Agreement rate initialized maximum likelihood estimator for ensemble classifier aggregation and its application in brain-computer interface

Wu, D; Lawhern, VJ; Gordon, S; Lance, BJ; Lin, CT

Agreement rate initialized maximum likelihood estimator for ensemble classifier aggregation and its application in brain-computer interface

Wu, D Lawhern, VJ Gordon, S Lance, BJ Lin, CT

Permalink

Publication Type:: Conference Proceeding
Citation:: 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings, 2017, pp. 724 - 729
Issue Date:: 2017-02-06

Closed Access

	Filename	Description	Size
	07844327.pdf	Published version	736.91 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wu, D	en_US
dc.contributor.author	Lawhern, VJ	en_US
dc.contributor.author	Gordon, S	en_US
dc.contributor.author	Lance, BJ	en_US
dc.contributor.author	Lin, CT https://orcid.org/0000-0001-8371-8197	en_US
dc.date.issued	2017-02-06	en_US
dc.identifier.citation	2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings, 2017, pp. 724 - 729	en_US
dc.identifier.isbn	9781509018970	en_US
dc.identifier.uri	http://hdl.handle.net/10453/113461
dc.description.abstract	© 2016 IEEE. Ensemble learning is a powerful approach to construct a strong learner from multiple base learners. The most popular way to aggregate an ensemble of classifiers is majority voting, which assigns a sample to the class that most base classifiers vote for. However, improved performance can be obtained by assigning weights to the base classifiers according to their accuracy. This paper proposes an agreement rate initialized maximum likelihood estimator (ARIMLE) to optimally fuse the base classifiers. ARIMLE first uses a simplified agreement rate method to estimate the classification accuracy of each base classifier from the unlabeled samples, then employs the accuracies to initialize a maximum likelihood estimator (MLE), and finally uses the expectation-maximization algorithm to refine the MLE. Extensive experiments on visually evoked potential classification in a brain-computer interface application show that ARIMLE outperforms majority voting, and also achieves better or comparable performance with several other state-of-the-art classifier combination approaches.	en_US
dc.relation.ispartof	2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings	en_US
dc.relation.isbasedon	10.1109/SMC.2016.7844327	en_US
dc.title	Agreement rate initialized maximum likelihood estimator for ensemble classifier aggregation and its application in brain-computer interface	en_US
dc.type	Conference Proceeding
utslib.for	0903 Biomedical Engineering	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

© 2016 IEEE. Ensemble learning is a powerful approach to construct a strong learner from multiple base learners. The most popular way to aggregate an ensemble of classifiers is majority voting, which assigns a sample to the class that most base classifiers vote for. However, improved performance can be obtained by assigning weights to the base classifiers according to their accuracy. This paper proposes an agreement rate initialized maximum likelihood estimator (ARIMLE) to optimally fuse the base classifiers. ARIMLE first uses a simplified agreement rate method to estimate the classification accuracy of each base classifier from the unlabeled samples, then employs the accuracies to initialize a maximum likelihood estimator (MLE), and finally uses the expectation-maximization algorithm to refine the MLE. Extensive experiments on visually evoked potential classification in a brain-computer interface application show that ARIMLE outperforms majority voting, and also achieves better or comparable performance with several other state-of-the-art classifier combination approaches.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/113461