The system is representing hierarchical multilevel approach of clustering and explores dynamic modeling in hierarchical clustering. Presented approach operates on a k-nn graph and hyper graph in which nodes represent data items, and weighted edges represent similarities among the data items. Presented hierarchical multilevel algorithm consists of several stages: building the graph, coarsening, partitioning, uncoarsening. Exploring of different combinations of algorithms on different stages for different data sets is the main goal of the work.
Ключові слова: cluster analysis, hierarchical clustering, coarsening, partitioning, uncoarsening, Chameleon
Research of dynamic clustering on linearly inseparable plagued experimental data,
Information Processing Systems,