An Ensemble Learning Method Based on an Evidential Reasoning Rule considering Combination Weighting

Table 3

Ensemble accuracy of Stanford’s dog dataset.

	DIE	DIR	IER	MIE	MIR
EW	0.8701	0.8858	0.8905	0.8779	0.8905
COV	0.8748	0.8826	0.8905	0.8842	0.8951
CRITIC	0.8811	0.8842	0.8858	0.8920	0.8936
AHP	0.8811	&	0.8826	0.8811	0.8858
EW + AHP	#	&	#	#	#
COV + AHP	#	&	#	#	#
CRITIC + AHP	#	&	#	#	#
EWAHP	0.8748	&	0.8842	0.8748	0.8826
COVAHP	0.8764	&	0.8826	0.8764	0.8811
CRITICAHP	0.8795	&	0.8858	0.8764	0.8811
EW(+)AHP	0.8764	&	0.8889	0.8826	0.8920
COV(+)AHP	0.8764	&	0.8889	0.8873	0.8920
CRITIC(+)AHP	0.8795	&	0.8858	0.8920	0.8936
EW()AHP	0.8748	&	0.8811	0.8748	0.8811
COV()AHP	0.8795	&	0.8826	0.8779	0.8826
CRITIC()AHP	0.8811	&	0.8811	0.8826	0.8826
EW(rg)AHP	0.8764	&	0.8905	0.8858	0.8920
COV(rg)AHP	0.8764	&	0.8889	0.8873	0.8920
CRITIC(rg)AHP	0.8795	&	0.8873	0.8920	0.8936