International Journal of Computer Engineering & Applications
Regionalization is one of the biggest problems faced by spatial data mining while representing economic and social geography. This problem could be solved by the spatial clustering algorithm for grouping spatial objects. The paper purpose of regionalization is to find compact and dense regions which also represent the homogeneous distribution of non-spatial variables. In this paper, various clustering algorithms which are used to solve regionalization issues in spatial data mining are studied and also compare the performance of K-means and Ward's algorithm on cohesion, variance, precision and recall parameters done.