Research Article Open Access

DISTINGUISHABILITY BASED WEIGHTED FEATURE SELECTION USING COLUMN WISE K NEIGHBORHOOD FOR THE CLASSIFICATION OF GENE MICROARRAY DATASET

Jeyachidra1 and Punithavalli2
  • 1 Department of Computer Science and Applications, Periyar Maniammai University, Vallam-613 403, Thanjavur, Tamilnadu, India
  • 2 Department of Computer Science, Sri Ramakrishna Engineering College, Coimbatore, Tamilnadu, India

Abstract

In data mining, much research is being carried out to discover the previously unknown, valid, novel, useful and understandable patterns in large databases. The patterns must be actionable so that they might be used for decision making to a variety of applications in healthcare. In this study, feature subset selection is an important area, where many approaches have been proposed. Hence, the authors chosen three existing feature selection algorithms analyzed their performance using the publicly available standard colon tumor dataset. The performance of the existing three methods evaluated and compared each method with DWFS-CKN under study.

American Journal of Applied Sciences
Volume 11 No. 1, 2014, 1-7

DOI: https://doi.org/10.3844/ajassp.2014.1.7

Submitted On: 6 September 2013 Published On: 13 November 2013

How to Cite: Jeyachidra, & Punithavalli, (2014). DISTINGUISHABILITY BASED WEIGHTED FEATURE SELECTION USING COLUMN WISE K NEIGHBORHOOD FOR THE CLASSIFICATION OF GENE MICROARRAY DATASET. American Journal of Applied Sciences, 11(1), 1-7. https://doi.org/10.3844/ajassp.2014.1.7

  • 3,013 Views
  • 3,335 Downloads
  • 2 Citations

Download

Keywords

  • Feature Selection
  • Microarray Data
  • Classification
  • C4.5
  • Bayes