Skip to main content

Table 8 Results for DIFF-FOM

From: Computational cluster validation for microarray data analysis: experimental assessment of Clest, Consensus Clustering, Figure of Merit, Gap Statistics and Model Explorer

 

Precision

Timing

 

CNS Rat

Leukemia

NCI60

Lymphoma

Yeast

PBM

CNS Rat

Leukemia

NCI60

Lymphoma

K-means-R

4

➌

4

➌

3

4

2.9 × 104

1.9 × 105

1.3 × 106

6.7 × 105

K-means-A

⑦

➌

3

6

3

8

2.2 × 104

9.3 × 104

5.5 × 105

2.7 × 105

K-means-C

⑦

➌

⑦

â‘£

3

5

1.9 × 104

9.4 × 104

5.5 × 105

2.6 × 105

K-means-S

⑦

➌

12

8

3

10

2.9 × 104

1.0 × 105

7.1 × 105

3.6 × 105

R-R0

10

â‘£

17

â‘£

3

3

2.6 × 103

3.1 × 104

1.7 × 105

5.3 × 104

R-R5

4

➌

11

➌

3

4

3.9 × 103

3.7 × 104

2.1 × 105

7.6 × 104

R-R2

⑦

➌

17

➌

3

7

3.4 × 103

3.8 × 104

2.2 × 105

7.2 × 104

Hier-A

⑦

➌

3

6

3

25

1.6 × 103

7.5 × 103

5.1 × 104

1.8 × 104

Hier-C

9

➌

⑦

7

3

7

1.6 × 103

7.7 × 103

4.5 × 104

1.8 × 104

Hier-S

20

7

22

9

7

20

1.6 × 103

7.4 × 103

4.9 × 105

1.7 × 104

Gold solution

6

3

8

3

5

18

-

-

-

-

  1. A summary of the results for DIFF-FOM on all algorithms and on all datasets. The columns under the label precision indicate the number of clusters predicted by DIFF-FOM, while the remaining four indicate the timing in milliseconds for the execution of the corresponding experiment. Cells with a dash indicate that DIFF-FOM did not give any useful indication.