Mining Subspace Clusters: Enhanced Models, Efficient Algorithms and an Objective Evaluation Study

Provided by: VLD Digital
Topic: Big Data
Format: PDF
In the knowledge discovery process, clustering is an established technique for grouping objects based on mutual similarity. However, in today's applications for each object very many attributes are provided in large and high dimensional databases. As multiple concepts described by different attributes are mixed in the same data set, clusters are hidden in subspace projections and do not appear in all dimensions. Subspace clustering aims at detecting such clusters in any projection of the database.

Find By Topic