Modeling and Synthesis of Computational Efficient Adaptive Neuro-Fuzzy Systems Based on Matlab

Authors:
Guillermo Bosque;Javier Echanobe;Inés Campo;José M. Tarela
Affiliations:
Department of Electronics and Telecommunications, University of the Basque Country, Bilbao, Spain 48012;Department of Electricity and Electronics, University of the Basque Country, Leioa, Spain 48940;Department of Electricity and Electronics, University of the Basque Country, Leioa, Spain 48940;Department of Electricity and Electronics, University of the Basque Country, Leioa, Spain 48940
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Year:
2008

Citing 7
Cited 0

Sugeno type controllers are universal controllers

Fuzzy Sets and Systems
Fuzzy Systems as Universal Approximators

IEEE Transactions on Computers
Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence

Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
A proposal of ubiquitous fuzzy computing for Ambient Intelligence

Information Sciences: an International Journal
An adaptive neuro-fuzzy system for efficient implementations

Information Sciences: an International Journal
Efficient Hardware/Software Implementation of an Adaptive Neuro-Fuzzy System

IEEE Transactions on Fuzzy Systems
An Experimental Study on Nonlinear Function Computation for Neural/Fuzzy Hardware Design

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

New potential applications for neural networks and fuzzy systems are emerging in the context of ubiquitous computing and ambient intelligence. This new paradigm demands sensitive and adaptive embedded systems able to deal with a large number of stimulus in an efficient way. This paper presents a design methodology, based on a new Matlab tool, to develop computational-efficient neuro-fuzzy systems. To fulfil this objective, we have introduced a particular class of adaptive neuro-fuzzy inference systems (ANFIS) with piecewise multilinear (PWM) behaviour. Results obtained show that the PWM-ANFIS model generates computational-efficient implementations without loss of approximation capabilities or learning performance. The tool has been used to develop both software and hardware approaches as well as special architectures for hybrid hardware/software embedded systems.