Electroencephalogram Emotion Recognition via AUC Maximization

TL;DR

This paper introduces an AUC maximization approach using numerical optimization to improve emotion recognition from EEG data, especially for minority classes in imbalanced datasets, outperforming traditional classifiers.

Contribution

The study presents a novel AUC maximization method for EEG emotion recognition that effectively handles class imbalance, surpassing traditional linear classifiers in performance.

Findings

Recall increased from 41.6% to 79.7%.

F1-score improved from 0.506 to 0.632.

Outperforms logistic regression and SVM in imbalanced scenarios.

Abstract

Imbalanced datasets pose significant challenges in areas including neuroscience, cognitive science, and medical diagnostics, where accurately detecting minority classes is essential for robust model performance. This study addresses the issue of class imbalance, using the `Liking' label in the DEAP dataset as an example. Such imbalances are often overlooked by prior research, which typically focuses on the more balanced arousal and valence labels and predominantly uses accuracy metrics to measure model performance. To tackle this issue, we adopt numerical optimization techniques aimed at maximizing the area under the curve (AUC), thus enhancing the detection of underrepresented classes. Our approach, which begins with a linear classifier, is compared against traditional linear classifiers, including logistic regression and support vector machines (SVM). Our method significantly outperforms these models, increasing recall from 41.6\% to 79.7\% and improving the F1-score from 0.506 to 0.632. These results highlight the efficacy of AUC maximization via numerical optimization in managing imbalanced datasets, providing an effective solution for enhancing predictive accuracy in detecting minority but crucial classes in out-of-sample datasets.