Study on Framework for Efficient Document Clustering on Centralized System

The word "cluster" is used broadly in computer networking to refer to a number of different implementations of shared computing resources. Typically, a cluster integrates the resources of two or more computing devices (that could otherwise function separately) together for some common purpose. In this paper we have presented brief introduction about cluster. We also presented document cluster, similarity measure and cosine similarity.

Keywords: -Cluster, Similarity Measure.