Mostrar el registro sencillo del ítem

dc.contributor.authorMillan-Valldeperas, Eva 
dc.contributor.authorBelmonte-Martinez, Maria Victoria 
dc.contributor.authorBoned-Purkiss, Francisco Javier 
dc.contributor.authorGavilanes-Velaz-de-Medrano, Juan 
dc.contributor.authorPerez-de-la-Cruz-Molina, Jose Luis 
dc.contributor.authorDíaz-López, Carmen
dc.date.accessioned2022-04-04T10:35:22Z
dc.date.available2022-04-04T10:35:22Z
dc.date.created2022
dc.date.issued2022
dc.identifier.citationEva Millán, María-Victoria Belmonte, Francisco-Javier Boned, Juan Gavilanes, José-Luis Pérez-de-la-Cruz, Carmen Díaz-López, Using machine learning techniques for architectural design tracking: An experimental study of the design of a shelter, Journal of Building Engineering, 2022, 104223es_ES
dc.identifier.urihttps://hdl.handle.net/10630/23912
dc.description.abstractIn this paper, we present a study aimed at tracking and analysing the design process. More concretely, we intend to explore whether some elements of the conceptual design stage in architecture might have an influence on the quality of the final project and to find and assess common solution pathways in problem-solving behaviour. In this sense, we propose a new methodology for design tracking, based on the application of data analysis and machine learning techniques to data obtained in snapshots of selected design instants. This methodology has been applied in an experimental study, in which fifty-two novice designers were required to design a shelter with the help of a specifically developed computer tool that allowed collecting snapshots of the project at six selected design instants. The snapshots were described according to nine variables. Data analysis and machine learning techniques were then used to extract the knowledge contained in the data. More concretely, supervised learning techniques (decision trees) were used to find strategies employed in higher-quality designs, while unsupervised learning techniques (clustering) were used to find common solution pathways. Results provide evidence that supervised learning techniques allow elucidating the class of the best projects by considering the order of some of the decisions taken. Also, unsupervised learning techniques can find several common problem-solving pathways by grouping projects into clusters that use similar strategies. In this way, our work suggests a novel approach to design tracking, using quantitative analysis methods that can complement and enrich the traditional qualitative approach.es_ES
dc.description.sponsorshipThis work has been partially funded by the Spanish Government, Agencia Estatal de Investigaci ́on (AEI), and the European Union, Fondo Europeo de Desarrollo Regional (FEDER), grant TIN2016-80774-R (AEI/FEDER, UE). Funding for open access charge: Universidad de Málaga/CBUA.es_ES
dc.language.isoenges_ES
dc.publisherElsevieres_ES
dc.rightsinfo:eu-repo/semantics/openAccesses_ES
dc.subjectAprendizaje automático (Inteligencia artificial)es_ES
dc.subjectDiseño arquitectónicoes_ES
dc.subject.otherMachine learninges_ES
dc.subject.otherDesign theoryes_ES
dc.subject.otherArchitectural projectses_ES
dc.subject.otherExperimental studyes_ES
dc.titleUsing machine learning techniques for architectural design tracking: an experimental study of the design of a shelteres_ES
dc.typeinfo:eu-repo/semantics/articlees_ES
dc.centroE.T.S.I. Informáticaes_ES
dc.identifier.doihttps://doi.org/10.1016/j.jobe.2022.104223.
dc.type.hasVersioninfo:eu-repo/semantics/publishedVersiones_ES


Ficheros en el ítem

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

Mostrar el registro sencillo del ítem