Biomarker detection using corrected degree of domesticity in hybrid social network feature selection for improving classifier performance

Table 5 Results of the simulated data with rho = 0.90

FS	CD	Acc.	Sens.	Spe.	AUC
SVM SQRT-RFE+CS	Louvain	0.675	0.604	0.746	0.760
SVM SQRT-RFE+IG		0.702	0.644	0.760	0.761
SVM SQRT-RFE+RF		0.629	0.498	0.760	0.689
IG+CS		0.683	0.636	0.730	0.733
IG+RF		0.632	0.606	0.658	0.687
CS+RF		0.632	0.606	0.658	0.688
SVM SQRT-RFE+CS	Walktrap	0.717	0.664	0.770	0.775
SVM SQRT-RFE+IG		0.702	0.644	0.760	0.761
SVM SQRT-RFE+RF		0.629	0.498	0.760	0.689
IG+CS		0.679	0.638	0.720	0.732
IG+RF		0.632	0.606	0.658	0.687
CS+RF		0.632	0.606	0.658	0.688
SVM SQRT-RFE+CS	Infomap	0.717	0.664	0.770	0.775
SVM SQRT-RFE+IG		0.702	0.644	0.760	0.761
SVM SQRT-RFE+RF		0.629	0.498	0.760	0.689
IG+CS		0.677	0.636	0.718	0.732
IG+RF		0.632	0.606	0.658	0.687
CS+RF		0.632	0.606	0.658	0.688

FS: feature selection method used in the first step of the algorithm; CD: community detection method used in the third step of the algorithm; Acc.: accuracy; Sens.: sensitivity; Spe.: specificity; AUC: area under the ROC curve

ISSN: 1471-2105