Research Article
The Impact of Simulated Spectral Noise on Random Forest and Oblique Random Forest Classification Performance
Table 2
oRF-RR classification accuracies for three simulated noise levels for three weeks of infestation.
| Noise (%) | Week one | Week two | Week three | 0 | 10 | 20 | 30 | 0 | 10 | 20 | 30 | 0 | 10 | 20 | 30 |
| Train accuracy | 99.28 | 98.51 | 97.14 | 97.03 | 98.79 | 98.63 | 98.62 | 97.71 | 95.65 | 95.49 | 95.38 | 95.24 | Test accuracy | 96.42 | 97.04 | 96.42 | 96.42 | 100.00 | 100.00 | 100.00 | 100.00 | 91.07 | 91.07 | 91.07 | 92.85 | Train kappa | 98.57 | 96.42 | 94.28 | 93.97 | 97.59 | 97.27 | 97.26 | 95.47 | 91.23 | 90.92 | 90.69 | 90.54 | Test kappa | 92.85 | 92.85 | 92.85 | 92.85 | 100.00 | 100.00 | 100.00 | 100.00 | 82.14 | 82.14 | 82.14 | 85.71 |
|
|