ClusterTools Contents

ClusterTools User Guide



Dissimilarity based clustering by the FFT algorithm.


 D Square dissimilarity matrix, size M*M
 K Scalar or a vector of length N with desired numbers of clusters.  Default is a set of N clusterings with numbers that naturally  arise from the data.

 LAB M*N array with the results of the multi-level clusterings for the
 M objects. The columns refer to the N clusterings. They yield for  the objects the prototype indices of the clusters they belong to.


The FFT (Farthest First Traversal) algorithm is used to find a set of K prototypes. All other objects are assigned to the nearest prototype.  In LAB for all objects the index in D of the nearest cluster prototype is  returned. If K is a vector LAB has length(K) columns, returning a  multilevel clustering.

Note that the FFT algorithm is not really a clustering procedure but just  a fast way to split the data in spatially distant parts.

Clusterings can be evaluated by CLUSTEVAL, CLUSTCERR or CLUSTC on the  basis of (some) true labels.

See also

datasets, mappings, kmeans, prkmeans, clustk, dclustm, dclusth, dcluste, clusteval, clustcerr, clustc,

ClusterTools Contents

ClusterTools User Guide

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