Classification and Prediction of Bee Honey Indirect Adulteration Using Physiochemical Properties Coupled with K-Means Clustering and Simulated Annealing-Artificial Neural Networks (SA-ANNs)

Table 6

Optimal configurations of MLP and RBF ANN architectures and topologies.

Network type	MLP	RBF
Number of nodes in hidden layers	7	10
Activation function in hidden layer	Hyperbolic tangent	Softmax
Training SSE	0.220	0.062
Training relative error	0.020	0.004
Validation SSE	0.096	0.073
Validation relative error	0.027	0.021
Training R^2	0.981	0.997
Validation R^2	0.987	0.990
Overall R^2	0.981	0.992