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

Beck, S., Mikut, Ralf, and Jäkel, Jens. "A cost-sensitive learning algorithm for fuzzy rule-based classifiers.." Mathware and Soft Computing 11.2-3 (2004): 179-195. <http://eudml.org/doc/39014>.

@article{Beck2004,
abstract = {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.},
author = {Beck, S., Mikut, Ralf, Jäkel, Jens},
journal = {Mathware and Soft Computing},
keywords = {Algoritmos de aprendizaje; Algoritmos de clasificación; Lógica difusa},
language = {eng},
number = {2-3},
pages = {179-195},
title = {A cost-sensitive learning algorithm for fuzzy rule-based classifiers.},
url = {http://eudml.org/doc/39014},
volume = {11},
year = {2004},
}

TY - JOUR
AU - Beck, S.
AU - Mikut, Ralf
AU - Jäkel, Jens
TI - A cost-sensitive learning algorithm for fuzzy rule-based classifiers.
JO - Mathware and Soft Computing
PY - 2004
VL - 11
IS - 2-3
SP - 179
EP - 195
AB - 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.
LA - eng
KW - Algoritmos de aprendizaje; Algoritmos de clasificación; Lógica difusa
UR - http://eudml.org/doc/39014
ER -