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

Table 5

Summary of imbalanced data sets.

Data sets	#sam.	(#min., #maj.)	IR	#fea.
wisconsin	683		0.54	9
pima	768		0.53	8
haberman	306		0.36	3
Vehicle1	846		0.345	18
Vehicle0	846		0.307	18
segment0	2308		0.17	19
yeast-0-3-5-9_vs_7-8	506		0.11	8
yeast-0-2-5-6_vs_3-7-8-9	1004		0.11	8
vowel0	988		0.10	13
led7digit-0-2-4-5-6-7-8-9_vs_1	443		0.09	7
Glass2	214		0.08	10
cleveland-0_vs_4	173		0.08	13
glass-0-1-6_vs_5	184		0.05	9
car-good	1728		0.04	6
flare-F	1066		0.04	11
car-vgood	1728		0.039	6
abalone-17_vs_7-8-9-10	2338		0.0254	9