EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces
EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces
复制标题
DOI：
10.1088/1741-2552/aace8c
复制
发表时间：
2018-10-01
影响因子：
4
通讯作者：
Lance, Brent J.
中科院分区：
文献类型：
--
作者：
Lawhern, Vernon J.;Solon, Amelia J.;Lance, Brent J.
目标。脑机接口（BCI）利用神经活动作为控制信号，实现与计算机的直接通信。这种神经信号通常是从各种经过充分研究的脑电图（EEG）信号中选择的。对于给定的脑机接口范例，特征提取器和分类器是针对其预期脑电图控制信号的不同特征进行定制的，从而限制了其对特定信号的应用。卷积神经网络（cnn）在计算机视觉和语音识别中用于自动特征提取和分类，并成功应用于基于脑电图的脑机接口；然而，它们主要应用于单一的BCI范例，因此尚不清楚这些架构如何推广到其他范例。在这里，我们的问题是我们是否可以设计一个单一的CNN架构来准确地分类来自不同脑机接口范式的脑电信号，同时尽可能地紧凑。的方法。在这项工作中，我们介绍了EEGNet，一个紧凑的卷积神经网络，用于基于脑电图的脑机接口。我们介绍了深度卷积和可分离卷积的使用来构建一个脑电特定模型，该模型封装了脑机接口中众所周知的脑电特征提取概念。我们将EEGNet与目前最先进的四种脑机接口范式（P300视觉诱发电位、错误相关的负性反应（ERN）、运动相关的皮质电位（MRCP）和感觉运动节律（SMR））进行了比较，包括受试者内分类和跨受试者分类。主要的结果。我们表明，当所有被测试的范式中只有有限的训练数据可用时，EEGNet比参考算法更好地泛化了范例，并取得了相当高的性能。此外，我们展示了三种不同的方法来可视化训练过的EEGNet模型的内容，从而能够解释学习到的特征。的意义。我们的研究结果表明，EEGNet具有足够的鲁棒性，可以在一系列脑机接口任务中学习各种各样的可解释特征。我们的模型可以在https://github.com/vlawhern/arl-eegmodels上找到。
Objective. Brain-computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI paradigm, feature extractors and classifiers are tailored to the distinct characteristics of its expected EEG control signal, limiting its application to that specific signal. Convolutional neural networks (CNNs), which have been used in computer vision and speech recognition to perform automatic feature extraction and classification, have successfully been applied to EEG-based BCIs; however, they have mainly been applied to single BCI paradigms and thus it remains unclear how these architectures generalize to other paradigms. Here, we ask if we can design a single CNN architecture to accurately classify EEG signals from different BCI paradigms, while simultaneously being as compact as possible. Approach. In this work we introduce EEGNet, a compact convolutional neural network for EEG-based BCIs. We introduce the use of depthwise and separable convolutions to construct an EEG-specific model which encapsulates well-known EEG feature extraction concepts for BCI. We compare EEGNet, both for within-subject and cross-subject classification, to current state-of-the-art approaches across four BCI paradigms: P300 visual-evoked potentials, error-related negativity responses (ERN), movement-related cortical potentials (MRCP), and sensory motor rhythms (SMR). Main results. We show that EEGNet generalizes across paradigms better than, and achieves comparably high performance to, the reference algorithms when only limited training data is available across all tested paradigms. In addition, we demonstrate three different approaches to visualize the contents of a trained EEGNet model to enable interpretation of the learned features. Significance. Our results suggest that EEGNet is robust enough to learn a wide variety of interpretable features over a range of BCI tasks. Our models can be found at: https://github.com/vlawhern/arl-eegmodels.