Two-Stage Bagging Pruning for Reducing the Ensemble Size and Improving the Classification Performance

Algorithm 1

Traditional bagging algorithm.

Input: -training set, - number of the sampled subsets or base models, - base learner

Output: -a set of base models, - bagging ensemble

1  Initialize

2  for   do:

3   Randomly generate a subset =

4   Base model is established using base classifier trained on the subset

5   

6 The outcome of a test sample predicted by the ensemble model is given as follows: