Table 1.

Trial and error calculations for selecting the most suitable ANN.

Number of neurons in the hidden layer	Training data (RMSE)	Test data (RMSE)
5	0.0122	0.0316
7	0.0126	0.03
9	0.0125	0.0302
11	0.0121	0.0314
15	0.0115	0.0312
18	0.0118	0.0311
20	0.0116	0.0297
21	0.0119	0.0298
23	0.0129	0.0317
24	0.0141	0.0319
25	0.0132	0.0312