Agreement Rate Initialized Maximum Likelihood Estimator for Ensemble Classifier Aggregation and Its Application in Brain-Computer Interface

TL;DR

This paper introduces ARIMLE, a novel ensemble classifier fusion method that estimates classifier accuracy from unlabeled data and refines it with EM, improving performance in brain-computer interface tasks.

Contribution

The paper presents ARIMLE, a new weighted ensemble method combining agreement rate estimation and maximum likelihood refinement, outperforming traditional voting and comparable methods.

Findings

ARIMLE outperforms majority voting in BCI classification.

ARIMLE achieves better or comparable results to state-of-the-art methods.

The approach effectively estimates classifier accuracy from unlabeled data.

Abstract

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.