Table 3. The top ten models as ranked by cross-validation error on the training data when restricted to nose data are shown here.
The error units in columns 1 and 4 are mean absolute error. The values in the NRMSE column are root mean squared error on the test set, divided by the mean ADD over all nose data.
| Training error | NRMSE | Regressor | Test error | Dataset |
|---|---|---|---|---|
| 74.03 | 0.84 | KNR | 138.45 | SPECIES_NONCURATED_NOSE |
| 76.60 | 0.67 | SVR | 121.15 | ORDER_NONCURATED_NOSE |
| 79.13 | 0.58 | KNR | 103.55 | GENUS_NONCURATED_NOSE |
| 79.53 | 0.69 | KNR | 116.66 | ORDER_NONCURATED_NOSE |
| 81.93 | 0.76 | SVR | 122.38 | PHYLUM_NONCURATED_NOSE |
| 82.16 | 0.57 | SVR | 102.58 | SPECIES_NONCURATED_NOSE |
| 84.57 | 0.61 | KNR | 114.67 | CLASS_NONCURATED_NOSE |
| 84.97 | 0.47 | SVR | 85.16 | GENUS_NONCURATED_NOSE |
| 86.76 | 0.53 | KNR | 87.95 | SPECIES_CURATED_NOSE |
| 86.94 | 0.71 | KNR | 128.13 | FAMILY_NONCURATED_NOSE |