|
Abstract
Clustering is a division of data into groups of similar objects. It's a
subject of active research in several fields such as statistics, pattern
recognition and data mining. Data mining adds to clustering the
complications of very large datasets with large amounts of attributes with
different data type. A variety of clustering algorithms have recently
emerged that can solve the problem successfully. In these algorithms,
density-based clustering algorithms can meet a lot of clustering
requirements very well. There are two major types of density-based
clustering algorithms, connectivity-based and density function based. In
this presentation, I'll introduce the representatives of these two kinds
of algorithms respectively. They are DBSCAN and DENCLUE. At the end of
presentation, I'll summary the traits of density-based clustering
algorithms and describe some open research issues.
Read the Presentation
Slides...
Referred Papers
|