| SOM Toolbox | Online documentation | http://www.cis.hut.fi/projects/somtoolbox/ |
[t,r] = db_index(D, cl, C, p, q)
DB_INDEX Davies-Bouldin clustering evaluation index.
[t,r] = db_index(D, cl, C, p, q)
Input and output arguments ([]'s are optional):
D (matrix) data (n x dim)
(struct) map or data struct
cl (vector) cluster numbers corresponding to data samples (n x 1)
[C] (matrix) prototype vectors (c x dim) (default = cluster means)
[p] (scalar) norm used in the computation (default == 2)
[q] (scalar) moment used to calculate cluster dispersions (default = 2)
t (scalar) Davies-Bouldin index for the clustering (=mean(r))
r (vector) maximum DB index for each cluster (size c x 1)
See also KMEANS, KMEANS_CLUSTERS, SOM_GAPINDEX.