• Login
    View Item 
    •   Academica-e
    • Departamentos y Centros - Sailak eta Ikastegiak
    • ISC - Institute of Smart Cities
    • Artículos de revista ISC - ISC aldizkari artikuluak
    • View Item
    •   Academica-e
    • Departamentos y Centros - Sailak eta Ikastegiak
    • ISC - Institute of Smart Cities
    • Artículos de revista ISC - ISC aldizkari artikuluak
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Unsupervised fuzzy measure learning for classifier ensembles from coalitions performance

    Thumbnail
    View/Open
    2020060143_Uriz_UnsupervisedFuzzy.pdf (3.432Mb)
    Date
    2020
    Author
    Uriz Martín, Mikel Xabier Upna
    Paternain Dallo, Daniel Upna
    Domínguez Catena, Iris 
    Bustince Sola, Humberto Upna
    Galar Idoate, Mikel Upna
    Version
    Acceso abierto / Sarbide irekia
    xmlui.dri2xhtml.METS-1.0.item-type
    Artículo / Artikulua
    Version
    Versión publicada / Argitaratu den bertsioa
    Project Identifier
    ES/1PE/TIN2016-77356-P 
    Impact
     
     
     
    10.1109/ACCESS.2020.2980949
     
     
     
    Show full item record
    Abstract
    In Machine Learning an ensemble refers to the combination of several classifiers with the objective of improving the performance of every one of its counterparts. To design an ensemble two main aspects must be considered: how to create a diverse set of classifiers and how to combine their outputs. This work focuses on the latter task. More specifically, we focus on the usage of aggregation functi ... [++]
    In Machine Learning an ensemble refers to the combination of several classifiers with the objective of improving the performance of every one of its counterparts. To design an ensemble two main aspects must be considered: how to create a diverse set of classifiers and how to combine their outputs. This work focuses on the latter task. More specifically, we focus on the usage of aggregation functions based on fuzzy measures, such as the Sugeno and Choquet integrals, since they allow to model the coalitions and interactions among the members of the ensemble. In this scenario the challenge is how to construct a fuzzy measure that models the relations among the members of the ensemble. We focus on unsupervised methods for fuzzy measure construction, review existing alternatives and categorize them depending on their features. Furthermore, we intend to address the weaknesses of previous alternatives by proposing a new construction method that obtains the fuzzy measure directly evaluating the performance of each possible subset of classifiers, which can be efficiently computed. To test the usefulness of the proposed fuzzy measure, we focus on the application of ensembles for imbalanced datasets. We consider a set of 66 imbalanced datasets and develop a complete experimental study comparing the reviewed methods and our proposal. [--]
    Subject
    Fuzzy measures, Choquet integral, Aggregation, Ensembles, Classification
     
    Publisher
    IEEE
    Published in
    IEEE Access, 2020, 8, 52288-52305
    Departament
    Universidad Pública de Navarra / Nafarroako Unibertsitate Publikoa. ISC - Institute of Smart Cities
    Publisher version
    https://doi.org/10.1109/ACCESS.2020.2980949
    URI
    https://hdl.handle.net/2454/37293
    Sponsorship
    This work was supported in part by the Spanish Ministry of Science and Technology (AEI/FEDER, UE) under Project TIN2016-77356-P, and in part by the Public University of Navarra under Project PJUPNA13.
    Appears in Collections
    • Artículos de revista - Aldizkari artikuluak [2947]
    • Artículos de revista ISC - ISC aldizkari artikuluak [208]
    Items in Academica-e are protected by copyright with all rights reserved, unless otherwise noted.

     © Universidad Pública de Navarra - Nafarroako Unibertsitate Publikoa
         Repositorio basado en DSpace

    Contact Us | Send Feedback
     

     

    Browse

    All of Academica-eCommunities & CollectionsAuthorsAuthors By Issue DateTitlesSubjectsBy DegreeThis CollectionAuthorsAuthors By Issue DateTitlesSubjectsBy Degree

    My Account

    LoginRegister

    Statistics

    View Usage Statistics

     © Universidad Pública de Navarra - Nafarroako Unibertsitate Publikoa
         Repositorio basado en DSpace

    Contact Us | Send Feedback