MMoGCN: a multi-gate mixture of graph convolutional network model for EEG emotion and mood disorder recognition
Daxing Zhang1, Yaru Guo1, Xinni Kong1
1School of Computer Science, Hangzhou Dianzi University, Hangzhou 310018, People's Republic of China.
Journal of Neural Engineering
|January 13, 2026
Summary
This study introduces a novel deep learning framework for simultaneously recognizing emotions and mood disorders using electroencephalogram (EEG) data. The model effectively captures shared neural features, outperforming existing methods in joint recognition tasks.
Area of Science:
- Neuroscience and Computational Psychiatry
- Application of deep learning in analyzing electroencephalogram (EEG) signals for mental state assessment.
Background:
- Emotional states and mood disorders are interconnected, yet current deep learning models often analyze them independently.
- Existing models struggle to leverage shared features in EEG data for both emotion and mood disorder recognition.
- This limitation impedes a comprehensive understanding of the complex interplay between emotions and mood disorders.
Purpose of the Study:
- To develop a novel EEG-based deep learning framework for the joint recognition of emotions and mood disorders.
- To explore the shared neural representations underlying emotional states and mood disorders.
- To provide a foundation for investigating the intricate relationship between emotions and mood disorders.
Main Methods:
- Development of a multi-gate mixture-of-experts graph convolutional network (MMoGCN) model.
- Utilized Differential Entropy (DE) for robust EEG signal feature extraction.
- Incorporated a Multi-Gated Shared Experts Module (MGSE) and Adaptive Task-Specific Towers (ATST) with Adaptive Weighting Loss (AWL) for multi-task learning.
Main Results:
- MMoGCN demonstrated superior performance in joint emotion and mood disorder recognition compared to state-of-the-art baselines.
- Validation on the public DEAP dataset confirmed the model's scalability and generalization capabilities.
- The study successfully identified cognitive differences in emotional responses between healthy individuals and those with mood disorders.
Conclusions:
- The proposed MMoGCN offers an effective multi-task learning approach for joint EEG-based emotion and clinical state recognition.
- The findings provide methodological insights into analyzing complex mental states using EEG.
- Offers potential guidance for cognitive rehabilitation strategies targeting both cognitive and emotional aspects.
More Related Videos
Related Concept Videos
01:30Classification of Neurotransmitters
5.3K
Neurotransmitters play a crucial role in the communication between neurons in the autonomic nervous system. Neurons in the autonomic nervous system can be cholinergic or adrenergic depending on the neurotransmitters synthesized. Cholinergic neurons use acetylcholine as their primary neurotransmitter. This includes all the preganglionic fibers of the sympathetic and pre- and postganglionic fibers of the parasympathetic nervous systems. In addition, neurons of the somatic nervous system also use...
5.3K
01:25Neural Circuits
3.0K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
3.0K