PHemoNet: A Multimodal Network for Physiological Signals

TL;DR

PHemoNet is a novel hypercomplex deep learning model that effectively combines multimodal physiological signals for emotion recognition, outperforming existing methods in classifying emotional states from EEG and other signals.

Contribution

This paper introduces PHemoNet, a hypercomplex neural network architecture that enhances multimodal emotion recognition from physiological signals by capturing latent relations between modalities.

Findings

Outperforms state-of-the-art models on MAHNOB-HCI dataset

Effectively classifies valence and arousal from EEG and physiological signals

Demonstrates the effectiveness of hypercomplex domain modeling in multimodal emotion recognition

Abstract

Emotion recognition is essential across numerous fields, including medical applications and brain-computer interface (BCI). Emotional responses include behavioral reactions, such as tone of voice and body movement, and changes in physiological signals, such as the electroencephalogram (EEG). The latter are involuntary, thus they provide a reliable input for identifying emotions, in contrast to the former which individuals can consciously control. These signals reveal true emotional states without intentional alteration, thus increasing the accuracy of emotion recognition models. However, multimodal deep learning methods from physiological signals have not been significantly investigated. In this paper, we introduce PHemoNet, a fully hypercomplex network for multimodal emotion recognition from physiological signals. In detail, the architecture comprises modality-specific encoders and a fusion module. Both encoders and fusion modules are defined in the hypercomplex domain through parameterized hypercomplex multiplications (PHMs) that can capture latent relations between the different dimensions of each modality and between the modalities themselves. The proposed method outperforms current state-of-the-art models on the MAHNOB-HCI dataset in classifying valence and arousal using electroencephalograms (EEGs) and peripheral physiological signals. The code for this work is available at https://github.com/ispamm/MHyEEG.