Zhang Shuai, Chu Chengxi, Zhang Xin, Zhang Xiu
Tianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin 300387, China.
Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur 50603, Malaysia.
Brain Sci. 2025 Jun 7;15(6):615. doi: 10.3390/brainsci15060615.
BACKGROUND/OBJECTIVES: Electroencephalogram (EEG) signals, which reflect brain activity, are widely used in emotion recognition. However, the variety of EEG features presents significant challenges in identifying key features, reducing redundancy, and simplifying the computational process.
To address these challenges, this paper proposes a multi-dimensional attention-based dynamic graph convolutional neural network (AttGraph) model. The model delves into the impact of different EEG features on emotion recognition by evaluating their sensitivity to emotional changes, providing richer and more accurate feature information.
Through the dynamic weighting of EEG features via a multi-dimensional attention convolution layer, the AttGraph method is able to precisely detect emotional changes and automatically choose the most discriminative features for emotion recognition tasks. This approach significantly improves the model's recognition accuracy and robustness. Finally, subject-independent and subject-dependent experiments were conducted on two public datasets.
Through comparisons and analyses with existing methods, the proposed AttGraph method demonstrated outstanding performances in emotion recognition tasks, with stronger generalization ability and adaptability.
背景/目的：脑电图（EEG）信号反映大脑活动，在情绪识别中被广泛应用。然而，EEG特征的多样性在识别关键特征、减少冗余和简化计算过程方面带来了重大挑战。
为应对这些挑战，本文提出了一种基于多维注意力的动态图卷积神经网络（AttGraph）模型。该模型通过评估不同EEG特征对情绪变化的敏感性，深入研究其对情绪识别的影响，提供更丰富、准确的特征信息。
通过多维注意力卷积层对EEG特征进行动态加权，AttGraph方法能够精确检测情绪变化，并自动选择最具判别力的特征用于情绪识别任务。这种方法显著提高了模型的识别准确率和鲁棒性。最后，在两个公共数据集上进行了独立于受试者和依赖于受试者的实验。
通过与现有方法的比较和分析，所提出的AttGraph方法在情绪识别任务中表现出色，具有更强的泛化能力和适应性。
