Comparison of Feature Selection Techniques in Knowledge Discovery Process 

Journal Title: TEM JOURNAL - Year 2014, Vol 3, Issue 4

Abstract

 The process of knowledge discovery in data consists of five steps. Data preparation, which includes data cleaning and feature selection, takes away from 60% to 95% total time of the whole process. Thus, it is crucial phase of the process. The purpose of this research is to investigate feature selection techniques performance by conducting empirical research. Our comparison of three feature selection techniques reveals significant difference in feature selection techniques performance.

Authors and Affiliations

Dijana Oreški, Tomislav Novosel

Keywords

Related Articles

The Reliability to Predict Threat in Social Networks  

 During the analysis and study it will be possible to create and describe information damping mechanism for transition of threats from one user group to another (within the parameters of portraits), which is the mai...

 Improvement of the QoS for WiMAX Service Classes

 Mobile users connected to the WiMAX technology can use five different service classes according to their different needs. In this paper we propose priority based uplink scheduling scheme for IEEE 802.16 sta...

The Assessment of Students’ Satisfaction in the South-Eastern European Countries: An Alternative Approach for Evaluating the Quality of Higher Education 

 In this paper we assess the student satisfaction as an alternative approach for evaluating the quality of higher education. For this purpose we have carried out a survey on representative samples of students in two...

Loss-minimal Algorithmic Trading Based on Levy Processes 

 In this paper we optimize portfolios assuming that the value of the portfolio follows a Lévy process. First we identify the parameters of the underlying Lévy process and then portfolio optimization is performed by...

Productivity Fluid Management as a Tool for Saving Money in Manufacturing 

 The following paper discusses the benefits arising from introduction of productivity fluid management (PFM) and their impact on the performance of machinery and equipment. It discusses the benefits and impacts of i...

Download PDF file
  • EP ID EP94654
  • DOI -
  • Views 175
  • Downloads 0

How To Cite

Dijana Oreški, Tomislav Novosel (2014). Comparison of Feature Selection Techniques in Knowledge Discovery Process . TEM JOURNAL, 3(4), 285-290. https://europub.co.uk./articles/-A-94654