K-means method is one of clustering techniques. The method aims at dividing objects into clusters to minimize the sum of distances between the objects and the corresponding cluster centers:
Where:
k. The number of clusters.
Si. Obtained clusters.
yi. Centers of the obtained clusters.
At each iteration the k-means method recalculates the center of masses for the cluster obtained at the previous step, next the objects are again divided into clusters.
See also:
ISmKmeansClusterAnalysis | Library of Methods and Models