Neuro-fuzzy Approach - Computational Intelligence in Time Series Forecasting - page 218

synergism of integrating neural networks with fuzzy logic technology into a hybrid
functional system with low-level learning and high-level reasoning transforms the
burden of the tedious design problems of the fuzzy logic decision systems to the
learning of connectionist neural networks. In this way the approximation capability
and the overall performance of the resulting system are enhanced.
A number of different schemes and architectures of this hybrid system have
been proposed, such as fuzzy-logic-based neurons (Pedrycz, 1995), fuzzy neurons
(Gupta, 1994), neural networks with fuzzy weights (Buckley and Hayashi, 1994),
neuro-fuzzy adaptive models (Brown and Harris, 1994), etc . The proposed
architectures have been successful in solving various engineering and real-world
problems, such as in applications like system identification and modelling, process
control, systems diagnosis, cognitive simulation, classification, pattern recognition,
image processing, engineering design, financial trading, signal processing, time
series prediction and forecasting, etc .

6.2 Neuro-fuzzy Modelling

There are several methods for implementing the neuro-fuzzy modelling technique.
An early merging approach was to replace the input-output signals or the weights
in neural networks by membership values of fuzzy sets, along with the application
of fuzzy neurons (Mitra and Hayashi, 2000). Several authors have proposed an
internal structure for fuzzy neurons (Gupta, 1994; Buckley and Hayashi, 1995), as
presented in the following section.

NN-outputs

Fuzzy
Inference

Neural
Network

Perception
as Neural
Inputs

Neural
output

NN-Learning
Algorithm

Linguistic
Statements

Figure 6.1. (a) Fuzzy-neural system (first model)

In general, neuro-fuzzy hybridization is done in two ways (Mitra and Hayashi,
2000):

x a neural network equipped with the capability of handling fuzzy

information processing, termed a fuzzy-neural network (FNN)

x a fuzzy system augmented by neural networks to enhance some of its

characteristics, like flexibility, speed, and adaptability, termed a neural-
fuzzy system (NFS).

Neural networks with fuzzy neurons are also termed FNN, because they are also
capable of processing fuzzy information. A neural-fuzzy system (NFS), on the
other hand, is designed to realize the process of fuzzy reasoning, where the