Objective. Motor-imagery (MI) classification base on electroencephalography (EEG) has been long studied in neuroscience and more recently widely used in healthcare applications such as mobile assistive robots and neurorehabilitation. In particular, EEG-based MI classification methods that rely on convolutional neural networks (CNNs) have achieved relatively high classification accuracy. However, naively training CNNs to classify raw EEG data from all channels, especially for high-density EEG, is computationally demanding and requires huge training sets. It often also introduces many irrelevant input features, making it difficult for the CNN to extract the informative ones. This problem is compounded by a dearth of training data, which is particularly acute for MI tasks, because these are cognitively demanding and thus fatigue inducing. Approach. To address these issues, we proposed an end-to-end CNN-based neural network with attentional mechanism together with different data augmentation (DA) techniques. We tested it on two benchmark MI datasets, brain–computer interface (BCI) competition IV 2a and 2b. In addition, we collected a new dataset, recorded using high-density EEG, and containing both MI and motor execution (ME) tasks, which we share with the community. Main results. Our proposed neural-network architecture outperformed all state-of-the-art methods that we found in the literature, with and without DA, reaching an average classification accuracy of 93.6% and 87.83% on BCI 2a and 2b, respectively. We also directly compare decoding of MI and ME tasks. Focusing on MI classification, we find optimal channel configurations and the best DA techniques as well as investigate combining data across participants and the role of transfer learning. Significance. Our proposed approach improves the classification accuracy for MI in the benchmark datasets. In addition, collecting our own dataset enables us to compare MI and ME and investigate various aspects of EEG decoding critical for neuroscience and BCI.

客观的。基于脑电图 (EEG) 的运动图像 (MI) 分类长期以来一直在神经科学领域进行研究，最近广泛用于医疗保健应用，例如移动辅助机器人和神经康复。特别是依赖于卷积神经网络 (CNN) 的基于 EEG 的 MI 分类方法已经取得了相对较高的分类准确率。然而，天真地训练 CNN 对来自所有通道的原始 EEG 数据进行分类，特别是对于高密度 EEG，计算要求很高，并且需要大量的训练集。它还经常引入许多不相关的输入特征，使 CNN 难以提取信息丰富的特征。这个问题因缺乏训练数据而变得更加复杂，这对于 MI 任务尤其严重，因为这些对认知要求很高，因此会导致疲劳。方法。为了解决这些问题，我们提出了一种基于 CNN 的端到端神经网络，具有注意力机制和不同的数据增强 (DA) 技术。我们在两个基准 MI 数据集、脑机接口 (BCI) 竞赛 IV 2a 和 2b 上对其进行了测试。此外，我们收集了一个新数据集，使用高密度 EEG 记录，并包含我们与社区共享的 MI 和运动执行 (ME) 任务。主要结果。我们提出的神经网络架构优于我们在文献中发现的所有最先进的方法，无论有没有 DA，在 BCI 2a 和 2b 上的平均分类准确率分别达到 93.6% 和 87.83%。我们还直接比较了 MI 和 ME 任务的解码。专注于 MI 分类，我们找到了最佳通道配置和最佳 DA 技术，并研究了跨参与者的数据组合和迁移学习的作用。意义。我们提出的方法提高了基准数据集中 MI 的分类精度。此外，收集我们自己的数据集使我们能够比较 MI 和 ME，并研究对神经科学和 BCI 至关重要的 EEG 解码的各个方面。