当前位置: X-MOL 学术IEEE Trans. Affect. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
EEG-Based Emotion Recognition Using Regularized Graph Neural Networks
IEEE Transactions on Affective Computing ( IF 9.6 ) Pub Date : 2020-05-11 , DOI: 10.1109/taffc.2020.2994159
Peixiang Zhong 1 , Di Wang 1 , Chunyan Miao 1
Affiliation  

Electroencephalography (EEG) measures the neuronal activities in different brain regions via electrodes. Many existing studies on EEG-based emotion recognition do not fully exploit the topology of EEG channels. In this article, we propose a regularized graph neural network (RGNN) for EEG-based emotion recognition. RGNN considers the biological topology among different brain regions to capture both local and global relations among different EEG channels. Specifically, we model the inter-channel relations in EEG signals via an adjacency matrix in a graph neural network where the connection and sparseness of the adjacency matrix are inspired by neuroscience theories of human brain organization. In addition, we propose two regularizers, namely node-wise domain adversarial training (NodeDAT) and emotion-aware distribution learning (EmotionDL), to better handle cross-subject EEG variations and noisy labels, respectively. Extensive experiments on two public datasets, SEED, and SEED-IV, demonstrate the superior performance of our model than state-of-the-art models in most experimental settings. Moreover, ablation studies show that the proposed adjacency matrix and two regularizers contribute consistent and significant gain to the performance of our RGNN model. Finally, investigations on the neuronal activities reveal important brain regions and inter-channel relations for EEG-based emotion recognition.

中文翻译:

使用正则化图神经网络的基于 EEG 的情绪识别

脑电图 (EEG) 通过电极测量不同大脑区域的神经元活动。许多现有的基于 EEG 的情绪识别研究并未充分利用 EEG 通道的拓扑结构。在本文中,我们提出了一种用于基于 EEG 的情绪识别的正则化图神经网络 (RGNN)。RGNN 考虑不同大脑区域之间的生物拓扑,以捕获不同 EEG 通道之间的局部和全局关系。具体来说,我们通过图神经网络中的邻接矩阵对 EEG 信号中的通道间关系进行建模,其中邻接矩阵的连接和稀疏性受到人类大脑组织的神经科学理论的启发。此外,我们提出了两个正则化器,即节点域对抗训练(NodeDAT)和情绪感知分布学习(EmotionDL),分别更好地处理跨主题的脑电图变化和嘈杂的标签。在两个公共数据集 SEED 和 SEED-IV 上进行的大量实验证明了我们的模型在大多数实验环境中的性能优于最先进的模型。此外,消融研究表明,所提出的邻接矩阵和两个正则化器为我们的 RGNN 模型的性能贡献了一致且显着的增益。最后,对神经元活动的研究揭示了基于 EEG 的情绪识别的重要大脑区域和通道间关系。消融研究表明,所提出的邻接矩阵和两个正则化器为我们的 RGNN 模型的性能贡献了一致且显着的增益。最后,对神经元活动的研究揭示了基于 EEG 的情绪识别的重要大脑区域和通道间关系。消融研究表明,所提出的邻接矩阵和两个正则化器为我们的 RGNN 模型的性能贡献了一致且显着的增益。最后,对神经元活动的研究揭示了基于 EEG 的情绪识别的重要大脑区域和通道间关系。
更新日期:2020-05-11
down
wechat
bug