A Comparative Study of Different Density based Spatial Clustering Algorithms

Clustering is an important descriptive model in data mining. It groups the data objects into meaningful classes or clusters such that the objects are similar to one another within the same cluster and are dissimilar to other clusters. Spatial clustering is one of the significant techniques in spatial data mining, to discover patterns from large spatial databases. In recent years, several basic and advanced algorithms have been developed for clustering spatial datasets. Clustering technique can be categorized into six types namely partitioning, hierarchical, density, grid, model, and constraint based models. Among these, the density based technique is best suitable for spatial clustering. It characteristically consider clusters as dense regions of objects in the data space that are separated by regions of low density (indicating noise). The clusters which are formed based on the density are easy to understand, filter out noise and discover clusters of arbitrary shape. This paper presents a comparative study of different density based spatial clustering algorithms, and the merits and limitations of the algorithms are also evaluated.