Weighted Decisions in a Fuzzy Random Forest.
Piero P. Bonissone, José Manuel Cadenas Figueredo, M. Carmen Garrido, Ramón Andrés Díaz, Raquel Martínez‐España · European Society for Fuzzy Logic and Technology Conference · 2009
A multi-classifier system - obtained by combining sev- eral individual classifiers - usually exhibits a better performance (precision) than any of the original classifiers. In this work we use a multi-classifier based on a forest of randomly generated fuzzy deci- sion trees (Fuzzy Random Forest), and we propose a new method to combine their decisions to obtain the final decision of the forest. The proposed combination is a weighted method based on the concept of local fusion and on the data set Out Of Bag (OOB) error. Keywords— combination methods, fuzzy trees, local fusion, multi-classifier, random forest