EEG Emotion Recognition via Graph-based Spatio-Temporal Attention Neural Networks
EEG Emotion Recognition via Graph-based Spatio-Temporal Attention Neural Networks
复制标题
DOI：
10.1109/embc46164.2021.9629628
复制
发表时间：
2021-11
期刊：
影响因子：
--
通讯作者：
Shadi Sartipi;Mastaneh Torkamani-Azar;Müjdat Çetin
中科院分区：
文献类型：
--
作者：
Shadi Sartipi;Mastaneh Torkamani-Azar;Müjdat Çetin
基于脑电信号的情感识别是情感计算和脑机接口领域的研究热点。尽管已经提出了几种深度学习方法来处理情感识别任务，但开发有效提取和使用区分特征的方法仍然是一个挑战。在这项工作中，我们提出了一种新的时空注意神经网络（STANN）的多列卷积神经网络和基于注意力的双向长短期记忆的并行结构，以提取有区别的空间和时间特征的脑电信号。此外，我们探索通过图形信号处理（GSP）工具的EEG信号的通道间的关系。我们的实验分析表明，所提出的网络提高了国家的最先进的结果，在主题明智的，二进制分类的效价和唤醒水平，以及四类分类的效价唤醒情绪空间时，原始EEG信号或其图形表示，在一个架构被称为GFT-STANN，被用作模型输入。
Emotion recognition based on electroencephalography (EEG) signals has been receiving significant attention in the domains of affective computing and brain-computer interfaces (BCI). Although several deep learning methods have been proposed dealing with the emotion recognition task, developing methods that effectively extract and use discriminative features is still a challenge. In this work, we propose the novel spatio-temporal attention neural network (STANN) to extract discriminative spatial and temporal features of EEG signals by a parallel structure of multi-column convolutional neural network and attention-based bidirectional long-short term memory. Moreover, we explore the inter-channel relationships of EEG signals via graph signal processing (GSP) tools. Our experimental analysis demonstrates that the proposed network improves the state-of-the-art results in subject-wise, binary classification of valence and arousal levels as well as four-class classification in the valence-arousal emotion space when raw EEG signals or their graph representations, in an architecture coined as GFT-STANN, are used as model inputs.