Microbial Decolorization of Triazo Dye, Direct Blue 71: An Optimization Approach Using Response Surface Methodology (RSM) and Artificial Neural Network (ANN)

Table 4

The effect of different neural network architecture and topologies on R² and AAD in the estimation of DB71 dye decolorization obtained in the training and testing of neural networks.

Network	Model	Learning algorithm	Connection type	Transfer function output	Transfer function hidden	Training set R^2	DC	Testing set R^2	DC
1	4.26.1	BBP	MNFF	Sigmoid	Tanh	0.999	0.980	0.999	0.950
2	4.26.1	BBP	MNFF	Tanh	Tanh	0.990	0.980	0.980	0.870
3	4.26.1	BBP	MNFF	Tanh	Sigmoid	0.991	0.982	0.900	0.790
4	4.26.1	BBP	MNFF	Sigmoid	Linear	0.98	0.97	0.99	0.900