This article presents the Neo-Fuzzy-Neuron Modified by Kohonen Network (NFN-MK), an hybrid computational model that combines fuzzy system technique and artificial neural networks. Its main task consists in the automatic generation of membership functions, in particular, triangle forms, aiming a dynamic modeling of a system. The model is tested by simulating real systems, here represented by a nonlinear mathematical function. Comparison with the results obtained by traditional neural networks, and correlated studies of neurofuzzy systems applied in system identification area, shows that the NFN-MK model has a similar performance, despite its greater simplicity.
Cite
@article{arxiv.cs/0503078,
title = {Obtaining Membership Functions from a Neuron Fuzzy System extended by Kohonen Network},
author = {Angelo Luis Pagliosa and Claudio Cesar de Sa and Fernando D. Sasse},
journal= {arXiv preprint arXiv:cs/0503078},
year = {2007}
}
Comments
6 pages, 6 figures, 5th Congress of Logic Applied to Technology (LAPTEC 2005) Himeji, Japan, April 2-6, 2005