Research Article
A Dynamic Ensemble Framework for Mining Textual Streams with Class Imbalance
Algorithm 2
Sample method.
Output: The optimal CF | Input: : The data chunk at each time stamp | : The number of CTs | : the prediction of | : Misclassified subset at the -th time stamp | : Rare-class subset at the -th time stamp. | : The label of rare-class | (1) At the -th time stamp: | (2) Obtain the by Algorithm 1. | (3) For all , where is the training chunk of ; | (4) Obtain the label by | (5) If : | (6) ; | (7) Endif | (8) If | (9) ; | (10) Endif. | (11) Endfor. | (12) if : | (13) RESAMPLE at the percentage | (14) ; | (15) Else | (16) ; | (17) Endif. | (18) Create a new CT using relying on Algorithm 1; | (19) UPDATE() |
|