Research Article
Applying Randomness Effectively Based on Random Forests for Classification Task of Datasets of Insufficient Information
Table 5
Comparison of accuracy in other data mining methods.
| Number | Method | Accuracy (%) | Sensitivity | Specificity | AUC (%) | Remarks |
| 1 | FLN tightest fit [3] | 78.33 | 0.6375 | 0.91 | NA | 2/3 for training, 1/3 for testing, once | 2 | FLN ordered tightest fit [4] | 85.56 | 0.7875 | 0.91 | NA | 2/3 for training, 1/3 for testing, once | 3 | Concurrent random forests [12] | 80.19 | NA | NA | 89.32 | 10-fold cross validation | 4 | SubBag-JRip [5] | 78.15 | NA | NA | NA | 10-fold cross validation | 5 | BAGGING-JRip [5] | 79.26 | NA | NA | NA | 10-fold cross validation | 6 | C4.5 [8] | 70.19 | 0.303 | 0.994 | 62.6 | 10-fold cross validation | 7 | Suggested random forests | 85.74 | 0.7763 | 0.9167 | 91.45 | 10-fold cross validation |
|
|