Investigation of Expert Addition Criteria for Dynamically Changing Online Ensemble Classifiers with Multiple Adaptive Mechanisms - Artificial Intelligence Applications and Innovations Access content directly
Conference Papers Year : 2013

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

Rashid Bakirov
  • Function : Author
  • PersonId : 1000675
Bogdan Gabrys
  • Function : Author
  • PersonId : 1000676

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.
Fichier principal
Vignette du fichier
978-3-642-41142-7_65_Chapter.pdf (535.9 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01459657 , version 1 (07-02-2017)

Licence

Attribution

Identifiers

Cite

Rashid Bakirov, Bogdan Gabrys. Investigation of Expert Addition Criteria for Dynamically Changing Online Ensemble Classifiers with Multiple Adaptive Mechanisms. 9th Artificial Intelligence Applications and Innovations (AIAI), Sep 2013, Paphos, Greece. pp.646-656, ⟨10.1007/978-3-642-41142-7_65⟩. ⟨hal-01459657⟩
68 View
64 Download

Altmetric

Share

Gmail Facebook X LinkedIn More