Does Determination of Initial Cluster Centroids Improve the Performance of -Means Clustering Algorithm? Comparison of Three Hybrid Methods by Genetic Algorithm, Minimum Spanning Tree, and Hierarchical Clustering in an Applied Study

Table 2

Comparison of four different ordinary clustering methods based on the silhouette and RPT indexes.

Index method	_Means	Hierarchical	DB scan	EM algorithm
Leukemia dataset
Silhouette	0.4702	0.4663	0.2693	0.4419
RPT	0.880	0.8612	0.5087	0.8160
Prostate dataset
Silhouette	0.3265	0.4029	0.3339	0.2756
RPT	0.6141	0.7586	0.6319	0.5295
Colon
Silhouette	0.5248	0.5189	0.3156	0.5176
RPT	0.9650	0.9516	0.5747	0.9478
Haberman
Silhouette	0.2477	0.6632	0.6266	0.1384
RPT	0.4787	1.21	1.15	0.2704
Iris
Silhouette	0.4589	0.4796	0.5029	0.3728
RPT	0.8446	0.8614	0.9085	0.6812
Wine
Silhouette	0.2469	0.1575	0.1911	0.2728
RPT	0.4788	0.3092	0.3742	0.5202
Glass
Silhouette	0.3411	0.4281	0.6389	0.2809
RPT	0.6369	0.7921	1.17	0.5148

RPT: robustness performance trade-off.