Diverse classifier ensemble creation based on heuristic dataset modification

DOI10.1080/02664763.2017.1363163MaRDI QIDQ5035729zbMATH OpenOpenAlexFDO

Authors Hamid Jamalinia, Saber Khalouei, Vahideh Rezaie, Samad Nejatian, Karamolah Bagheri-Fard, Hamid Parvin

Publication date 22 February 2022

Published in Journal of Applied Statistics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/02664763.2017.1363163

zbMATH Keywords

classificationdiversityartificially created datacombining classifier

Mathematics Subject Classification ID

Applications of statistics (62Pxx)

Recommendations

• Improving bagging performance through multi-algorithm ensembles
• scientific article; zbMATH DE number 5646846
• Research on construction of base classifiers based on discretization method for ensemble learning
• scientific article; zbMATH DE number 2089096
• FuzzyBagging: a novel ensemble of classifiers

Cites work

• scientific article; zbMATH DE number 5957419 (Why is no real title available?)
• A decision-theoretic generalization of on-line learning and an application to boosting
• Bagging predictors
• BoosTexter: A boosting-based system for text categorization
• Boosting first-order learning
• Coevolutionary learning of neural network ensemble for complex classification tasks
• Combining Pattern Classifiers
• Random forests
• Sparse ensembles using weighted combination methods based on linear programming
• Subsemble: an ensemble method for combining subset-specific algorithm fits
• The elements of statistical learning. Data mining, inference, and prediction
• Weighted bagging: a modification of AdaBoost from the perspective of importance sampling

Cited in

(1)

• Research on construction of base classifiers based on discretization method for ensemble learning

Describes a project that uses

Uses Software

• BoosTexter
• AdaBoost.MH

This page was built for publication: Diverse classifier ensemble creation based on heuristic dataset modification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5035729)