Emotion recognition based on multi-modal electrophysiology multi-head attention Contrastive Learning

TL;DR

This paper introduces ME-MHACL, a self-supervised contrastive learning approach utilizing multi-head attention for multimodal electrophysiological emotion recognition, effectively addressing data scarcity and cross-individual generalization challenges.

Contribution

It proposes a novel self-supervised contrastive learning framework with multi-head attention for multimodal electrophysiological emotion recognition, improving performance and generalization.

Findings

Outperforms existing benchmark methods on DEAP and MAHNOB-HCI datasets.

Demonstrates strong cross-individual generalization ability.

Effectively learns meaningful features from unlabeled signals.

Abstract

Emotion recognition is an important research direction in artificial intelligence, helping machines understand and adapt to human emotional states. Multimodal electrophysiological(ME) signals, such as EEG, GSR, respiration(Resp), and temperature(Temp), are effective biomarkers for reflecting changes in human emotions. However, using electrophysiological signals for emotion recognition faces challenges such as data scarcity, inconsistent labeling, and difficulty in cross-individual generalization. To address these issues, we propose ME-MHACL, a self-supervised contrastive learning-based multimodal emotion recognition method that can learn meaningful feature representations from unlabeled electrophysiological signals and use multi-head attention mechanisms for feature fusion to improve recognition performance. Our method includes two stages: first, we use the Meiosis method to group sample and augment unlabeled electrophysiological signals and design a self-supervised contrastive learning task; second, we apply the trained feature extractor to labeled electrophysiological signals and use multi-head attention mechanisms for feature fusion. We conducted experiments on two public datasets, DEAP and MAHNOB-HCI, and our method outperformed existing benchmark methods in emotion recognition tasks and had good cross-individual generalization ability.