The Effect of the Characteristics of the Dataset on the Selection Stability
Authors:
- Salem AlelyaniSASalem Alelyani
- Huan LiuHLHuan Liu
- Lei WangLWLei Wang
- 1 November 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10823409,p. 970-977
Abstract
Feature selection is an effective technique to reduce the dimensionality of a data set and to select relevant features for the domain problem. Recently, stability of feature selection methods has gained increasing attention. In fact, it has become a crucial factor in determining the goodness of a feature selection algorithm besides the learning performance. In this work, we conduct an extensive experimental study using verity of data sets and different well-known feature selection algorithms in order to study the behavior of these algorithms in terms of the stability.Keywords
This publication has 10 references indexed in Scilit:
- A Variance Reduction Framework for Stable Feature Selection2010
- Effect of finite sample size on feature selection and classification: A simulation studyMedical Physics, 2010
- Stable feature selection via dense feature groups2008
- Stability of feature selection algorithms: a study on high-dimensional spacesKnowledge and Information Systems, 2006
- Reliable gene signatures for microarray classification: assessment of stability and performanceBioinformatics, 2006
- Elements of Information Theory2001
- The Elements of Statistical Learning2001
- 10.1162/153244303322753616Applied Physics Letters, 2000
- Feature Selection for Knowledge Discovery and Data Mining1998
- Feature selection: evaluation, application, and small sample performanceIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997