A CLASSIFIER SYSTEM USING SMOOTH GRAPH COLORING

Autor: JORGE FLORES CRUZ, PEDRO LARA VELÁZQUEZ, MIGUEL A. GUTIÉRREZ ANDRADE, SERGIO G. DE LOS COBOS SILVA, ERIC A. RINCÓN GARCÍA
Jazyk: English<br />Spanish; Castilian
Rok vydání: 2017
Předmět:
Zdroj: Revista de Matemática: Teoría y Aplicaciones, Vol 24, Iss 1, Pp 129-156 (2017)
Druh dokumentu: article
ISSN: 2215-3373
DOI: 10.15517/rmta.v24i1.27795
Popis: Unsupervised classifiers allow clustering methods with less or no human intervention. Therefore it is desirable to group the set of items with less data processing. This paper proposes an unsupervised classifier system using the model of soft graph coloring. This method was tested with some classic instances in the literature and the results obtained were compared with classifications made with human intervention, yielding as good or better results than supervised classifiers, sometimes providing alternative classifications that considers additional information that humans did not considered.
Databáze: Directory of Open Access Journals