Research Article
Applying Randomness Effectively Based on Random Forests for Classification Task of Datasets of Insufficient Information
Table 17
The accuracy of random forests for the data set “lung cancer.”
| Number of attr. to pick randomly (R) | Worst accuracy (%) | Median accuracy (%) | Best accuracy (%) | Number of trees in random forests resulting in the best accuracy (t) |
| 57 | 56.25 | 56.25 | 56.25 | All | 19 | 46.75 | 53.125 | 56.25 | 200, 325, 575, 600, 625, 650 | 12 | 43.75 | 46.875 | 56.25 | 175 | 6 (default) | 46.875 | 50.0 | 59.375 | 150 | 3 | 46.875 | 50.0 | 56.25 | 300, 325 | 2 | 43.75 | 50.0 | 53.125 | 200, 250 ~ 300 | 1 | 34.375 | 37.5 | 56.25 | 150 |
|
|