1 October 2021 in Computer Methods and Programs in Biomedicine
29 September 2023 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
In recent years, Graph Neural Networks (GNNs) based on deep learning techniques have achieved promising results in EEG-based depression detection tasks but still have some limitations. Firstly, most existing GNN-based methods use pre-computed graph adjacency matrices, which ignore the differences in brain networks between individuals. Additionally, methods based on graph-structured data do not consider the temporal dependency information of brain networks. To address these issues, we propose a deep learning algorithm that explores adaptive graph topologies and temporal graph networks for EEG-based depression detection. Specifically, we designed an Adaptive Graph Topology Generation (AGTG) module that can adaptively model the real-time connectivity of the brain networks, revealing differences between individuals. In addition, we designed a Graph Convolutional Gated Recurrent Unit (GCGRU) module to capture the temporal dynamical changes of brain networks. To further explore the differential features between depressed and healthy individuals, we adopt Graph Topology-based Max-Pooling (GTMP) module to extract graph representation vectors accurately. We conduct a comparative analysis with several advanced algorithms on both public and our own datasets. The results reveal that our final model achieves the highest Area Under the Receiver Operating Characteristic Curve (AUROC) on both datasets, with values of 83% and 99%, respectively. Furthermore, we perform extensive validation experiments demonstrating our proposed method’s effectiveness and advantages. Finally, we present a comprehensive discussion on the differences in brain networks between healthy and depressed individuals based on the outputs of our final model’s AGTG and GTMP modules.
10 October 2022 in IEEE Transactions on Neural Networks and Learning Systems
Electroencephalogram (EEG) plays an important role in studying brain function and human cognitive performance, and the recognition of EEG signals is vital to develop an automatic sleep staging system. However, due to the complex nonstationary characteristics and the individual difference between subjects, how to obtain the effective signal features of the EEG for practical application is still a challenging task. In this article, we investigate the EEG feature learning problem and propose a novel temporal feature learning method based on amplitude–time dual-view fusion for automatic sleep staging. First, we explore the feature extraction ability of convolutional neural networks for the EEG signal from the perspective of interpretability and construct two new representation signals for the raw EEG from the views of amplitude and time. Then, we extract the amplitude–time signal features that reflect the transformation between different sleep stages from the obtained representation signals by using conventional 1-D CNNs. Furthermore, a hybrid dilation convolution module is used to learn the long-term temporal dependency features of EEG signals, which can overcome the shortcoming that the small-scale convolution kernel can only learn the local signal variation information. Finally, we conduct attention-based feature fusion for the learned dual-view signal features to further improve sleep staging performance. To evaluate the performance of the proposed method, we test 30-s-epoch EEG signal samples for healthy subjects and subjects with mild sleep disorders. The experimental results from the most commonly used datasets show that the proposed method has better sleep staging performance and has the potential for the development and application of an EEG-based automatic sleep staging system.
13 March 2026 in IEEE Journal of Biomedical and Health Informatics
EEG-based emotion recognition is a crucial task with significant implications for mental health monitoring, affective computing, and clinical decision support. While Graph Neural Networks (GNNs) have shown promise in modeling the complex spatio-temporal dynamics of EEG signals, existing methods fall short by only considering pairwise spatial dependencies and neglecting critical higher-order associations among functionally related brain regions. Moreover, these approaches often fail to achieve frequency-specific temporal learning, leading to suboptimal results. To overcome these limitations, we propose the Sub-band Embedded Spatio-Temporal Network (SESTN), a novel framework that jointly models multi-frequency spatial and temporal dependencies. In SESTN, EEG features are first projected into sub-band embedding spaces, enabling finer-grained frequency-specific representation. Our approach then uses neurophysiological priors to construct weighted hyperedges, capturing intra-regional spatial relationships more effectively. A multi-head, Mamba-based temporal module is subsequently utilized to extract frequency-specific temporal dynamics. Finally, a graph convolutional fusion strategy integrates these features across different frequency bands. Extensive experiments on two widely used EEG emotion recognition datasets, SEED and SEED-IV, demonstrate that SESTN significantly improves classification performance in both subject-dependent and subject-independent scenarios. These results underscore SESTN's potential as a robust and effective framework for real-world biomedical applications, particularly in affective state monitoring and mental health assessment.