| |
This modified hyper plane clustering algorithm (HPCluster) works in two stages:
(1)Reduction of the dataset using cluster features and (2) Conventional k-means clustering
on the cluster features obtained in stage-1. The first stage of the algorithm is
derived from the Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH)
algorithm proposed by Zhang et al (Zhang et al., 1996) BIRCH summarizes a dataset
into a set of cluster features (subclus-ters) to reduce the scale of the clustering
problem. Dense data points that are extremely close to each other are treated collectively
as a single cluster feature and not individually.
This software is distributed under the Open Software License v3.0 agreement
To download the software please read and accept the license here
We designed the software so it can be deployed on most Windows operating systems.
The applications are written for the .NET Framework v1.1 using the C# programming
language.
|
|
|
