EEG emotion recognition using improved graph neural network with channel selection
EEG emotion recognition using improved graph neural network with channel selection
复制标题
DOI：
10.1016/j.cmpb.2023.107380
复制
发表时间：
2023-02-04
影响因子：
6.1
通讯作者：
Wang, Yuchen
中科院分区：
文献类型：
--
作者：
Lin, Xuefen;Chen, Jielin;Wang, Yuchen
背景和目的：基于脑电图的情绪分类任务是人工智能的重要组成部分，在自闭症研究和孕妇情绪检测等医疗保健领域具有广阔的应用前景。然而，复杂的数据采集环境提供了可变数量的EEG通道，这干扰了模型模拟人脑中的信息传递过程。为此，本文提出了一种改进的具有动态通道选择的图卷积模型。方法：该模型结合了一维卷积和图卷积的优点，分别提取通道内和通道间的脑电信号特征。我们在图结构中添加了功能连接，这有助于进一步模拟大脑区域之间的关系。此外，一个可调节的规模的通道选择可以执行的基础上的注意力分布图structure.Results：我们进行了各种实验上的DEAP-Twente，DEAP-Geneva，和SEED数据集，并取得了90.74%，91%，和90.22%，分别超过了大多数现有的mod-els的平均准确率。同时，在只保留20%的EEG通道的情况下，模型在上述三个数据集上的平均分类准确率分别为82.78%、84%和83.93%。结论：实验结果表明，该模型能够在复杂数据集环境下实现有效的情感分类。此外，所提出的通道选择方法是信息，以减少情感计算的成本。(c)2023爱思唯尔有限公司版权所有。
Background and objective: Emotion classification tasks based on electroencephalography (EEG) are an essential part of artificial intelligence, with promising applications in healthcare areas such as autism re-search and emotion detection in pregnant women. However, the complex data acquisition environment provides a variable number of EEG channels, which interferes with the model to simulate the process of information transfer in the human brain. Therefore, this paper proposes an improved graph convolution model with dynamic channel selection.Methods: The proposed model combines the advantages of 1D convolution and graph convolution to cap-ture the intra-and inter-channel EEG features, respectively. We add functional connectivity in the graph structure that helps to simulate the relationship between brain regions further. In addition, an adjustable scale of channel selection can be performed based on the attention distribution in the graph structure.Results: We conducted various experiments on the DEAP-Twente, DEAP-Geneva, and SEED datasets and achieved average accuracies of 90.74%, 91%, and 90.22%, respectively, which exceeded most existing mod-els. Meanwhile, with only 20% of the EEG channels retained, the models achieved average accuracies of 82.78%, 84%, and 83.93% on the above three datasets, respectively.Conclusions: The experimental results show that the proposed model can achieve effective emotion clas-sification in complex dataset environments. Also, the proposed channel selection method is informative for reducing the cost of affective computing. (c) 2023 Elsevier B.V. All rights reserved.