Table 7.

Depression Dataset: comparisons of 5 repetitions of a nested 10-fold cross-validation balanced accuracy using the clinical information selected by a FDR procedure. The results are divided in 5 families: Baseline, Feature Selection (FS), Random Forests-based family (RF), standard Multiple Kernel Learning (MKL), Feature Weighting by using MKL (FW) and our method Feature Weighting and Selection (FWS). R corresponds to the number of kernels used.

	Algorithm	Kernels	R	Bal. Acc. %
Baseline	SVM	$\mathbf{I}$ + $\mathbf{C}$	1	$67.00\pm 14.87$
FS	SVM RFE	$\mathcal{V}$ & $\mathcal{C}$	$-$	$64.99\pm 13.01$
	SVM t-test	$\mathcal{V}$ & $\mathcal{C}$	$-$	$62.72\pm 11.12$
RF	Gray	$\mathbf{I}$ & $\mathbf{C}$	$-$	$75.34\pm 16.34$
	Pustina	$\mathbf{I}$ & $\mathbf{C}$	$-$	$73.88\pm 15.19$
MKL	SimpleMKL	$\mathbf{I}$ & $\mathcal{C}$	45	$79.67\pm 13.11$
	EasyMKL	$\mathbf{I}$ & $\mathcal{C}$	45	$79.61\pm 14.12$
FW	SimpleMKL	$\mathcal{V}$ & $\mathcal{C}$	713860	Out of memory
	EasyMKL	$\mathcal{V}$ & $\mathcal{C}$	713860	$80.02\pm 11.32$
FWS	EasyMKLFS	$\mathcal{V}$ & $\mathcal{C}$	713860	$80.01\pm 10.11$