Mostrar el registro sencillo del ítem

Exploring the Potential of Machine Learning for Automatic Slum Identification from VHE Imagery

dc.contributor.authorDuque, Juan Carlos
dc.contributor.authorPatino, Jorge Eduardo
dc.contributor.authorBetancourt, Alejandro
dc.coverage.spatialArgentinaen_US
dc.coverage.spatialBrasilen_US
dc.coverage.spatialColombiaen_US
dc.date.accessioned2016-11-25T15:25:43Z
dc.date.available2016-11-25T15:25:43Z
dc.date.issued2016-11-23
dc.identifier.citationDuque, J. C., Patino, J. E., & Betancourt, A. (2016, November 23). Exploring the Potential of Machine Learning for Automatic Slum Identification from VHE Imagery. Working Paper;N° 2016/13, Buenos Aires: CAF. Retrieved from https://scioteca.caf.com/handle/123456789/975en_GB
dc.identifier.urihttps://scioteca.caf.com/handle/123456789/975
dc.description.tableofcontentsSlum identification in urban settlements is a crucial step in the process of formulation of propoor policies. However, the use of conventional methods for slums detection such as field surveys may result 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 deliver the best performance (over 0.81). We also found that singularities within cities preclude the use of a unified classification model.en_US
dc.language.isoenen_US
dc.publisherCAFen_US
dc.relation.ispartofseriesWorking Paper;N° 2016/13
dc.rightsCC-BY-NCes_ES
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/es_ES
dc.subjectCiudadesen_US
dc.subjectDesarrollo urbanoen_US
dc.subjectEconomíaen_US
dc.subjectEquidad e inclusión socialen_US
dc.subjectGeorreferenciaciónen_US
dc.subjectInvestigación socioeconómicaen_US
dc.subjectPobrezaen_US
dc.subjectPolíticas públicasen_US
dc.subjectServicios públicosen_US
dc.subjectViviendaen_US
dc.titleExploring the Potential of Machine Learning for Automatic Slum Identification from VHE Imageryen_US
dc.typeworkingPaperen_US
dc.publisher.cityBuenos Airesen_US


Ficheros en el ítem

Thumbnail
Nombre:
Duque, Patino & Betancourt ...
Tamaño:
6.965Mb
Formato:
PDF
Descripción:
Exploring the Potential of Machine ...
Descargar

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem

CC-BY-NC
Excepto si se señala otra cosa, la licencia del ítem se describe como CC-BY-NC