International Journal of Advanced Information and Communication Technology


High Dimensional Data Clustering Through Efficient Evolutionary Algorithm

S. Saravanan, Assistant Professor, Adhiyamaan College of Engineering, Hosur, Tamilnadu, India.

G.M. Kadhar Nawaz, Director, Sona College of Technology, Salem, Tamilnadu, India.

DOI : 01.0401/ijaict.2014.03.17

International Journal of Advanced Information and Communication Technology

Received On : July 12, 2015

Revised On : August 23, 2015

Accepted On : September 14, 2015

Published On : October 05, 2015

Volume 02, Issue 10

Pages : 364-371

Abstract


Dimensionality reduction is essential in multidimensional data mining since the dimensionality of real time data could easily extend to higher dimensions. Most recent efforts on dimensionalityreduction, however, are not adequate for multidimensional data due to lack of scalability. In this paper, we use the evolutionary algorithm for the dimension reduction process. Initially, our proposed evolutionary algorithm gets the values of a number of clusters and the total number of dimensions of the database. For each number of dimensions, we generate a solution. The next step of our proposed algorithm is selection of centroid for each cluster from the dataset as per the dimension of each solution. The next step is to evaluate each solution through our proposed fitness function and store the values of best one subsequently the solutions are updated through the proposed attribute evaluation process. As a consequence of the proposed evolutionary algorithm selects the best set of dimension with the best set of centroids which will apply for the K-Means clustering algorithm to create the clusters. Finally, our proposed hybrid optimization algorithm is implemented using JAVA and we compare our proposed algorithm with the standard dimension reduction algorithm in terms of clustering accuracy.

Keywords


Wireless Mesh Network, Capability Based Routing, QoS, Security, Mobile Agents, Threat Locator Mechanism.

Cite this article


S. Saravanan, G.M. Kadhar Nawaz, “High Dimensional Data Clustering Through Efficient Evolutionary Algorithm ” INTERNATIONAL JOURNAL OF ADVANCED INFORMATION AND COMMUNICATION TECHNOLOGY, pp.364-371, October 05, 2015.

Copyright


© 2015 S. Saravanan, G.M. Kadhar Nawaz. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.