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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of advanced computational intelligence and intelligent informatics Ročník 13; číslo 3; s. 331 - 337
Hlavní autor: Osman, Hassab Elgawi
Médium: Journal Article
Jazyk:angličtina
Vydáno: 20.05.2009
ISSN:1343-0130, 1883-8014
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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