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
- EP ID EP94654
- DOI -
- Views 174
- Downloads 0
Dynamics of Flexible Wind Power Generator with Unbalanced Rotor
The paper deals with dynamic analysis of a wind power generator as a large flexible structure with high speed rotating machines and considerable masses. The dynamic model is considered as a multibody system of rigi...
Mathematical Model for Fluid Flow and Heat Transfer Processes in Plate Exchanger
Within the analytical solution of the system of equations which solve fluid flow and heat transfer processes, the elliptical and parabolic differential equations based on initial and boundary conditions is usually...
Analysis of Specific Electric Conductivity of Thin Films of Polyaniline Doped with Sulfuric and Hydrochloric Acid
This paper describes the specific electric conductivity of thin films of the polymer polyaniline, depending on the type of material that is used for doping the specified polymer. In our own laboratory, there were m...
A Review on the Use of Performance Indicators in the Public Sector
When set in strategic context and developed according to valuable criteria, performance indicators can be a powerful tool for different purposes in the public sector. Since their use in public services is evidently incre...
A Query Evaluation Approach using Opinions of Turkish Financial Market Professionals
People who do not have expertise in the financial area may not see the relationship between the numerical and linguistic data. In our study, a knowledge discovery approach using Turkish natural language processing...