% and a recall of 95% when identifying nonductile buildings, which are the buildings most likely to be damaged in an earthquake. Identifying fine-grained material typology is more difficult, because many visual clues are physically hidden, but our model matches expert level performances, achieving a recall of 85% and accuracy scores ranging from 60% to 82% on the three most common building typologies, which account for 91% of the total building population in Medellín. Overall, this study shows that a CNN can make a substantial contribution to developing cost-effective exposure models. © 2020 Elsevier Ltd
  • No hay miniatura disponible
    Ítem
    Automatic detection of building typology using deep learning methods on street level images
    (PERGAMON-ELSEVIER SCIENCE LTD, 2020-03-20) Duque, J.; Gonzalez, D.; Rueda Plata, Diego; Acevedo, A.; Ramos, R.; Betancourt, A.; García, S.; Duque, J.; Gonzalez, D.; Rueda Plata, Diego; Acevedo, A.; Ramos, R.; Betancourt, A.; García, S.; Universidad EAFIT. Departamento de Ingeniería de Producción; Materiales de Ingeniería
    An exposure model is a key component for assessing potential human and economic losses from natural disasters. An exposure model consists of a spatially disaggregated description of the infrastructure and population of a region under study. Depending on the size of the settlement area, developing such models can be a costly and time-consuming task. In this paper we use a manually annotated dataset consisting of approximately 10,000 photos acquired at street level in the urban area of Medellín to explore the potential for using a convolutional neural network (CNN) to automatically detect building materials and types of lateral-load resisting systems, which are attributes that define a building's structural typology (which is a key issue in exposure models for seismic risk assessment). The results of the developed model achieved a precision of 93% and a recall of 95% when identifying nonductile buildings, which are the buildings most likely to be damaged in an earthquake. Identifying fine-grained material typology is more difficult, because many visual clues are physically hidden, but our model matches expert level performances, achieving a recall of 85% and accuracy scores ranging from 60% to 82% on the three most common building typologies, which account for 91% of the total building population in Medellín. Overall, this study shows that a CNN can make a substantial contribution to developing cost-effective exposure models. © 2020 Elsevier Ltd
  • No hay miniatura disponible
    Ítem
    Institutional fragmentation and metropolitan coordination in Latin American cities: Are there links with city productivity?
    (Wiley-Blackwell, 2020-07-08) Duque, J.; Nancy Lozano-Gracia; Jorge E. Patino; Paula Restrepo Cadavid; Universidad EAFIT. Departamento de Economía y Finanzas; Research in Spatial Economics (RISE)
    This paper provides empirical evidence on the impact of institutional fragmentation and metropolitan coordination on urban productivity in Latin American Cities. The use of night-time lights satellite imagery and high resolution population data allow us to use a definition of metropolitan area based on the urban extents that result from the union between the formally defined metropolitan areas and the contiguous patches of urbanized areas with more than 500,000 inhabitants. Initial results suggest that the presence of multiple local governments within metropolitan areas generate opposite effects in urban productivity. On the one hand, smaller governments tend to be more responsive and efficient, which increases productivity. But, on the other hand, multiple local governments face co-ordination costs that result in lower productivity levels. © 2020 The Author(s). Regional Science Policy and Practice © 2020 RSAI
  • No hay miniatura disponible
    Ítem
    ParaVoxel: A domain decomposition based fixed grid preprocessor
    (WORLD SCIENTIFIC PUBL CO PTE LTD, 2015-06-01) Garcia, M.J.; Duque, J.; Henao, M.; Boulanger, P.; Mecánica Aplicada
    In this paper, a parallel cartesian fixed grid mesh generator for structural and fluid dynamics problems is presented. The method uses the boundary representation of a body and produces a set of equal sized cells which are classified in three different types according to its location with respect to the body. Cells are inside, outside or intersecting the boundary of the body. This classification is made by knowing the number of nodes of a cell that are inside body. That process is accomplished very efficiently as the nodes can be classified in batch. Once boundary cells are identified, its geometry is approximated by the convex hull of the nodes inside the body and the intersection points of the boundary against the cell edges. This paper presents the basics of the Fixed Grid Meshing algorithm, followed by some domain decomposition modifications and the data structures required for its parallel implementation. A set of examples and a brief discussion on the possibility of applying this algorithm together with other approaches is presented. © 2015 World Scientific Publishing Company.
  • No hay miniatura disponible
    Ítem
    Spatiotemporal Modeling of Urban Growth Using Machine Learning
    (MDPI AG, 2019-12-28) Duque, J.; Jorge E. Patino; Gomez, J.; Passos, S.; Universidad EAFIT. Departamento de Economía y Finanzas; Research in Spatial Economics (RISE)
    This paper presents a general framework for modeling the growth of three important variables for cities: population distribution, binary urban footprint, and urban footprint in color. The framework models the population distribution as a spatiotemporal regression problem using machine learning, and it obtains the binary urban footprint from the population distribution through a binary classifier plus a temporal correction for existing urban regions. The framework estimates the urban footprint in color from its previous value, as well as from past and current values of the binary urban footprint using a semantic inpainting algorithm. By combining this framework with free data from the Landsat archive and the Global Human Settlement Layer framework, interested users can get approximate growth predictions of any city in the world. These predictions can be improved with the inclusion in the framework of additional spatially distributed input variables over time subject to availability. Unlike widely used growth models based on cellular automata, there are two main advantages of using the proposed machine learning-based framework. Firstly, it does not require to define rules a priori because the model learns the dynamics of growth directly from the historical data. Secondly, it is very easy to train new machine learning models using different explanatory input variables to assess their impact. As a proof of concept, we tested the framework in Valledupar and Rionegro, two Latin American cities located in Colombia with different geomorphological characteristics, and found that the model predictions were in close agreement with the ground-truth based on performance metrics, such as the root-mean-square error, zero-mean normalized cross-correlation, Pearson's correlation coefficient for continuous variables, and a few others for discrete variables such as the intersection over union, accuracy, and the f1 metric. In summary, our framework for modeling urban growth is flexible, allows sensitivity analyses, and can help policymakers worldwide to assess different what-if scenarios during the planning cycle of sustainable and resilient cities. © 2019 by the authors.
  • No hay miniatura disponible
    Ítem
    Understanding cycling travel distance: The case of Medellin city (Colombia)
    (Elsevier Ltd., 2020-06-23) Duque, J.; Ospina, J.; Botero Ferna´ndez, Vero´nica; Brussel, Mark; Grigolon, Anna; Universidad EAFIT. Departamento de Economía y Finanzas; Research in Spatial Economics (RISE)
    The relevance of cycling as a mode of transportation is increasingly being recognized in many cities around the world, and the city of Medellin (Colombia) is no exception. To better understand cycling travel behavior in Medellin, we perform a multiple regression to analyze the importance of route characteristics in explaining cycling travel distance. We control for socioeconomic and built environment variables at the origin and destination. Our results reveal that the effects of the socio-economic and built environment characteristics at the origin and destination are modest or statistically insignificant in explaining travel distance. However, the variables that characterize the built and natural environment along the route are significant and appreciably improve the explanatory power of the baseline econometric model. An analysis of interacting effects shows that the interaction between the dedicated infrastructure along the route and the degree of deviation from direct routes has a relevant effect on explaining travel distance. The findings of this work are useful for designing cycling policy and developing more usable cycling infrastructure. © 2020 Elsevier Ltd