Performance Exploration on Various Document Clustering Techniques with K-Means Family

Abstract

Clustering performs a important position in numerous fields which include Computer science & packages, facts, pattern reputation, system studying technique and find out dating among the files. Clustering focuses on document clustering, and other related area. Increase within the extent of statistics saved in virtual form (text, photograph, audio) has improved the need for requirement of an automated tool, that allows people to find and manage the records in an efficient way. Usually clustering refer to document clustering technique investigates the documents and find its relation. This paper center of attention on the a range of clustering methods and evaluation its overall performance. This paper also categories the document clustering techniques as three major groups, namely Group K-means, Expectation Maximization and Semantic-based techniques (Hybrid method). Several experiments were conducted to analyse the performance accuracy and Speed.