PRTools Contents

PRTools User Guide

kcentres

KCENTRES

Finds K center objects from a distance matrix

   [LAB,J,DM] = KCENTRES(D,K,N)

Input
 D Distance matrix between, e.g. M objects (may be a dataset)
 K Number of center objects to be found (optional; default: 1)
 N Number of trials starting from a random initialisation  (optional; default: 1)

Output
 LAB Integer labels: each object is assigned to its nearest center
 J Indices of the center objects
 DM A list of distances corresponding to J: for each center in J the maximum distance of the objects assigned to this center.

Description

Finds K center objects from a symmetric distance matrix D. The center  objects are chosen from all M objects such that the maximum of the  distances over all objects to the nearest center is minimised. For K > 1,  the results depend on a random initialisation. The procedure is repeated  N times and the best result is returned.

If N = 0, initialisation is not random, but done by a systematic  selection based on a greedy approach.

Faster and more advanced tools for cluster analysis may be found in the  ClusterTools toolbox.

See also

hclust, prkmeans, emclust, modeseek,

PRTools Contents

PRTools User Guide

This file has been automatically generated. If badly readable, use the help-command in Matlab.