K-NichePSO clustering
N. Salmani Niasar, Sasan Yazdani, M. Mohajeri · 2008
In clustering algorithm based on criterion function optimization, at first the numbers of clusters are predefined the clustering will be done. For obtaining a suitable result, these algorithms must be suitable with different number of clusters, after that result will be evaluated. To solve this problem a new method is presented, in this article NichePSO algorithm which enables us to calculate the number of clusters and estimate their position by considering data automatically.