cluster data for real time

I need to create a cluster of datas (in two dimensions for the example X & Y). I can use for example k-means… but for this I need to know “k”… and in my case I haven’t any idea of “k” value… I just know that “k” in most of case is lower than 12. If I use other clustering methods “silhouette” that work well off-line… but If I need to embedded, it in Simulink for an export in C++… that function are not compatible with compilation for ECU running

How I should solve this real time clustering issue?

Thank you in advance

[Walter Roberson]

If you were to cluster with all the k from 1 to 12, then how would you decide which was the "best" number of clusters?

Any deterministic clustering will always fit better with more clusters, until the number of clusters reaches the number of distinct points. Consider, after all, that if you were to place one cluster centroid at each unique point, then the distance of each point to its centroid would be 0, but that for any lower number of clusters, you could always improve the clustering by adding a centroid that matches exactly the location of one of the existing points that is not currently exactly at a centroid. Therefore, according to most definitions, the optimal number of clusters is the same as the number of distinct points.