Universidad de Burgos RIUBU Principal Default Universidad de Burgos RIUBU Principal Default
  • español
  • English
  • français
  • Deutsch
  • português (Brasil)
  • italiano
Universidad de Burgos RIUBU Principal Default
  • Ayuda
  • Contact Us
  • Send Feedback
  • Acceso abierto
    • Archivar en RIUBU
    • Acuerdos editoriales para la publicación en acceso abierto
    • Controla tus derechos, facilita el acceso abierto
    • Sobre el acceso abierto y la UBU
    • español
    • English
    • français
    • Deutsch
    • português (Brasil)
    • italiano
    • español
    • English
    • français
    • Deutsch
    • português (Brasil)
    • italiano
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of RIUBUCommunities and CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Statistics

    View Usage Statistics

    Compartir

    View Item 
    •   RIUBU Home
    • E-Prints
    • Untitled
    • Untitled
    • Untitled
    • View Item
    •   RIUBU Home
    • E-Prints
    • Untitled
    • Untitled
    • Untitled
    • View Item

    Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10259/6207

    Título
    Rotation Forest for Big Data
    Autor
    Juez Gil, Mario
    Arnaiz González, ÁlvarUBU authority Orcid
    Rodríguez Diez, Juan JoséUBU authority
    López Nozal, CarlosUBU authority Orcid
    García Osorio, CésarUBU authority Orcid
    Publicado en
    Information Fusion. 2021, V. 74, p. 39-49
    Editorial
    Elsevier
    Fecha de publicación
    2021-10
    ISSN
    1566-2535
    DOI
    10.1016/j.inffus.2021.03.007
    Abstract
    The Rotation Forest classifier is a successful ensemble method for a wide variety of data mining applications. However, the way in which Rotation Forest transforms the feature space through PCA, although powerful, penalizes training and prediction times, making it unfeasible for Big Data. In this paper, a MapReduce Rotation Forest and its implementation under the Spark framework are presented. The proposed MapReduce Rotation Forest behaves in the same way as the standard Rotation Forest, training the base classifiers on a rotated space, but using a functional implementation of the rotation that enables its execution in Big Data frameworks. Experimental results are obtained using different cloud-based cluster configurations. Bayesian tests are used to validate the method against two ensembles for Big Data: Random Forest and PCARDE classifiers. Our proposal incorporates the parallelization of both the PCA calculation and the tree training, providing a scalable solution that retains the performance of the original Rotation Forest and achieves a competitive execution time (in average, at training, more than 3 times faster than other PCA-based alternatives). In addition, extensive experimentation shows that by setting some parameters of the classifier (i.e., bootstrap sample size, number of trees, and number of rotations), the execution time is reduced with no significant loss of performance using a small ensemble.
    Palabras clave
    Rotation Forest
    Random Forest
    Ensemble learning
    Machine learning
    Big Data
    Spark
    Materia
    Informática
    Computer science
    URI
    http://hdl.handle.net/10259/6207
    Versión del editor
    https://doi.org/10.1016/j.inffus.2021.03.007
    Collections
    • Untitled
    Attribution-NonCommercial-NoDerivatives 4.0 Internacional
    Documento(s) sujeto(s) a una licencia Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 Internacional
    Files in this item
    Nombre:
    Juez-if_2021.pdf
    Tamaño:
    1.532Mb
    Formato:
    Adobe PDF
    Thumbnail
    FilesOpen

    Métricas

    Citas

    Academic Search
    Ver estadísticas de uso

    Export

    RISMendeleyRefworksZotero
    • edm
    • marc
    • xoai
    • qdc
    • ore
    • ese
    • dim
    • uketd_dc
    • oai_dc
    • etdms
    • rdf
    • mods
    • mets
    • didl
    • premis
    Show full item record