Relevancia y calidad en sistemas de clasificación borrosaun enfoque algebraico

  1. Castiblanco Ruiz, Fabian Alberto
Dirigida per:
  1. Francisco Javier Montero de Juan Director
  2. Camilo Andrés Franco de los Ríos Director/a
  3. Juan Tinguaro Rodríguez González Director

Universitat de defensa: Universidad Complutense de Madrid

Fecha de defensa: 26 de de gener de 2021

Tribunal:
  1. Matilde Santos Peñas Presidenta
  2. Daniel Gómez González Secretari
  3. Vincenzo Cutello Vocal
  4. Fabio A. González Osorio Vocal
  5. Ana Isabel del Amo Blanco Vocal
Departament:
  1. Estadística e Investigación Operativa

Tipus: Tesi

Teseo: 155176 DIALNET

Resum

Fuzzy cluster validation is an open problem with several perspectives for study. This doctoral thesis addresses the problem of determining the quality of fuzzy partitionsin unsupervised classification processes. For this purpose, criteria and indexes have been proposed that allow determining quality and high-quality fuzzy partitions, the relevance of a class or family of classes in a given fuzzy partition and, the optimal number of classes of a partition according to some characteristics studied.The proposal uses tools from abstract algebra such as group theory, particularly the theory of fuzzy subgroups, matrices of relations and the characteristic polynomials of such matrices. The theoretical results were applied and validated in the image segmentation problem...