Weighted Delta Factor Cluster Ensemble Algorithm for Categorical Data Clustering in Data Mining

Weighted Delta Factor Cluster Ensemble Algorithm for Categorical Data Clustering in Data Mining

Sarumathi Sengottaian1, Shanthi Natesan2, and Sharmila Mathivanan3

1Department of Information Technology, K.S.R College of Technology, India

2Department of Computer Science and Engineering, Nandha Engineering College, India

3Department of Information Technology, M.Kumarasamy College of Engineering, India

Abstract: Though many cluster ensemble approaches came forward as a potential and dominant method for enhancing the robustness, stability and the quality of individual clustering systems, it is intensely observed that this approach in most cases generate a final data partition with deficient information. The primary ensemble information matrix generated in the traditional cluster ensemble approaches results only the cluster data point relations with unknown entries. This paper mainly denotes the improved analysis of the Link based Cluster Ensemble (LCE) approach which overcomes the problem of degrading the quality of clustering result and in particular it presents an efficient novel Weighted Delta Factor Cluster Ensemble algorithm (WDFCE) which enhances the refined matrix by augmenting the values of similitude measures between the clusters formed in the Bipartite cluster graph. Subsequently to obtain the final ultimate cluster result, the pairwise-similarity consensus method is used in which K-means clustering technique is applied over the similarity measures that are formulated from the Refined Similitude Matrix (RSM). Experimental results on few UCI datasets and synthetic dataset reveals that this proposed method always outperforms the traditional cluster ensemble techniques and individual clustering algorithms.

 

Keywords: Clustering, cluster ensembles, consensus function, data mining, refined matrix, similitude measures.

 

 


Received October 28, 2013, accepted November 4, 2014 

 

Full Text

Read 2495 times Last modified on Wednesday, 08 May 2019 03:53
Share
Top
We use cookies to improve our website. By continuing to use this website, you are giving consent to cookies being used. More details…