A cost-sensitive learning algorithm for fuzzy rule-based classifiers.

Título inglés	A cost-sensitive learning algorithm for fuzzy rule-based classifiers.
Título español	Un algoritmo de aprendizaje sensible al coste para clasificadores basados en reglas difusas.
Autor/es	Beck, S. ; Mikut, Ralf ; Jäkel, Jens
Organización	Inst. Appl. Comput. Sci. Forsch. Karlsruhe, Karlsruhe, Alemania
Revista	1134-5632
Publicación	2004, 11 (2-3): 179-195, 26 Ref.
Tipo de documento	articulo
Idioma	Inglés
Resumen inglés	Designing classifiers may follow different goals. Which goal to prefer among others depends on the given cost situation and the class distribution. For example, a classifier designed for best accuracy in terms of misclassifications may fail when the cost of misclassification of one class is much higher than that of the other. This paper presents a decision-theoretic extension to make fuzzy rule generation cost-sensitive. Furthermore, it will be shown how interpretability aspects and the costs of feature acquisition can be accounted for during classifier design. Natural language text is used to explain the generated fuzzy rules and their design process.
Clasificación UNESCO	120903 ; 110208
Palabras clave español	Algoritmos de aprendizaje ; Algoritmos de clasificación ; Lógica difusa
Código MathReviews	MR2139295
Código Z-Math	Zbl 1105.68363
Acceso al artículo completo