HSDP: A Hybrid Sampling Method for Imbalanced Big Data Based on Data Partition

Table 3

F-measure values of KNN + various sampling methods.

Dataset	Algorithm
	KNN	SMOTE + KNN	ADASYN + KNN	Borderline-SMOTE + KNN	HSDP (proposed) + KNN
Pima	0.5543	0.5766	0.5824	0.5726	0.6105
Yeast3	0.6343	0.6301	0.6294	0.6528	0.6698
Abalone19	0.2019	0.3355	0.2801	0.2438	0.3045
Segment0	0.8653	0.8734	0.8697	0.8843	0.8928
Page-blocks0	0.7146	0.7301	0.7099	0.7401	0.6988
Glass5	0.7132	0.7102	0.7129	0.7265	0.6827
Ecoli4	0.5401	0.5268	0.6011	0.5701	0.6698
Haberman	0.2922	0.3027	0.3417	0.3285	0.3636