Person:
Espínola Vílchez, María Rosario

Profile Picture
First Name
María Rosario
Last Name
Espínola Vílchez
URI
https://hdl.handle.net/20.500.14352/77448
Affiliation
Universidad Complutense de Madrid
Faculty / Institute
Estudios estadísticos
Department
Estadística y Ciencia de los Datos
Area
Estadística e Investigación Operativa
Identifiers
UCM identifierORCIDScopus Author IDWeb of Science ResearcherIDDialnet ID

Filters

20222
Reset filters

Settings

Start date: 2015 × Has files: false ×

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Explanation of machine learning classification models with fuzzy measures: an approach to individual classification
    (2022) Santos, Daniel; Gutiérrez García-Pardo, Inmaculada; Castro Cantalejo, Javier; Gómez González, Daniel; Guevara Gil, Juan Antonio; Espínola Vílchez, María Rosario; Kahraman, Cengiz; Tolga, A. Cagri; Onar, Sezi Cevik; Cebi, Selcuk; Oztaysi, Basar; Sari, Irem Ucal
    Abstract: In the field of Machine Learning, there is a common point in almost all methodologies about measuring the importance of features in a model: estimating the value of a collection of them in several situations where different information sources (features) are available. To establish the value of the response feature, these techniques need to know the predictive ability of some features over others. We can distinguish two ways of performing this allocation. The first does not pay attention to the available information of known characteristics, assigning a random allocation value. The other option is to assume that the feasible values for the unknown features have to be any of the values observed in the sample (in the known part of the database), assuming that the values of the known features are correct. Despite its interest, there is a serious problem of overfitting in this approach, in situations in which there is a continuous feature: the values of a continuous feature are not likely to occur in any other, so there is a large loss of randomization (there will surely be an insignificant number of records for each possible value). In this scenario, it is probably unrealistic to assume a perfect estimation. Then, in this paper we propose a new methodology based on fuzzy measures which allows the analysis and consideration of the available information in known features, avoiding the problem of overfitting in the presence of continuous features. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG
  • No Thumbnail Available
    Item
    A new community detection problem based on bipolar fuzzy measures
    (2022) Gutiérrez García-Pardo, Inmaculada; Gómez González, Daniel; Castro Cantalejo, Javier; Espínola Vílchez, María Rosario
    In social network research, one of the most important analysis is community detection. Fuzzy uncertainty appears clearly when modeling real situations by means of networks. Nevertheless, most of the algorithms used to detect communities in graphs represent them as something crisp. Due to its speed and efficiency, Louvain algorithm is one of the most popular methods used to find clusters in crisp networks. In this study, we propose a modification of it, based on the incorporation of a bipolar fuzzy measure defined over the nodes of the network. Our proposal is based on the use of the Shapley value, which is considered to measure the importance of each node.