Distance Based Multiple Kernel ELM: A Fast Multiple Kernel Learning Approach

Table 4

Classification case: classification accuracy (%). Boldface means no statistical difference from the best one ( val ).

Data	DBMK-ELM	SimpleMKL [16]	-MK-ELM [23]	R-MK-ELM [23]	ELM [8]	UW
Ionosphere	94.23 ± 1.44	94.23 ± 1.96	94.62 ± 1.78	94.32 ± 1.82	90.38 ± 2.88	93.33 ± 1.93
	(0.25)	(0.22)	(1.00)	(0.23)	(0.00)	(0.00)
Sonar	84.71 ± 5.35	84.36 ± 5.51	84.64 ± 5.75	82.57 ± 5.22	84.21 ± 4.71	81.57 ± 5.16
	(1.00)	(0.62)	(0.90)	(0.00)	(0.56)	(0.00)
wdbc	97.13 ± 1.32	97.05 ± 1.11	97.16 ± 1.19	97.08 ± 1.45	97.21 ± 1.26	97.11 ± 1.41
	(0.70)	(0.44)	(0.74)	(0.49)	(1.00)	(0.62)
wpbc	77.38 ± 3.57	75.31 ± 3.55	75.23 ± 3.56	75.46 ± 3.91	76.23 ± 3.72	76.31 ± 4.16
	(1.00)	(0.01)	(0.00)	(0.02)	(0.16)	(0.18)
Breast	69.03 ± 5.65	65.56 ± 7.45	65.83 ± 8.26	67.08 ± 7.34	65.83 ± 7.55	66.94 ± 6.98
	(1.00)	(0.01)	(0.02)	(0.04)	(0.03)	(0.00)
Glass	71.04 ± 4.31	54.86 ± 4.22	68.61 ± 5.71	70.14 ± 4.33	67.57 ± 5.18	69.31 ± 5.46
	(1.00)	(0.00)	(0.01)	(0.15)	(0.01)	(0.08)
Wine	97.92 ± 1.94	98.33 ± 1.71	98.17 ± 2.22	98.00 ± 2.45	97.58 ± 2.13	98.00 ± 2.27
	(0.20)	(1.00)	(0.61)	(0.41)	(0.02)	0.43
AVG	84.49	81.39	83.47	83.52	82.72	83.22