MATLAB: Help in k means clustering

Question

Dear all, I am still not comfortable with k-means clustering in classification. Especially while rerunning with the code

eva = evalclusters(params,'kmeans','silhouette','KList',[2:20]);

It gives me different cases. Also while using separate code like

[idx,cent,sumdist, meansilh] =kcluster('param2W_sac.cld', optkn, s);

there is different answers. I think I am concemptually wrong in using rng-function. Is there some one to help me in this manner. It will be great is there availability to have online tutor in such cases.

Answer 1

There is a randomness component in k-means clustering, as you surmise.

Have you tried putting the statement

rng(1)

at the beginning of your code? This will set the generator seed, and therefore produce the same series of pseudorandom numbers each time you run it.