Question

I need and example showing how to use K-means clustering in MATLAB but using some prespecified datapoints as the initial seeds.

Thanks

Answer 1

IDX = kmeans(X,k,'start',seeds)

will run K-means with predefined datapoints seeds (such as k rows of X, but you can choose any seeds as long as it’s a k-by-p array, where p is the number of columns of X) as initial seeds. Note that if you specify seeds, you don’t need to specify k (pass [] instead). kmeans will infer from the number of rows of seeds how many clusters you want.

By default, kmeans chooses k randomly picked rows of X as seeds.