Investigation of Expert Addition Criteria for Dynamically Changing Online Ensemble Classifiers with Multiple Adaptive Mechanisms

Abstract : We consider online classification problem, where concepts may change over time. A prominent model for creation of dynamically changing online ensemble is used in Dynamic Weighted Majority (DWM) method. We analyse this model, and address its high sensitivity to misclassifications resulting in creation of unnecessary large ensembles, particularly while running on noisy data. We propose and evaluate various criteria for adding new experts to an ensemble. We test our algorithms on a comprehensive selection of synthetic data and establish that they lead to the significant reduction in the number of created experts and show slightly better accuracy rates than original models and non-ensemble adaptive models used for benchmarking.
Type de document :
Communication dans un congrès
Harris Papadopoulos; Andreas S. Andreou; Lazaros Iliadis; Ilias Maglogiannis. 9th Artificial Intelligence Applications and Innovations (AIAI), Sep 2013, Paphos, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-412, pp.646-656, 2013, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-642-41142-7_65〉
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01459657
Contributeur : Hal Ifip <>
Soumis le : mardi 7 février 2017 - 13:07:11
Dernière modification le : vendredi 1 décembre 2017 - 01:16:33
Document(s) archivé(s) le : lundi 8 mai 2017 - 14:07:19

Fichier

978-3-642-41142-7_65_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Rashid Bakirov, Bogdan Gabrys. Investigation of Expert Addition Criteria for Dynamically Changing Online Ensemble Classifiers with Multiple Adaptive Mechanisms. Harris Papadopoulos; Andreas S. Andreou; Lazaros Iliadis; Ilias Maglogiannis. 9th Artificial Intelligence Applications and Innovations (AIAI), Sep 2013, Paphos, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-412, pp.646-656, 2013, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-642-41142-7_65〉. 〈hal-01459657〉

Partager

Métriques

Consultations de la notice

50

Téléchargements de fichiers

25