Step 3: Decision makers will assign fuzzy neutrosophic numbers (FNNs
) to each multiple valued linguistic variables.
The fusion of fuzzy logic controllers and artificial neural networks results in FNNs
Various metaheuristic optimization methods have been used to train FNNs
. GA, inspired by Darwinians' theory of evolution and natural selection , is one of the earliest methods for training FNNs
that proposed by Montana and Davis .
This study proposed a method based on DST and fuzzy neural network (FNN
)  to recognize fatigue driving.
The author experimentally evaluates the ability of the proposed FPSO by applying it to evolution of FNNs
, in the same manner as in .
On the other hand, an FNN
can give good results for small hidden neuron number.
In this section, a fuzzy neural network (FNN
), which is used to estimate unknown functions a(x) and b(x), is described.
Buckley and Hayashi (1994) have analyzed new findings in the learning algorithm and its applications for FNN
emphasized in the above, is suitable only for numerical data.
of Model PI E_PI rules Regression model 17.68 19.23 Hybrid FS-FNNs  2.806 5.164 Hybrid FR-FNNs  0.080 0.190 Multi-FNN  0.720 2.205 Hybrid rule-based FNNs
 3.725 5.291 SOFPNN  0.012 0.094 Choi's model  0.012 0.067 18 HFC-PGA model  0.006 0.027 16 Our model PSO+IG 0.035 0.297 16 SSA+IG Sequential tuning 0.0179 0.0845 16 Simultaneous tuning 0.0038 0.0187 16 Table.
Fuzzy neural network (FNN
) can combine the advantages of both fuzzy logic in processing vague information and neural network in good learning abilities .
Ko, "A genetic-fuzzy-neuro model encodes FNNs
using SWRM and BRM," Engineering Applications of Artificial Intelligence, vol.
In addition, a fuzzy neural network (FNN
) is capable of fuzzy reasoning in handling uncertain information and artificial neural networks for learning from processes.