Table 2.
Confusion matrices and performance metrics of averages over 400 testing datasets of models 1 and 2. TN, true negative; TP, true positive; FN, false negative; FP, false positive. A, accuracy; P, precision; R, recall; F1, F1-score. Mean and variation values of each quantity are average and standard deviation over 400 testing datasets.
| Model | TN | FP | FN | TP | A | P | R | F1 |
|---|---|---|---|---|---|---|---|---|
| Model 1 mean | 91.38% | 8.62% | 4.39% | 95.61% | 0.997 | 0.915 | 0.955 | 0.929 |
| Model 1 SD | 5.49% | 5.49% | 5.04% | 5.04% | 0.002 | 0.100 | 0.063 | 0.049 |
| Model 2 mean | 99.98% | 0.02% | 5.80% | 94.20% | 0.998 | 0.994 | 0.935 | 0.964 |
| Model 2 SD | 0.03% | 0.03% | 2.54% | 2.54% | 0.001 | 0.007 | 0.028 | 0.014 |