Fast Cluster Polygonization and its Applications in Data-Rich Environments

We develop a linear time method for transforming clusters of 2D-point data into area data while identifying the shape robustly. This method translates a data layer into a space filling layer where shaped clusters are identified as the resulting regions. The method is based on robustly identifying cluster boundaries in point data using the Delaunay Diagram. The method can then be applied to modelling point data, to displaying choropleth maps of point data without a reference map, to identifying association rules in the spatial dimension for geographical data mining, or to measuring a gap between clusters for cluster validity.