LGGNet：面向脑机接口的局部-全局图表示学习
LGGNet: Learning from Local-Global-Graph Representations for Brain-Computer Interface
AI总结：
本文提出受神经科学启发的图神经网络 LGGNet，通过多尺度时间卷积与局部-全局图滤波建模 EEG 脑区内外关系，并在三类数据集的四项认知任务上取得显著优于基线的分类效果。
摘要：
神经心理学研究表明，不同脑功能区之间的协同活动驱动着高级认知过程。为了学习大脑不同功能区内部及彼此之间的脑活动，我们提出 LGGNet，这是一种新颖的受神经学启发的图神经网络，用于为脑机接口（BCI）学习脑电图（EEG）的局部-全局图表示。LGGNet 的输入层由一系列采用多尺度一维卷积核和核级注意力融合的时间卷积组成。它捕捉 EEG 的时间动态，随后将其作为所提出的局部和全局图滤波层的输入。利用一组定义好的、具有神经生理学意义的局部图和全局图，LGGNet 对脑功能区内部及功能区之间的复杂关系进行建模。在稳健的嵌套交叉验证设置下，所提方法在三个公开可用数据集上针对四类认知分类任务进行评估，即注意力、疲劳、情绪和偏好分类任务。LGGNet 与 DeepConvNet、EEGNet、R2G-STNN、TSception、RGNN、AMCNN-DGCN、HRNN 和 GraphNet 等最先进方法进行比较。结果表明，LGGNet 优于这些方法，并且在多数情况下性能提升具有统计学显著性（p<0.05）。结果表明，将神经科学先验知识引入神经网络设计能够提升分类性能。源代码可在 https://github.com/yi-ding-cs/LGG 获取。
英文摘要：
Neuropsychological studies suggest that co-operative activities among different brain functional areas drive high-level cognitive processes. To learn the brain activities within and among different functional areas of the brain, we propose LGGNet, a novel neurologically inspired graph neural network, to learn local-global-graph representations of electroencephalography (EEG) for Brain-Computer Interface (BCI). The input layer of LGGNet comprises a series of temporal convolutions with multi-scale 1D convolutional kernels and kernel-level attentive fusion. It captures temporal dynamics of EEG which then serves as input to the proposed local and global graph-filtering layers. Using a defined neurophysiologically meaningful set of local and global graphs, LGGNet models the complex relations within and among functional areas of the brain. Under the robust nested cross-validation settings, the proposed method is evaluated on three publicly available datasets for four types of cognitive classification tasks, namely, the attention, fatigue, emotion, and preference classification tasks. LGGNet is compared with state-of-the-art methods, such as DeepConvNet, EEGNet, R2G-STNN, TSception, RGNN, AMCNN-DGCN, HRNN and GraphNet. The results show that LGGNet outperforms these methods, and the improvements are statistically significant (p<0.05) in most cases. The results show that bringing neuroscience prior knowledge into neural network design yields an improvement of classification performance. The source code can be found at https://github.com/yi-ding-cs/LGG
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
