Skip to main content

Table 2 Comparison of models with \(p=1000\) in easy, medium and hard classification scenarios using \(\eta =10^{-4}\) and \(n=30\)

From: Knowledge-slanted random forest method for high-dimensional data and small sample size with a feature selection application for gene expression data

 

PE

S

E

F1

Method

Mean

SD

Mean

SD

Mean

SD

Mean

SD

Easy scenario

     Lasso

0.10

0.13

0.82

0.22

1.00

0.00

0.88

0.17

     Conv. RF

0.01

0.03

0.99

0.04

1.00

0.02

0.99

0.03

     Slanted (0)

0.08

0.13

0.91

0.17

0.97

0.10

0.92

0.15

     Slanted (0.1)

0.04

0.09

0.95

0.11

0.98

0.07

0.96

0.09

     Slanted (0.5)

0.01

0.03

0.99

0.04

1.00

0.02

0.99

0.03

     Slanted (0.8)

0.00

0.02

0.99

0.02

1.00

0.00

1.00

0.01

     Slanted (1)

0.00

0.01

1.00

0.01

1.00

0.01

1.00

0.02

Medium scenario

     Lasso

0.13

0.13

0.78

0.21

0.98

0.06

0.84

0.16

     Conv. RF

0.10

0.15

0.87

0.19

0.96

0.13

0.89

0.15

     Slanted (0)

0.23

0.19

0.72

0.26

0.90

0.20

0.74

0.22

     Slanted (0.1)

0.16

0.14

0.81

0.20

0.92

0.14

0.83

0.16

     Slanted (0.5)

0.05

0.07

0.94

0.11

0.98

0.05

0.95

0.07

     Slanted (0.8)

0.03

0.04

0.97

0.07

0.99

0.04

0.97

0.04

     Slanted (1)

0.03

0.05

0.97

0.08

0.99

0.03

0.97

0.06

Hard scenario

     Lasso

0.49

0.15

0.28

0.33

0.78

0.30

0.27

0.29

     Conv. RF

0.49

0.16

0.56

0.41

0.46

0.42

0.45

0.30

     Slanted (0)

0.48

0.15

0.54

0.38

0.48

0.38

0.45

0.28

     Slanted (0.1)

0.48

0.16

0.56

0.38

0.47

0.40

0.47

0.28

     Slanted (0.5)

0.46

0.15

0.57

0.39

0.50

0.37

0.48

0.29

     Slanted (0.8)

0.46

0.16

0.58

0.38

0.51

0.38

0.49

0.28

     Slanted (1)

0.45

0.16

0.57

0.38

0.54

0.38

0.49

0.29