An NMF and Hierarchical Based Clustering Approach to support Multiviewpoint-Based

  IJCOT-book-cover
 
International Journal of Computer Trends and Technology (IJCTT)          
 
© - Issue 2013 by IJCTT Journal
Volume-4 Issue-3                           
Year of Publication : 2013
Authors :K.S.Jeen Marseline, A.Premalatha

MLA

K.S.Jeen Marseline, A.Premalatha "An NMF and Hierarchical Based Clustering Approach to support Multiviewpoint-Based"International Journal of Computer Trends and Technology (IJCTT),V4(3):286-291 Issue 2013 .ISSN 2231-2803.www.ijcttjournal.org. Published by Seventh Sense Research Group.

Abstract: - In data mining, clustering technique is an interesting and important technique. The main goal of the clustering is finding the similarity between the data points or similarity between the data within intrinsic data structure and grouping them the data into single groups (or) subgroups in clustering process. The existing Systems is mainly used for finding the next frequent item set using greedy method, greedy algorithm can reduce the overlapping between the documents in the itemset. The documents will contain both the item set and some remaining item sets. The result of the clustering process is based on the order for choosing the item sets in the greedy approach; it doesn`t follow a sequential order when selecting clusters. This problem will lead to gain less optimal solution for clustering method. To resolve this problem, proposed system which is developing a novel hierarchal algorithm for document clustering which produces superlative efficiency and performance which is mainly focusing on making use of cluster overlapping phenomenon to design cluster merging criteria. Hierarchical Agglomerative clustering establishes through the positions as individual clusters and, by the side of every step, combines the mainly similar or neighboring pair of clusters. This needs a definition of cluster similarity or distance. With this we are proposing the multiview point clustering approach with the NMF clustering method. The experimental results will be displayed based on the clustering result of three algorithms.

References-

[1] Johnson,S.C., "Hierarchical Clustering Schemes" Psychometrika, 2:241-254. 1967
[2] Cole, A. J. & Wishart, D. An improved algorithm for the Jardine-Sibson method of generating overlapping clusters. The Computer Journal 13(2):156- 163. (1970).
[3] D`andrade,R., "U-Statistic Hierarchical Clustering" Psychometrika, 4:58-67. 1978
[4] Jeff A. Bilmes. A Gentle Tutorial of the EM Algorithm and its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models. ICSI TR-97-021, U.C. Berkeley,1998.
[5] P. Berkhin. Survey of clustering data mining techniques.Unpublished manuscript, available from accrue.com, 2002.
[6] A. Blum and T. Mitchell. Combining labeled and unlabeled data with co-training. In Proceedings of the Conference on Computational Learning Theory, pages 92–100, 1998.
[7] U. Brefeld and T. Scheffer. Co-EM support vector learning. In Proc. of the Int. Conf. on Machine Learning, 2004.
[8] M. Collins and Y. Singer. Unsupervised models for named entity classification. In EMNLP, 1999.

Keywords— Clustering, Multi-view point, Hierarchical clustering, Hierarchical Agglomerative clustering, Cosine similarity, Non-Negative Matrix Factorization.