Research Article

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

Table 4

Base classifier methods and corresponding ensemble algorithms.

MethodsDescriptions and parametersAbbreviations

(1) Naïve Bayesweka.classifiers.bayes.NaiveBayesNB

(2) C4.5weka.classifiers.trees.J48 -C 0.25 -M 2C4.5

(3) -nearest neighborweka.classifiers.lazy.IBk -K 1 -W 0 -A "weka.core.neighboursearch.LinearNNSearch -A ∖"weka.core.EuclideanDistance -R first-last∖""KNN

(4) Cost-sensitive with Naïve Bayesweka.classifiers.meta.AdaBoostM1 -P 100 -S 1 -I 10 -W weka.classifiers.bayes.NaiveBayesCost-NB

(5) AdaBoost with Naïve Bayesweka.classifiers.meta.AdaBoostM1 -P 100 -S 1 -I 10 -W weka.classifiers.bayes.NaiveBayesAda-NB

(6) AdaBoost with cost-sensitive and Naïve Bayesweka.classifiers.meta.AdaBoostM1 -P 100 -S 1-I10 -W weka.Classifiers.meta.CostSensitiveClassifier -- -cost-matrix "[1.0 3.0; 1.0 1.0]" -S 1 -W weka. classifiers.bayes.NaiveBayesAda-Cost-NB

(7) Bagging with Naïve Bayesweka.classifiers.meta.Bagging -P 100 -S 1 -num-slots 1 -I 10 -W weka.classifiers.bayes.NaiveBayesBag-NB

(8) Bagging with cost-sensitive and Naïve Bayesweka.classifiers.meta.Bagging -P 100 -S 1 -num-slots 1 -I 10 -W weka.classifiers.meta.CostSensitive Classifier -- -cost-matrix "[1.0 3.0; 1.0 1.0]" -S 1 -W weka.classifiers.bayes.NaiveBayesBag-Cost-NB

(9) Stacking with NB, KNN, C4.5, and logisticweka.classifiers.meta.Stacking -X 10 -M "weka. classifiers.functions.Logistic -R 1.0E-8 -M -1 –num –decimal-places 4" -S 1 -num-slots 1 -B "weka. classifiers.bayes.NaiveBayes" -B "weka.classifiers. lazy.IBk -K 1 -W 0 -A "weka.core.neighboursearch. LinearNNSearch -A ∖∖∖"weka.core.EuclideanDistance -R first-last∖∖∖""" -B "weka.classifiers.trees.J48 -C 0.25 -M 2"Stacking-log

(10) Stacking cost-sensitive with NB, KNN, C4.5, and logisticweka.classifiers.meta.Stacking -X 10 -M "weka. classifiers.meta.CostSensitiveClassifier –cost -matrix ∖"[1.0 3.0; 1.0 1.0]∖" -S 1 -W weka.classifiers. functions.Logistic -- -R 1.0E-8 -M -1 –num –decimal –places 4" -S 1 -num-slots 1 -B "weka. classifiers. bayes.NaiveBayes " -B "weka.classifiers.lazy.IBk -K 1 -W 0 -A ∖"weka.core.neighboursearch.LinearNN Search -A ∖∖∖"weka.core.EuclideanDistance -R first- last∖∖∖""" -B "weka.classifiers.trees.J48 -C 0.25 -M 2"Stacking-Cost-log