Table 5 MSD comparisons with different number of points when k = 10 (in millions of actual values).
From: A practical comparison of two K-Means clustering algorithms
for k= 10 | 50 pts | 100 pts | 1000 pts | 5000 pts | 10000 pts |
|---|---|---|---|---|---|
Lloyd min MSD | 0.745 | 2.633 | 4.905 | 4.823 | 5.015 |
Lloyd global avg. MSD | 4.355 | 4.845 | 5.519 | 5.538 | 5.588 |
Lloyd max MSD | 7.350 | 6.916 | 6.497 | 5.983 | 6.097 |
Progressive min MSD | 0.745 | 2.633 | 4.578 | 4.602 | 4.713 |
Progressive global avg. MSD | 5.266 | 4.978 | 5.564 | 5.503 | 5.547 |
Progressive max MSD | 9.721 | 6.970 | 6.222 | 6.106 | 6.149 |