Localized instance fusion of MRI data of Alzheimer’s disease for classification based on instance transfer ensemble learning

Table 6 The results of the target domain in the case of different sampling after feature growing

Number of samples in TD	Kernel type	SD_GraTrans_Opt_SamSel+TD_train (Mean, std)	SD_GraTrans_FG+TD_train (Mean, std)	TD_train (Mean, std)
60	Linear	(81.67%, 0)	(71.67%, 0)	(71.67%, 0)
60	RBF	(78.33%, 0)	(78.33%, 0)	(76.67%, 0)
40	Linear	(77.29%, 0.0505)	(77.29%, 0.0376)	(75.21%, 0.0538)
40	RBF	(77.25%, 0.0362)	(77.75%, 0.0416)	(75.5%, 0.0705)
20	Linear	(75.5%, 0.1322)	(73.5%, 0.1292)	(72.5%, 0.1112)
20	RBF	(69.5%, 0.1707)	(67%, 0.1844)	(73.5%, 0.0747)

The italicized data represents the highest classification accuracy under the same experimental conditions

ISSN: 1475-925X