Table 3. Comparison of the performance of Artificial Neural Networks (ANN) classifier with gradient descent back-propagation using hidden units {1, 2, 4, 8} and the momentum {0,0.2, 0.5} using 10-fold cross validation using SMOTE.

	H = 1			H = 2			H = 4			H = 8
	M = 0	M = 0.2	M = 0.5	M = 0	M = 0.2	M = 0.5	M = 0	M = 0.2	M = 0.5	M = 0	M = 0.2	M = 0.5
Sensitivity	59.30	50.06	51.44	49.77	51.33	42.21	30.06	32.29	62.05	51.38	56.41	37.49
Specificity	64.34	73.22	71.68	72.45	71.52	79.07	88.00	85.04	57.74	73.50	66.83	82.34
Precision	47.24	50.16	49.44	49.30	49.25	52.05	57.43	53.75	44.15	51.07	47.79	53.33
F-score	52.59	50.11	50.42	49.53	50.27	46.61	39.46	40.34	51.59	51.22	51.74	44.03
AUC	0.66	0.66	0.65	0.66	0.66	0.67	0.67	0.67	0.66	0.67	0.67	0.67
RMSE	0.47	0.47	0.47	0.47	0.47	0.46	0.46	0.46	0.47	0.47	0.47	0.47