Skip to main content

Table 6 Statistics on the Average Number of Important Features of the Models Described in Table 5

From: Ovarian cancer detection from metabolomic liquid chromatography/mass spectrometry data by support vector machines

Classifier

Feature Selection

52-20-split Validation

(50 trials)

12-fold CV

(10 trials)

LOOCV

SVM

SVMRFE

22 ± 9

27 ± 9

28 ± 7

SVM

L1SVM

34 ± 2

41 ± 2

43 ± 1

SVM_NL

SVMRFE_NL

26 ± 8

31 ± 8

38 ± 9

SVM_NL

SVMRW

29 ± 9

36 ± 8

40 ± 5