Skip to main content

Table 4 Experimental results for each run using epso on leukemia2, lung_cancer, SRBCT prostate_tumor, and DLBCL data stes

From: An enhancement of binary particle swarm optimization for gene selection in classifying cancer classes

Run#

Leukemia2

Lung_Cancer

SRBCT

Prostate_Tumor

DLBCL

 

#Acc (%)

#Selected genes

#Acc (%)

#Selected genes

#Acc (%)

#Selected genes

#Acc (%)

#Selected genes

#Acc (%)

#Selected genes

1

100

4

96.06

7

100

27

99.02

5

100

3

2

100

4

96.06

10

100

11

98.04

4

100

4

3

100

5

96.06

12

100

12

98.04

6

100

4

4

100

6

95.57

6

98.80

8

98.04

8

100

5

5

100

7

95.57

7

98.80

9

98.04

8

100

5

6

100

7

95.57

7

100

48

98.04

11

100

5

7

100

7

95.57

8

98.80

7

98.04

8

100

5

8

100

8

95.57

9

100

12

97.06

4

100

5

9

100

9

95.57

11

100

8

97.06

6

100

5

10

100

11

95.07

6

100

7

97.06

6

100

6

Average ± S.D.

100.00 ±0

6.80 ±2.20

95.67 ±0.31

8.30 ±2.11

99.64 ±0.58

14.90 ±13.03

97.84 ±0.62

6.60 ±2.17

100.00 ±0

4.70 ±0.82

  1. Note: Results of the best subsets shown are written in a bold style. A near-optimal subset that produces the highest classification accuracy with the smallest number of genes is selected as the best subset. #Acc and S.D. denote the classification accuracy and the standard deviation, respectively, whereas #Selected Genes and Run# represent the number of selected genes and a run number, respectively.