Skip to main content

Table 1 Datasets description

From: The stability of different aggregation techniques in ensemble feature selection

Dataset name and source

No. observations

No. Features

No. Classes

Dimensionality\(^{*}\)

Jasminea

2984 (1492/1492)

145

2

0.048592

Imageb

2000 (1420/580)

140

2

0.070000

Scenec

2407 (1976/431)

295

2

0.122559

Muskd

6598 (5581/1017)

170

2

0.025765

Philippinea

5832 (2916/2916)

309

2

0.052984

Ionosphered

351 (126/225)

34

2

0.096866

Optdigitsb

5620 (572/5048)

64

2

0.011388

Satelliteb

5100 (75/5025)

37

2

0.007255

Adaa

4147 (1029/3118)

49

2

0.011816

Spliceb

3190 (1535/1655)

62

2

0.019436

Indian Pinesb

9144

221

8

0.024168

Semeiond

1593

257

10

0.161330

  1. *Dimensionality is the ratio of features to number of observations. Superscripts indicate the data sources as follows:
  2. aautoml.chalearn.org
  3. bwww.openml.org
  4. cmulan.sourceforge.net
  5. darchive.ics.uci.edu