An Enhanced K Means Clustering using Improved Hopfield Artificial Neural Network and Genetic Algorithm
M. Sakthi1, Antony Selvadoss Thanamani2
1M.Sakthi, Research Scholar Head, Department of Computer Science, NGM College, Pollachi (Tamil Nadu), India.
2Antony Selvadoss Thanamani, Associate Professor Head, Department of Computer Science, NGM College, Pollachi (Tamil Nadu), India.
Manuscript received on 21 July 2013 | Revised Manuscript received on 28 July 2013 | Manuscript published on 30 July 2013 | PP: 16-21 | Volume-2 Issue-3, July 2013 | Retrieval Number: C0671072313/2013©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Due to the increase in the quantity of data across the world, it turns out to be very complex task for analyzing those data. Categorize those data into remarkable collection is one of the common forms of understanding and learning. This leads to the requirement for better data mining technique. These facilities are provided by a standard data mining technique called Clustering. The key intention of this technique is to categorize a dataset into a set of clusters that contains similar data items, as computed by some distance function. One of the widely used clustering techniques is K-Means clustering. K-Means clustering is very simple and effective for clustering. But, the main disadvantage of this technique is when the large dataset is used for clustering. To overcome this difficulty, various researchers focus on suggesting better alteration in K-Means clustering. This paper provides a new technique to modify K-Means clustering which can result in better performance. For initialization, this paper uses an improved version of Hopfield Artificial Neural Network (HANN) algorithm. Also, the Genetic Algorithm (GA) is in combined with K-Means algorithm. The experimental result indicates that the proposed KMeans clustering algorithm results in better clustering result.
Keywords: K-Means, Genetic Algorithm, Hopfield Artificial Neural Network
Scope of the Article: Computer Network