Skip to main content

Table 5 Number of times different methods achieve the best results with DT classifier

From: A novel method of constrained feature selection by the measurement of pairwise constraints uncertainty

Dataset

LS

GCNC

FGUFS

FS

FAST

FJMI

PCA

PCFS

SPECTF

1

1

1

0

0

2

1

4

SpamBase

0

1

0

1

1

0

0

7

Sonar

0

1

0

0

1

1

1

6

Arrhythmia

0

1

1

0

1

1

0

6

Madelon

0

1

1

0

1

0

1

6

Isolet

0

1

0

0

1

1

1

6

Multiple Features

0

2

0

1

1

1

0

5

Colon

0

1

0

1

0

1

1

6

Average

0.12

1.12

0.37

0.37

0.75

0.87

0.62

5.75