Consider partitioning clustering and the following constraint on clusters:

Consider partitioning clustering and the following constraint on clusters: The number of objects in each cluster must be between

n/k ( 1-δ) and , n/k( 1+δ) where n is the total number of objects in the data set, k is the number of clusters desired, and in [0,1] is a parameter. Can you extend the k-means method to handle this constraint? Discuss situations where the constraint is hard and soft.