This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Parameter Tuning for Induction-Algorithm-Oriented Feature Elimination
March/April 2004 (vol. 19 no. 2)
pp. 40-49
Ying Yang, University of Vermont
Xindong Wu, University of Vermont

Induction-algorithm-oriented feature elimination considers not only the data and the target concept but also the induction algorithm that will learn the target concept from the data. Because of its very nature, IAOFE is controlled by abundant parameters. This article reports on a study to understand which parameter settings can produce ideal performance from IAOFE. The authors ran comparative studies for various parameter settings and identified effective configurations. Empirical evidence from a large number of data sets demonstrates that IAOFE, with the suggested parameter configurations, can achieve higher predictive accuracy than existing popular feature selection approaches with statistically significant frequencies.

Index Terms:
feature elimination, parameter tuning, inductive learning
Citation:
Ying Yang, Xindong Wu, "Parameter Tuning for Induction-Algorithm-Oriented Feature Elimination," IEEE Intelligent Systems, vol. 19, no. 2, pp. 40-49, March-April 2004, doi:10.1109/MIS.2004.1274910
Usage of this product signifies your acceptance of the Terms of Use.