TABLE 3.
Performance of the best models developed on the HSE + LSE/NSE + INA partitioning scheme on the TeS. For each model, the following statistics are reported: Balanced Accuracy (BA), Sensitivity (SEN), Specificity (SPE), Matthews Correlation Coefficient (MCC), number of True Negatives (TN), False Positives (FP), True Positives (TP) and False Negatives (FNs).
| Classifier | BRF | KNN | SVM | RF |
|---|---|---|---|---|
| #Descriptors | 170 | 30 | 30 | 130 |
| BA | 0.80 | 0.78 | 0.77 | 0.70 |
| SEN | 0.79 | 0.79 | 0.70 | 0.70 |
| SPE | 0.81 | 0.77 | 0.84 | 0.71 |
| MCC | 0.52 | 0.48 | 0.48 | 0.32 |
| TN | 140 | 133 | 144 | 122 |
| FP | 32 | 39 | 28 | 50 |
| TP | 34 | 34 | 30 | 30 |
| FN | 9 | 9 | 13 | 13 |
| # | 215 | 215 | 215 | 215 |