Consensus Clustering-Based Undersampling Approach to Imbalanced Learning

Table 3

Average AUC values of homogeneous clustering schemes with C4.5 classifier.

Consensus function	Simple voting	Simple voting	Simple voting	Simple voting	Simple voting	Incremental voting	Incremental voting	Incremental voting	Incremental voting	LCS	Incremental voting	LCS	LCS	LCS	LCS
Method	CONS1 (KM)	CONS1 (KM++)	CONS1 (KMOD)	CONS1 (SOM)	CONS1 (DIANA)	CONS1 (KM)	CONS1 (KM++)	CONS1 (KMOD)	CONS1 (DIANA)	CONS1 (KM)	CONS1 (SOM)	CONS1 (KM++)	CONS1 (KMOD)	CONS1 (SOM)	CONS1 (DIANA)
Abalone19	0.746	0.746	0.746	0.766	0.747	0.747	0.747	0.748	0.766	0.766	0.766	0.766	0.766	0.746	0.766
Abalone9-18	0.770	0.770	0.770	0.794	0.770	0.792	0.792	0.793	0.793	0.793	0.793	0.793	0.793	0.770	0.811
Breast cancer	0.855	0.867	0.870	0.940	0.882	0.879	0.891	0.887	0.903	0.909	0.921	0.926	0.918	0.888	0.931
Ecoli-0_vs_1	0.870	0.880	0.920	0.970	0.900	0.910	0.930	0.930	0.950	0.950	0.960	0.960	0.960	0.940	0.980
Ecoli-0-1-3-7_vs_2-6	0.775	0.775	0.775	0.782	0.775	0.778	0.779	0.780	0.780	0.780	0.781	0.781	0.782	0.775	0.788
Ecoli1	0.850	0.850	0.850	0.950	0.870	0.870	0.880	0.880	0.900	0.910	0.920	0.930	0.930	0.870	0.950
Ecoli2	0.830	0.840	0.850	0.930	0.860	0.860	0.870	0.860	0.870	0.890	0.900	0.910	0.910	0.860	0.910
Ecoli3	0.840	0.850	0.850	0.940	0.870	0.870	0.870	0.870	0.890	0.900	0.900	0.910	0.920	0.860	0.940
Ecoli4	0.830	0.840	0.840	0.930	0.860	0.860	0.870	0.860	0.870	0.890	0.890	0.910	0.850	0.850	0.850
Glass0	0.780	0.781	0.781	0.823	0.784	0.822	0.822	0.822	0.822	0.823	0.823	0.823	0.823	0.781	0.824
Glass0123vs456	0.840	0.850	0.850	0.950	0.870	0.870	0.880	0.880	0.900	0.900	0.900	0.910	0.930	0.860	0.940
Glass016vs2	0.774	0.774	0.774	0.789	0.774	0.786	0.787	0.787	0.788	0.788	0.789	0.789	0.789	0.774	0.790
Glass016vs5	0.850	0.860	0.860	0.960	0.880	0.880	0.890	0.890	0.910	0.920	0.940	0.940	0.950	0.890	0.960
Glass1	0.740	0.740	0.740	0.765	0.741	0.742	0.743	0.743	0.764	0.765	0.765	0.765	0.765	0.741	0.765
Glass2	0.784	0.784	0.784	0.842	0.784	0.842	0.842	0.842	0.842	0.842	0.842	0.842	0.842	0.784	0.842
Glass4	0.800	0.810	0.800	0.840	0.840	0.800	0.840	0.810	0.830	0.800	0.820	0.850	0.800	0.840	0.810
Glass5	0.850	0.870	0.880	0.960	0.890	0.890	0.900	0.910	0.920	0.930	0.940	0.950	0.950	0.900	0.970
Glass6	0.820	0.820	0.840	0.900	0.860	0.860	0.860	0.820	0.870	0.820	0.880	0.890	0.810	0.850	0.820
Haberman	0.718	0.722	0.722	0.759	0.725	0.725	0.725	0.727	0.757	0.757	0.758	0.758	0.759	0.724	0.759
Iris0	0.900	0.960	0.930	0.980	0.930	0.910	0.950	0.940	0.950	0.950	0.960	0.970	0.970	0.960	0.990
New-thyroid1	0.850	0.860	0.870	0.960	0.890	0.880	0.900	0.910	0.910	0.930	0.940	0.950	0.950	0.890	0.970
New-thyroid2	0.850	0.850	0.850	0.950	0.880	0.870	0.880	0.880	0.900	0.920	0.930	0.930	0.930	0.870	0.960
Page-blocks0	0.860	0.880	0.890	0.970	0.890	0.900	0.910	0.920	0.930	0.940	0.950	0.950	0.960	0.920	0.970
Page-blocks13vs2	0.960	0.960	0.950	0.990	0.970	0.940	0.950	0.940	0.950	0.970	0.990	0.980	0.970	0.960	0.990
Pima	0.777	0.777	0.777	0.792	0.777	0.790	0.790	0.791	0.791	0.791	0.792	0.792	0.792	0.777	0.792
Segmemt0	0.870	0.880	0.890	0.970	0.900	0.900	0.920	0.930	0.940	0.940	0.950	0.960	0.960	0.920	0.980
Shuttle0vs4	0.980	0.990	0.980	1.000	0.980	0.990	0.970	0.940	0.970	1.000	1.000	0.980	0.990	0.990	1.000
Shuttle2vs4	0.890	0.950	0.920	0.970	0.910	0.910	0.940	0.930	0.950	0.950	0.960	0.960	0.960	0.950	0.980
Vehicle0	0.850	0.870	0.880	0.960	0.890	0.890	0.900	0.910	0.920	0.930	0.940	0.950	0.950	0.890	0.970
Vehicle1	0.768	0.768	0.768	0.766	0.769	0.760	0.761	0.762	0.762	0.763	0.763	0.765	0.765	0.768	0.766
Vehicle2	0.860	0.880	0.880	0.970	0.890	0.900	0.900	0.910	0.920	0.940	0.950	0.950	0.950	0.900	0.970
Vehicle3	0.779	0.779	0.779	0.801	0.779	0.799	0.799	0.800	0.800	0.800	0.801	0.801	0.801	0.779	0.803
Vowel0	0.840	0.850	0.850	0.950	0.870	0.870	0.880	0.880	0.900	0.910	0.910	0.920	0.930	0.870	0.940
Wisconsin	0.850	0.860	0.870	0.960	0.880	0.880	0.890	0.890	0.910	0.930	0.940	0.950	0.950	0.890	0.960
Yeast05679vs4	0.826	0.826	0.826	0.842	0.826	0.842	0.842	0.842	0.842	0.842	0.842	0.842	0.842	0.826	0.842
Yeast1	0.779	0.780	0.780	0.811	0.780	0.809	0.810	0.810	0.810	0.810	0.811	0.811	0.811	0.780	0.813
Yeast1289vs7	0.756	0.756	0.756	0.767	0.756	0.757	0.757	0.757	0.767	0.767	0.767	0.767	0.767	0.756	0.770
Yeast1458vs7	0.730	0.731	0.731	0.762	0.732	0.732	0.733	0.734	0.760	0.762	0.762	0.762	0.762	0.732	0.762
Yeast1vs7	0.771	0.772	0.772	0.787	0.772	0.782	0.783	0.784	0.784	0.785	0.785	0.786	0.786	0.772	0.787
Yeast2vs4	0.840	0.840	0.850	0.940	0.870	0.870	0.870	0.870	0.890	0.900	0.900	0.910	0.910	0.860	0.920
Yeast2vs8	0.827	0.827	0.827	0.851	0.827	0.850	0.850	0.850	0.850	0.851	0.851	0.851	0.851	0.827	0.851
Yeast3	0.850	0.850	0.860	0.950	0.880	0.870	0.890	0.890	0.900	0.920	0.930	0.930	0.940	0.880	0.960
Yeast4	0.830	0.840	0.840	0.910	0.860	0.860	0.870	0.860	0.870	0.880	0.890	0.900	0.840	0.850	0.840
Yeast5	0.870	0.880	0.890	0.970	0.890	0.900	0.910	0.920	0.930	0.940	0.950	0.950	0.960	0.920	0.980
Yeast6	0.810	0.820	0.830	0.850	0.850	0.800	0.840	0.810	0.850	0.810	0.870	0.870	0.810	0.850	0.810
Protein homology prediction	0.850	0.865	0.875	0.960	0.888	0.885	0.898	0.905	0.915	0.930	0.940	0.950	0.950	0.893	0.968
Twitter-sentiment	0.896	0.918	0.917	0.977	0.918	0.918	0.931	0.929	0.943	0.953	0.963	0.962	0.964	0.940	0.982
Average	0.826	0.835	0.837	0.893	0.845	0.848	0.856	0.854	0.867	0.871	0.879	0.883	0.878	0.849	0.888