Variable Ranking for Online Ensemble Learning

In proposing, incremental feature selection based on correlation ranking (CR) for classification problems, we develop on-line training using the random forests (RF) algorithm, then evaluate the performance of the combination based on an NIPS 2003 Feature Selection Challenge dataset. Results show tha...

Full description

Saved in:
Bibliographic Details
Published inJournal of advanced computational intelligence and intelligent informatics Vol. 13; no. 3; pp. 331 - 337
Main Author Osman, Hassab Elgawi
Format Journal Article
LanguageEnglish
Published 20.05.2009
Online AccessGet full text

Cover

More Information
Summary:In proposing, incremental feature selection based on correlation ranking (CR) for classification problems, we develop on-line training using the random forests (RF) algorithm, then evaluate the performance of the combination based on an NIPS 2003 Feature Selection Challenge dataset. Results show that our approach achieves performance comparable to others batch learning algorithms, including RF.
ISSN:1343-0130
1883-8014
DOI:10.20965/jaciii.2009.p0331