Table 2.

Various architecture of neural network and their criteria used in this study

Architecture	Layer number	Number of training cycles	Average error for training set	Average error for validation set
11-4-1	1	363	0.009987	0.008889
11-7-1	1	258	0.009941	0.009839
11-14-1	1	320	0.009998	0.009787
11-16-1	1	327	0.009981	0.008973
11-5-4-1	2	615	0.009987	0.009876
11-8-4-1	2	333	0.009924	0.00459
11-8-7-1	2	435	0.009932	0.009567
11-8-12-1	2	350	0.00996	0.00657
11-4-5-4-1	3	1259	0.09999	0.07789
11-8-4-4-1	3	1554	0.09999	0.09054
11-12-5-4-1	3	1198	0.08812	0.08639
11-12-7-3-1	3	947	0.06812	0.07687