Fuzzy Rule Base Design With Probabilistic Weights

Título: Fuzzy Rule Base Design With Probabilistic Weights

Autores: Melo, Leonardo G.; Lucas, Luís A.; Delgado, Myriam R.

Resumo: This paper proposes a simple and innovative method to design rule bases for inference systems by joining wellknown theories to treat uncertainty, such as probability and fuzzy systems. The rule base design is based on some modifications in the Wang-Mendel method in the sense that all the information obtained from the training set can be considered. The proposed method provides fuzzy rules where each consequent is determined in a probabilistic way. The resulting fuzzy system is applied in a classification problem and has its performance compared with a fuzzy classifier obtained by the original Wang-Mendel method. The results show that the design method being proposed outperforms the traditional WM method, especially when data is noisy.

Palavras-chave: Fuzzy Rules; Probabilistic Weights; Wang-Mendel Method; Automatic Rule Base Design; Classification Problem

Páginas: 8

Código DOI: 10.21528/CBIC2011-05.3

Artigo em pdf: st_05.3.pdf

Arquivo BibTex: st_05.3.bib