论文标题
卷积神经网络具有基于脑电图的脑部计算机界面的地形表示模块
Convolutional Neural Networks with A Topographic Representation Module for EEG-Based Brain-Computer Interfaces
论文作者
论文摘要
目的：卷积神经网络（CNN）在脑部计算机界面（BCIS）领域显示出巨大的潜力。原始脑电图（EEG）信号通常表示为由通道和时间点组成的二维（2-D）矩阵，忽略了空间拓扑信息。我们的目标是使CNN具有原始脑电图信号，因为输入具有学习脑电图空间拓扑特征的能力，并提高了其性能，同时实质上保持其原始结构。方法：我们提出了一个EEG地形表示模块（TRM）。该模块由（1）从RAW EEG信号到3-D地形图的映射块和（2）从地形图到与输入相同大小的输出的卷积块。根据卷积块中使用的内核的大小，我们设计了两种类型的TRM，即TRM-（5,5）和TRM-（3,3）。我们将TRM嵌入了3个广泛使用的CNN中，并将其测试到2个公开可用的数据集中（在模拟驾驶数据集（EBDSDD）（EBDSDD）和High Gamma DataSet（HGD））中进行了测试。结果：结果表明，使用TRM后，两个数据集的所有3个CNN的分类精度均得到改善。使用TRM-（5,5），DeepConvnet，EEGNet和ShandowConvnet的平均准确性在EBDSDD上提高了6.54％，1.72％和2.07％，HGD分别提高了6.05％，3.02％和5.14％。对于TRM-（3,3），HGD分别提高了EBDSDD的7.76％，1.71％和2.17％，HGD分别提高了7.61％，5.06％和6.28％。意义：我们通过使用TRM在2个数据集上提高了3个CNN的分类性能，这表明它具有挖掘EEG空间拓扑信息的能力。此外，由于TRM的输出的大小与输入相同，因此具有原始脑电图信号的CNN作为输入可以使用此模块而无需更改其原始结构。
Objective: Convolutional Neural Networks (CNNs) have shown great potential in the field of Brain-Computer Interfaces (BCIs). The raw Electroencephalogram (EEG) signal is usually represented as 2-Dimensional (2-D) matrix composed of channels and time points, which ignores the spatial topological information. Our goal is to make the CNN with the raw EEG signal as input have the ability to learn EEG spatial topological features, and improve its performance while essentially maintaining its original structure. Methods:We propose an EEG Topographic Representation Module (TRM). This module consists of (1) a mapping block from the raw EEG signal to a 3-D topographic map and (2) a convolution block from the topographic map to an output of the same size as input. According to the size of the kernel used in the convolution block, we design 2 types of TRMs, namely TRM-(5,5) and TRM-(3,3). We embed the TRM into 3 widely used CNNs, and tested them on 2 publicly available datasets (Emergency Braking During Simulated Driving Dataset (EBDSDD), and High Gamma Dataset (HGD)). Results: The results show that the classification accuracies of all 3 CNNs are improved on both datasets after using the TRM. With TRM-(5,5), the average accuracies of DeepConvNet, EEGNet and ShallowConvNet are improved by 6.54%, 1.72% and 2.07% on EBDSDD, and by 6.05%, 3.02% and 5.14% on HGD, respectively; with TRM-(3,3), they are improved by 7.76%, 1.71% and 2.17% on EBDSDD, and by 7.61%, 5.06% and 6.28% on HGD, respectively. Significance: We improve the classification performance of 3 CNNs on 2 datasets by the use of TRM, indicating that it has the capability to mine the EEG spatial topological information. In addition, since the output of TRM has the same size as the input, CNNs with the raw EEG signal as input can use this module without changing their original structures.
