Prediction of the hot asphalt mix properties using deep neural networks

Beni-Suef University Journal of Basic and Applied Sciences

Table 10 Comparison between the optimum ANN for every output and the optimum ANN for all predictions

	Optimum ANN for every output			R-value	Optimum ANN for all predictions			R-value	R-difference
	Hidden layers	Neurons/layer	Activation function	R-value	Hidden layers	Neurons/layer	Activation function	R-value	R-difference
OAC	3	16	Logistic	0.909	2	11	Linear	0.841	0.068
Stability	3	9	Tanh	0.795				0.753	0.042
Flow	2	15	Logistic	0.528				0.512	0.016
Density	2	11	Linear	0.653				0.653	0
AV	4	8	Tanh	0.768				0.714	0.054
VMA	4	7	Tanh	0.657				0.37	0.287