Table 2 Average quality indices for clustering methods with OSCC data
From: DiviK: divisive intelligent K-means for hands-free unsupervised clustering in big biological data
Clustering algorithm | Adjusted Rand index | Dice index | Relative EXIMS score | Overall quality d(0, 0, 0) | Overall quality d(1, 1, 1) |
|---|---|---|---|---|---|
Spectral | 0.375 (0.241) | 0.543 (0.325) | 0.775 (0.202) | 1.083 (0.184) | 0.844 (0.357) |
K-means | 0.385 (0.111) | 0.440 (0.266) | 0.889 (0.113) | 1.099 (0.048) | 0.859 (0.234) |
Spatial | 0.483 (0.281) | 0.638 (0.363) | 0.781 (0.127) | 1.192 (0.123) | 0.706 (0.402) |
DiviK | 0.556 (0.088) | 0.750 (0.071) | 0.793(0.167) | 1.236 (0.073) | 0.576 (0.067) |