Classifying Imbalanced Data Sets by a Novel RE-Sample and Cost-Sensitive Stacked Generalization Method

Pseudocode 1

Pseudocodes of RE-sample and Cost-Sensitive Stacked Generalization.

Input Training set , Test dataset

Output Predict class labels of the test samples

For each do

(1) Resample imbalance data and generate –fold cross-validation sets to obtain New ;

(2) Train and compute and in Level-0 (base)-layer classifier

end

(3) Construct , and

(4) Based on the data , classification (cost-sensitive and Logistic Regression) is used to

generate Level-1 (meta)-layer model , through with to predict