Learning to cluster urban areas: two competitive approaches and an empirical validation

Simple item page
dc.article.number62
dc.catalogadorpva
dc.contributor.authorVera Villa, Camila
dc.contributor.authorLucchini Wortzman, Francesca
dc.contributor.authorBro, Naim
dc.contributor.authorMendoza Rocha, Marcelo
dc.contributor.authorLöbel Díaz, Hans-Albert
dc.contributor.authorGutiérrez, Felipe
dc.contributor.authorDimter, Jan
dc.contributor.authorCuchacovic, Gabriel
dc.contributor.authorReyes, Axel
dc.contributor.authorValdivieso López, Hernán Felipe
dc.contributor.authorAlvarado Monardez, Nicolás
dc.contributor.authorToro, Sergio
dc.date.accessioned2023-03-06T15:15:03Z
dc.date.available2023-03-06T15:15:03Z
dc.date.issued2022
dc.date.updated2022-12-25T01:02:21Z
dc.description.abstractUrban clustering detects geographical units that are internally homogeneous and distinct from their surroundings. It has applications in urban planning, but few studies compare the effectiveness of different methods. We study two techniques that represent two families of urban clustering algorithms: Gaussian Mixture Models (GMMs), which operate on spatially distributed data, and Deep Modularity Networks (DMONs), which work on attributed graphs of proximal nodes. To explore the strengths and limitations of these techniques, we studied their parametric sensitivity under different conditions, considering the spatial resolution, granularity of representation, and the number of descriptive attributes, among other relevant factors. To validate the methods, we asked residents of Santiago, Chile, to respond to a survey comparing city clustering solutions produced using the different methods. Our study shows that DMON is slightly preferred over GMM and that social features seem to be the most important ones to cluster urban areas.
dc.fechaingreso.objetodigital2022-12-25
dc.format.extent22 páginas
dc.fuente.origenAutoarchivo
dc.identifier.citationEPJ Data Science. 2022 Dec 20;11(1):62
dc.identifier.doi10.1140/epjds/s13688-022-00374-2
dc.identifier.urihttps://doi.org/10.1140/epjds/s13688-022-00374-2
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/66528
dc.information.autorucEscuela de ingeniería ; Vera Villa, Camila ; S/I ; 1151914
dc.information.autorucEscuela de ingeniería ; Lucchini Wortzman, Francesca ; S/I ; 203806
dc.information.autorucEscuela de ingeniería ; Mendoza Rocha, Marcelo ; 0000-0002-7969-6041 ; 1237020
dc.information.autorucEscuela de ingeniería ; Löbel Díaz, Hans-Albert ; S/I ; 131278
dc.information.autorucEscuela de ingeniería ; Gutiérrez González, Felipe Iván ; S/I ; 186172
dc.information.autorucEscuela de ingeniería ; Cuchacovic, Gabriel ; S/I ; 185719
dc.information.autorucEscuela de ingeniería ; Valdivieso López, Hernán Felipe ; S/I ; 245906
dc.information.autorucEscuela de ingeniería ; Alvarado Monardez, Nicolás ; S/I ; 204444
dc.language.isoen
dc.nota.accesoContenido completo
dc.pagina.final22
dc.pagina.inicio1
dc.revistaEPJ Data Science
dc.rightsacceso abierto
dc.rights.holderThe Author(s)
dc.subjectUrban clusteringes_ES
dc.subjectGraph Neural Networkses_ES
dc.subjectGaussian Mixture Modelses_ES
dc.subject.ddc000
dc.subject.deweyCiencias de la computaciónes_ES
dc.titleLearning to cluster urban areas: two competitive approaches and an empirical validationes_ES
dc.typeartículo
dc.volumen11
sipa.codpersvinculados1151914
sipa.codpersvinculados203806
sipa.codpersvinculados1237020
sipa.codpersvinculados131278
sipa.codpersvinculados186172
sipa.codpersvinculados185719
sipa.codpersvinculados245906
sipa.codpersvinculados204444
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
13688_2022_Article_374.pdf
Size:
9.85 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
0 B
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos de revistas