Implementation of Genetic Algorithm Integrated with the Deep Neural Network for Estimating at Completion Simulation

Table 8

The numerical evaluation indicators for the GA-SVR predictive model over the testing modeling phase.

Method	RMSE	MAE	MRE	NSE	SI	BIAS	WI
Model 1	0.0923	0.0571	0.3860	0.7473	0.5889	−0.0064	0.8710
Model 2	0.0847	0.5820	0.3972	0.7874	0.5401	−0.0016	0.8925
Model 3	0.0767	0.0468	0.4033	0.8254	0.4895	−0.0064	0.9106
Model 4	0.1014	0.0588	0.4669	0.6948	0.6471	−0.0001	0.8359
Model 5	0.1056	0.0641	0.6324	0.6772	0.6555	0.0074	0.8241
Model 6	0.1096	0.0652	0.5087	0.6523	0.6803	0.0244	0.8359
Model 7	0.1121	0.0629	0.7884	0.6271	0.7154	−0.0229	0.8187