Visualization of Crisp and Rough Clustering using MATLAB

Abstract

The main goal of data visualization is to communicate information clearly and effectively through graphical means. In the new millennium, data visualization has become an active area of research, teaching, and development. There are different types of open source software available in market to improve the visualizing capabilities like Weka3.6, ORANGE, MATLAB 6.0 etc., of which MATLAB an advanced interactive software package specially designed for scientific and engineering computation. Data mining is a “knowledge discovery process of extracting previously unknown, actionable information from very large databases”. Data mining is an information extraction activity, where it searches for consistent pattern and/or systematic relationship between variables. Data Clustering is similar to classification in which, the objects of similar properties is placed in one class of objects. Conventional clustering or crisp clustering assigns objects to exactly one cluster whereas in rough clustering an object may display characteristics of different clusters. The objective of clustering is to find the right groups or clusters, for the given set of objects.