A Supervised Information Enhanced Multi-Granularity Contrastive Learning Framework for EEG Based Emotion Recognition

TL;DR

This paper presents SI-CLEER, a novel supervised contrastive learning framework that enhances EEG-based emotion recognition by integrating multi-granularity contrastive learning with classification, achieving superior accuracy and robustness.

Contribution

It introduces a joint learning model combining contrastive and classification losses for EEG emotion recognition, improving upon existing methods.

Findings

SI-CLEER outperforms state-of-the-art methods on the SEED dataset.

Electrode analysis highlights the importance of frontal and temporal regions.

The framework demonstrates robustness and versatility across EEG classification tasks.

Abstract

This study introduces a novel Supervised Info-enhanced Contrastive Learning framework for EEG based Emotion Recognition (SICLEER). SI-CLEER employs multi-granularity contrastive learning to create robust EEG contextual representations, potentiallyn improving emotion recognition effectiveness. Unlike existing methods solely guided by classification loss, we propose a joint learning model combining self-supervised contrastive learning loss and supervised classification loss. This model optimizes both loss functions, capturing subtle EEG signal differences specific to emotion detection. Extensive experiments demonstrate SI-CLEER's robustness and superior accuracy on the SEED dataset compared to state-of-the-art methods. Furthermore, we analyze electrode performance, highlighting the significance of central frontal and temporal brain region EEGs in emotion detection. This study offers an universally applicable approach with potential benefits for diverse EEG classification tasks.