Research Article
Feature Selection for Intelligent Firefighting Robot Classification of Fire, Smoke, and Thermal Reflections Using Thermal Infrared Images
Table 4
Performance of each feature.
| ā | Resubstitution error (%) | Cross-validation error (%) |
| MNI | 23.7 | 23.8 | VAR | 24.3 | 24.3 | NOP | 72.1 | 72.0 | STD | 23.2 | 23.2 | SKE | 52.7 | 52.8 | KUR | 50.6 | 50.6 | OFVN | 39.5 | 40.0 | OFVMM | 58.6 | 58.6 | DIS | 29.0 | 29.0 | ENT | 44.6 | 44.6 | CON | 28.5 | 28.5 | IND | 30.1 | 30.1 | COR | 41.2 | 41.1 | UNI | 34.5 | 34.5 | IDM | 37.7 | 37.7 |
|
|