Table 7 Comparison of the performance of Artificial Neural Networks (ANN) classifier with gradient descent backpropagation using hidden units {1, 2, 4, 8, 32} and the momentum {0,0.2,0.5,0.9} without using sampling
|  | H = 1 | H = 2 | H = 4 | H = 8 | H = 32 | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
|  | M = 0 | M = 0.2 | M = 0.5 | M = 0.9 | M = 0 | M = 0.2 | M = 0.5 | M = 0.9 | M = 0 | M = 0.2 | M = 0.5 | M = 0.9 | M = 0 | M = 0.2 | M = 0.5 | M = 0.9 | M = 0 | M = 0.2 | M = 0.5 | M = 0.9 |
Sensitivity | – | – | 42.30% | – | 52.65% | 52.72% | 52.40% | 61.99% | 49.67% | 52.10% | 50.99% | 47.50% | 51.16% | 49.19% | 51.93% | 51.89% | 42.69% | 40.05% | 42.31% | 66.67% |
Specificity | 88.30% | 88.30% | 90.62% | 88.30% | 91.37% | 91.32% | 91.42% | 89.29% | 90.90% | 89.96% | 90.59% | 91.64% | 90.89% | 90.79% | 90.56% | 89.37% | 90.83% | 90.98% | 91.07% | 88.38% |
Precision | 0 | 0 | 25.43% | 0 | 31.39% | 30.86% | 31.84% | 10.14% | 27.18% | 17.51% | 24% | 34.57% | 26.94% | 26.12% | 23.54% | 11.51% | 27.46% | 29.55% | 29.93% | 0.77% |
F-score | 0 | 0 | 31.76% | 0 | 39.33% | 38.93% | 39.61% | 17.43% | 35.13% | 26.21% | 32.63% | 40.02% | 35.29% | 34.13% | 32.40% | 18.84% | 33.43% | 34.00% | 35.06% | 1.51% |
RMSE | 0.29 | 0.30 | 0.30 | 0.30 | 0.29 | 0.29 | 0.29 | 0.30 | 0.29 | 0.29 | 0.30 | 0.30 | 0.30 | 0.30 | 0.30 | 0.31 | 0.33 | 0.33 | 0.33 | 0.34 |
AUC | 0.79 | 0.77 | 0.76 | 0.73 | 0.78 | 0.78 | 0.79 | 0.79 | 0.78 | 0.78 | 0.79 | 0.79 | 0.80 | 0.80 | 0.80 | 0.79 | 0.77 | 0.76 | 0.76 | 0.50 |