Data Clustering using Bisecting K-Means

Clustering is one the one of the most important technique of data mining. It is used in many applications like fraud detection, image processing, bioinformatics etc. It has been used in various domains. Many types of the clustering techniques are the following like hierarchical, partitional, spectral clustering, density clustering, grid clustering, model based clustering etc. Bisecting K-Means comes under partitional clustering. It gives better performance, when huge data is used. There are many approached that are developed in the similar domain. One of the technique is Text Mining through which useful information is extracted through text. One of the important concept is statistical pattern mining through which important information is extracted by planning different trends and patterns. Input text patterns are structured that are derived from structured data and corresponding output is generated. The steps of text mining are categories of text, clustering text, extraction, summarization of text, E-R modeling. The various steps of text analysis are retrieval of information, lexical analysis for distribution of word frequency distribution study, recognition of pattern, tagging, extraction of information, techniques of data mining and also link analysis, association, visual and predictive analytics. In the given paper bisect. K Means algorithm is presented which has the features of k-Means and hierarchy clustering.