High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

A Modified Approach for Feature Subset Selection using Multithreaded Boruvka's Algorithm


Vaidehi Bhavsar , L. J. Institute of Technology


Subset Selection, Boruvka's Algorithm


Data mining is a multidisciplinary effort to extract a small chunk of knowledge from data. Feature Subset selection is an effective technique in dealing with dimensionality reduction. A feature selection algorithm may be evaluated from both the efficiency and effectiveness points of view. Based on these criteria, a fast clustering-based feature selection algorithm, FAST, is given. It is based on the minimum spanning tree method. The algorithm is a two steps process in which, In the first step, features are divided into clusters by using graph-theoretic clustering methods. In the second step, the most representative feature that is strongly related to target classes is selected from each cluster to form the final subset of features. The clustering-based scheme of FAST has a high possibility of producing a subset of constructive and independent characteristics. In this FAST algorithm, I have used Boruvka's Algorithm. By using Boruvka’s Algorithm, parallel computing can be done. The proposed system will decrease the computational time of creating MST in the FAST Algorithm. I also used Chi-Square test that is used to find correlation among attributes for removing irrelevant features. Hence, this will improve the accuracy.

Other Details

Paper ID: IJSRDV3I40771
Published in: Volume : 3, Issue : 4
Publication Date: 01/07/2015
Page(s): 1089-1092

Article Preview

Download Article