IEEE Trans Neural Syst Rehabil Eng. 2022;30:2283-2291. doi: 10.1109/TNSRE.2022.3198041. Epub 2022 Aug 19.
Motor imagery (MI) based brain-computer interface (BCI) is an important BCI paradigm which requires powerful classifiers. Recent development of deep learning technology has prompted considerable interest in using deep learning for classification and resulted in multiple models. Finding the best performing models among them would be beneficial for designing better BCI systems and classifiers going forward. However, it is difficult to directly compare performance of various models through the original publications, since the datasets used to test the models are different from each other, too small, or even not publicly available. In this work, we selected five MI-EEG deep classification models proposed recently: EEGNet, Shallow & Deep ConvNet, MB3D and ParaAtt, and tested them on two large, publicly available, databases with 42 and 62 human subjects. Our results show that the models performed similarly on one dataset while EEGNet performed the best on the second with a relatively small training cost using the parameters that we evaluated.
基于运动想象（MI）的脑机接口（BCI）是一种重要的 BCI 范式，需要强大的分类器。深度学习技术的最新发展促使人们对使用深度学习进行分类产生了浓厚的兴趣，并产生了多种模型。在这些模型中找到性能最佳的模型将有助于设计更好的 BCI 系统和分类器。然而，由于用于测试模型的数据集彼此不同，太小甚至不可公开获得，因此很难通过原始出版物直接比较各种模型的性能。在这项工作中，我们选择了最近提出的五个基于 MI-EEG 的深度学习分类模型：EEGNet、Shallow & Deep ConvNet、MB3D 和 ParaAtt，并在两个具有 42 和 62 名人类受试者的大型公共数据库上对它们进行了测试。我们的结果表明，这些模型在一个数据集上的表现相似，而 EEGNet 在第二个数据集上的表现最好，使用我们评估的参数，训练成本相对较低。
