Supervised Classification Fuzzy Growing Hierarchical SOM

Authors:
Rafael Del-Hoyo;Nicolás Medrano;Bonifacio Martín-Del-Brio;Francisco José Lacueva-Pérez
Affiliations:
Instituto Tecnológico de Aragón, Zaragoza, Spain 50005;Departamento de Electrónica y Comunicaciones, University of Zaragossa, Zaragoza, Spain 50005;Departamento de Electrónica y Comunicaciones, University of Zaragossa, Zaragoza, Spain 50005;Instituto Tecnológico de Aragón, Zaragoza, Spain 50005
Venue:
HAIS '08 Proceedings of the 3rd international workshop on Hybrid Artificial Intelligence Systems
Year:
2008

Citing 5
Cited 1

Neural-Network-Based Fuzzy Logic Control and Decision System

IEEE Transactions on Computers - Special issue on artificial neural networks
Self-Organizing Maps

Self-Organizing Maps
An adaptive rule extraction with the fuzzy self-organizing map and a comparison with other methods

ISUMA '95 Proceedings of the 3rd International Symposium on Uncertainty Modelling and Analysis
Granular self-organizing map (grSOM) for structure identification

Neural Networks
Evolving fuzzy neural networks for supervised/unsupervised onlineknowledge-based learning

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Aggregate distance based clustering using fibonacci series-FIBCLUS

APWeb'11 Proceedings of the 13th Asia-Pacific web conference on Web technologies and applications

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper introduces a fuzzy-extension of the Kohonen Self Organizing Map model called Fuzzy Growing Hierarchical SOM that is able to extract Fuzzy rules in hierarchical way. The main idea of the FGHSOM is to provide an architecture that can be initialized with prior knowledge and without, and can be trained directly using SOM learning methods. The training is carried out using competitive methods in such a way that the learning result is interpretable in the form of linguistic fuzzy if-then rules and rules are organized in a tree-like structure. The structure allows increasing the information using parent/child relationships. The FGHSOM is successfully compared with different neuro-fuzzy algorithms in different classification problems.