MMoGCN: Un modelo de red neuronal convolucional de mezcla de puertas múltiples para el reconocimiento de trastornos...

Emotional states and mood disorders are closely interconnected, and their joint recognition serves as a critical pathway to uncovering their intrinsic relationship. Currently, deep learning models based on electroencephalogram (EEG) have achieved significant progress in single tasks such as emotion recognition or mood disorder recognition. However, most existing models are limited to handling only one of these tasks independently and fail to effectively leverage the shared features in EEG data related to both emotions and mood disorders. This limitation hinders the in-depth exploration of the complex interplay between emotions and mood disorders. Therefore, this study aims to develop an EEG-based deep learning framework for the joint recognition of emotions and mood disorders, thereby providing a foundation for further investigation into their interaction.} Approach. We design a multi-gate mixture-of-experts graph convolutional network model(MMoGCN) for joint emotion and mood disorder recognition. MMoGCN comprises three key modules: (1) a Feature Extraction Module based on Differential Entropy (DE) to robustly represent EEG signals; (2) a Multi-Gated Shared Experts Module (MGSE), which integrates two experts, and combines them through a gating mechanism to extract shared representations across tasks; and (3) Adaptive Task-Specific Towers (ATST), which consist of individual classification towers for each task and incorporate an Adaptive Weighting Loss (AWL) function to dynamically adjust task contributions. MMoGCN is evaluated on a self-collected dataset and further validated on the public DEAP dataset.} Main results. MMoGCN achieves superior performance compared with state-of-the-art single-task and multi-task baselines in both emotion and mood disorder recognition. Validation experiments on DEAP further demonstrate the scalability and generalization of MMoGCN. Significance. This work presents an effective multi-task learning model for joint emotion and clinical state recognition based on EEG. Additionally, we analyze cognitive differences in emotional responses between healthy controls and subjects with mood disorders, providing methodological insights and potential guidance for cognitive rehabilitation from both cognitive and emotional perspectives.