Research Article
A New Ensemble Method with Feature Space Partitioning for High-Dimensional Data Classification
Table 2
Performance of proposed method on AR10P dataset. Each row indicates the performance on each class and the last row shows the weighted average.
| Class | Instances | TP rate | FP rate | Precision | Recall | -measure | Roc area |
| 1 | 13 | 1 | 0.017 | 0.867 | 1 | 0.929 | 1 | 2 | 13 | 0.923 | 0 | 1 | 0.923 | 0.96 | 0.995 | 3 | 13 | 0.923 | 0 | 1 | 0.923 | 0.96 | 0.998 | 4 | 13 | 1 | 0.009 | 0.929 | 1 | 0.963 | 1 | 5 | 13 | 0.923 | 0.009 | 0.923 | 0.923 | 0.923 | 0.983 | 6 | 13 | 1 | 0 | 1 | 1 | 1 | 1 | 7 | 13 | 0.923 | 0 | 1 | 0.923 | 0.96 | 0.992 | 8 | 13 | 1 | 0 | 1 | 1 | 1 | 1 | 9 | 13 | 1 | 0 | 1 | 1 | 1 | 1 | 10 | 13 | 1 | 0 | 1 | 1 | 1 | 1 |
| Average | 0.969 | 0.003 | 0.972 | 0.969 | 0.969 | 0.977 |
|
|