Skip to main content
. 2019 Nov 18;5:e237. doi: 10.7717/peerj-cs.237

Table 5. SVM Precision(P), Recall(R) and F-measure(F) on top 20 features using 5-fold CV on different data sets.

GF-CSFS (Pineda-Bautista, Carrasco-Ochoa & Martınez-Trinidad, 2011) framework is compared against our SMBA-CSFS. FS: Fisher Score, mRMR: Minimum-Redundancy-Maximum-Relevance, MI: Mutual Information, RFS: Robust Feature Selector, EN: Elastic Net, BSL: all features. The best results are highlighted in bold. The number in parentheses is the number of features when the performance is achieved.

ALLAML LEUKEMIA CLL_SUB_111 GLIOMA LUNG_C LUNG_D DLBCL CARCINOM GCM(14)
P R F P R F P R F P R F P R F P R F P R F P R F P R F
Fisher 0.96(15) 0.96(14) 0.96 0.97(2) 0.97(2) 0.97 0.84(4) 0.84(4) 0.84 0.76(8) 0.75(8) 0.75 0.96(18) 0.96(18) 0.96 0.97(16) 0.97(16) 0.97 1.0(17) 1.0(17) 1.0 0.95(13) 0.95(13) 0.95 0.93(18) 0.93(18) 0.93
Relief 0.98(16) 0.98(16) 0.98 0.97(8) 0.97(8) 0.97 0.82(5) 0.82(5) 0.82 0.72(19) 0.7(15) 0.71 0.95(19) 0.95(19) 0.95 0.96(9) 0.95(9) 0.95 1.0(10) 1.0(10) 1.0 0.96(17) 0.96(17) 0.96 0.91(20) 0.91(20) 0.91
mRMR 0.69(8) 0.69(8) 0.69 0.97(13) 0.97(4) 0.97 0.84(15) 0.84(15) 0.84 0.77(20) 0.77(20) 0.77 0.97(18) 0.97(18) 0.97 0.97(17) 0.97(17) 0.97 1.0(11) 1.0(11) 1.0 0.97(15) 0.97(15) 0.97 0.91(20) 0.91(20) 0.91
MI 0.99(17) 0.99(17) 0.99 0.98(2) 0.98(17) 0.98 0.8(13) 0.8(13) 0.8 0.75(3) 0.75(3) 0.75 0.94(18) 0.94(18) 0.94 0.97(11) 0.97(11) 0.97 1.0(12) 1.0(12) 1.0 0.97(17) 0.97(16) 0.97 0.91(19) 0.91(19) 0.91
ls_l21 0.82(18) 0.78(18) 0.8 0.92(17) 0.91(17) 0.91 0.7(14) 0.69(14) 0.69 0.67(20) 0.67(20) 0.67 0.96(20) 0.96(20) 0.96 0.9(16) 0.9(16) 0.9 0.91(19) 0.91(19) 0.91 0.77(18) 0.77(18) 0.77 0.83(19) 0.83(19) 0.83
ll_l21 0.91(19) 0.9(19) 0.9 0.87(14) 0.86(14) 0.86 0.76(20) 0.76(20) 0.76 0.73(19) 0.73(19) 0.73 0.96(16) 0.96(16) 0.96 0.91(18) 0.9(18) 0.9 0.97(17) 0.97(17) 0.97 0.85(20) 0.85(20) 0.85 0.78(20) 0.78(20) 0.78
RFS 0.87(14) 0.85(14) 0.86 0.96(19) 0.96(19) 0.96 0.68(12) 0.69(12) 0.68 0.69(20) 0.67(20) 0.68 0.95(20) 0.95(20) 0.95 0.93(19) 0.91(19) 0.92 0.94(20) 0.93(20) 0.93 0.85(19) 0.85(19) 0.85 0.79(20) 0.79(20) 0.79
LASSO 0.87(16) 0.87(16) 0.87 0.72(16) 0.71(16) 0.71 0.78(18) 0.78(18) 0.78 0.8(18) 0.78(18) 0.79 0.94(17) 0.94(17) 0.94 0.89(20) 0.88(20) 0.88 0.97(19) 0.97(19) 0.97 0.84(20) 0.85(20) 0.84 0.73(20) 0.73(20) 0.73
EN 0.87(16) 0.87(16) 0.87 0.72(16) 0.71(16) 0.71 0.78(18) 0.78(18) 0.78 0.8(18) 0.78(18) 0.79 0.94(17) 0.94(17) 0.94 0.89(20) 0.88(20) 0.88 0.97(19) 0.97(19) 0.97 0.84(20) 0.85(20) 0.84 0.73(20) 0.73(20) 0.73
SMBA-CSFS 0.83(16) 0.83(16) 0.83 0.86(20) 0.86(20) 0.86 0.67(20) 0.68(20) 0.67 0.8(20) 0.77(20) 0.78 0.98(15) 0.98(15) 0.98 0.99(19) 0.99(19) 0.99 1.0(20) 1.0(20) 1.0 0.99(20) 0.98(20) 0.98 0.97(20) 0.97(20) 0.97
BSL 1 1 1 1 1 1 0.74 0.74 0.74 0.92 0.92 0.92 0.93 0.93 0.93 0.8 0.8 0.8 1 1 1 0.98 0.98 0.98 1 1 1