Knowledge Discovery & Web Mining Lab, University of Louisville

 
UNSUPERVISED LEARNING WITH DATA MULTIPLICITY AND INCOMPATIBILITY

 

Home

People

Publications

Data sets

Links

Outreach Activities

 

This project is supported by National Science Foundation under Data Intensive Computation grant NSF IIS-0916489.

 
 
Synthetic data set 1 used in robust clustering

Data set

# of Clusters

Size

(# of points)

Noise (%)

Three_Close_Clust.txt

3

811

0%

Three_Close_Clust_nois_pt005.txt

3

1157

30%

Three_Close_Clust_nois_pt01.txt

3

1458

44%

Three_Close_Clust_nois_pt02.txt

3

2106

61%

Five_Clust.txt

5

1972

0%

Five_Clust_nois_pt005.txt

5

2308

15%

Five_Clust_nois_pt01.txt

5

2602

24%

Five_Clust_nois_pt02.txt

5

3230

39%

Six_Clust.txt

6

2530

0%

Six_Clust_nois_pt005.txt

6

2865

12%

Six_Clust_nois_pt01.txt

6

3156

20%

Six_Clust_nois_pt02.txt

6

3780

33%

       Synthetic data set 2

Data set

# of Clusters

Size

(# of points)

Noise (%)

cluster-2-0.txt

2

1600

0

cluster-2-1.txt

2

1777

10

cluster-2-2.txt

2

2000

20

cluster-5-0.txt

5

3360

0

cluster-5-1.txt

5

3733

10

cluster-5-2.txt

5

4200

20

cluster-10-0.txt

10

6400

0

cluster-10-1.txt

10

7111

10

cluster-10-2.txt

10

8000

20

cluster-15-0.txt

15

8460

0

cluster-15-1.txt

15

9400

10

cluster-15-2.txt

15

10575

20


Go to back to Knowledge Discovery & Web Mining Lab