ntra cluster similarity of clique by positive and negative objects

Raghunath Kar, Minakshi Sahu, Tarini Charan Tripathy

Abstract


Clustering of high dimensional data sets
is a challenge in now a days. Finding of good
clusters is a big problem for the researchers. The
outlier detection of clusters and finalize about the
noisy data also an important thing in
highdimensional data sets. In this paper it is
researched about intracluster similarity of clusters
with respect to occurrence of positive and negative
objects through RandIndex. There are many
methods are present to find good clusters from the
high dimensional datasets like BIRCH, CLARA,
CLARANS, DBScan, PAM, CLIQUE etc.The
CLIQUE ( Clustering in Quest ) is a dimensionGrowth
subspace clustering method is used to find
clusters. Here the process starts at single
dimensional subspaces grows upward to higher
dimensional ones. After finding the clusters from
CLIQUE, with a user defined threshold value the
occurrence of positive and negative objects are
also found and it compares with the entropy of
positive and negative objects with the value of
RandIndex.


References


Data Mining Concepts and Techniques

Jiawei Han, Micheline Kamber

An empirical study on principal component

Analysis for clustering gene expression dada by

Ka yee yeung,Watter L. Ruzzo.

Insight into Datamining: Theory and Practice –

K.P.Soman, Shyam Diwakar, V.Ajay.

An Efficient Cell-based Clustering Method for

Handling Large, High-Dimensional Data Jae-Woo

Chang

Automatic Subspace Clustering of high

Dimensional Data for Data Mining Applications

by Rakesh Agrawal, Johannes Gehrke, Dimitrios

Gunopulos, Prabhakar Raghavan

Subspace Clustering for Uncertain Data by

Stephan Gunnemann, Hardy Kremer, Thomas

Seidl.

Subspace Clustering for High Dimensional Data:

A Review by Lance Parsons, Ehtesham Haque,

Haun Liu.

Mining Subspace Clusters: Enhanced Models,

Efficient Algorithms and an Objective

Evaluation Study by Emmanuel Muller.


Full Text: PDF [FULL TEXT]

Refbacks

  • There are currently no refbacks.


Copyright © 2013, All rights reserved.| ijseat.com

Creative Commons License
International Journal of Science Engineering and Advance Technology is licensed under a Creative Commons Attribution 3.0 Unported License.Based on a work at IJSEat , Permissions beyond the scope of this license may be available at http://creativecommons.org/licenses/by/3.0/deed.en_GB.

Â