JavaScript is disabled for your browser. Some features of this site may not work without it.

    Listar

    Todo RIUMAComunidades & ColeccionesPor fecha de publicaciónAutoresTítulosMateriasTipo de publicaciónCentrosEsta colecciónPor fecha de publicaciónAutoresTítulosMateriasTipo de publicaciónCentros

    Mi cuenta

    AccederRegistro

    Estadísticas

    Ver Estadísticas de uso

    DE INTERÉS

    Datos de investigaciónReglamento de ciencia abierta de la UMAPolítica de RIUMAPolitica de datos de investigación en RIUMASHERPA/RoMEODulcinea
    Preguntas frecuentesManual de usoDerechos de autorContacto/Sugerencias
    Ver ítem 
    •   RIUMA Principal
    • Investigación
    • Lenguajes y Ciencias de la Computación - (LCC)
    • LCC - Artículos
    • Ver ítem
    •   RIUMA Principal
    • Investigación
    • Lenguajes y Ciencias de la Computación - (LCC)
    • LCC - Artículos
    • Ver ítem

    Using machine learning techniques for architectural design tracking: an experimental study of the design of a shelter

    • Autor
      Millan-Valldeperas, EvaAutoridad Universidad de Málaga; Belmonte-Martinez, Maria VictoriaAutoridad Universidad de Málaga; Boned-Purkiss, Francisco JavierAutoridad Universidad de Málaga; Gavilanes-Velaz-de-Medrano, JuanAutoridad Universidad de Málaga; Perez-de-la-Cruz-Molina, Jose LuisAutoridad Universidad de Málaga; [et al.]
    • Fecha
      2022
    • Editorial/Editor
      Elsevier
    • Palabras clave
      Aprendizaje automático (Inteligencia artificial); Diseño arquitectónico
    • Resumen
      In 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.
    • URI
      https://hdl.handle.net/10630/23912
    • DOI
      https://dx.doi.org/https://doi.org/10.1016/j.jobe.2022.104223.
    • Compartir
      RefworksMendeley
    Mostrar el registro completo del ítem
    Ficheros
    1-s2.0-S2352710222002364-main.pdf (11.92Mb)
    Colecciones
    • LCC - Artículos

    Estadísticas

    Ver Estadísticas de uso
    REPOSITORIO INSTITUCIONAL UNIVERSIDAD DE MÁLAGA
    REPOSITORIO INSTITUCIONAL UNIVERSIDAD DE MÁLAGA
     

     

    REPOSITORIO INSTITUCIONAL UNIVERSIDAD DE MÁLAGA
    REPOSITORIO INSTITUCIONAL UNIVERSIDAD DE MÁLAGA