Skip to Main Content
Density-based spatial clustering algorithm DBSCAN has a relatively low efficiency since it carries out a large number of useless distance computing; Grid-based spatial clustering algorithm is more efficient, but the clustering result has a low accuracy. Considering the advantage and disadvantages of the two algorithms, this paper proposes a grid and density based fast clustering algorithm GNDBSCAN. This algorithm performs density-based clustering on datasets space, which has been divided by grids. It improves the efficiency of clustering and at the same time, maintains high accuracy for clustering results.
Artificial Intelligence and Computational Intelligence, 2009. AICI '09. International Conference on (Volume:4 )
Date of Conference: 7-8 Nov. 2009