School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, People's Republic of China.
These authors contributed equally.
J Neural Eng. 2021 Apr 6;18(4):046026. doi: 10.1088/1741-2552/abecc5.
Motor imagery (MI) classification is an important task in the brain-computer interface (BCI) field. MI data exhibit highly dynamic characteristics and are difficult to obtain. Therefore, the performance of the classification model will be challenged. Recently, convolutional neural networks (CNNs) have been employed for MI classification and have demonstrated favorable performances. However, the traditional CNN model uses an end-to-end output method, and part of the feature information is discarded during the transmission process.
Herein, we propose a novel algorithm, that is, a combined long short-term memory generative adversarial networks (LGANs) and multi-output convolutional neural network (MoCNN) for MI classification, and an attention network for improving model performance. Specifically, the proposed method comprises three steps. First, MI data are obtained, and preprocessing is performed. Second, additional data are generated for training. Here, a data augmentation method based on a LGAN is designed. Last, the MoCNN is proposed to improve the classification performance.
The BCI competition IV datasets 2a and 2b are employed to evaluate the performance of the proposed method. With multiple evaluation indicators, the proposed generative model can generate more realistic data. The expanded training set improves the performance of the classification model.
The results show that the proposed method improves the classification of MI data, which facilitates motion imagination.
运动想象（MI）分类是脑机接口（BCI）领域的一项重要任务。MI 数据具有高度动态的特点，并且难以获取。因此，分类模型的性能将受到挑战。最近，卷积神经网络（CNNs）已被用于 MI 分类，并表现出良好的性能。然而，传统的 CNN 模型使用端到端的输出方法，在传输过程中会丢弃部分特征信息。
本文提出了一种新的算法，即结合长短时记忆生成对抗网络（LGANs）和多输出卷积神经网络（MoCNN）进行 MI 分类，并采用注意力网络来提高模型性能。具体来说，该方法包括三个步骤。首先，获取 MI 数据并进行预处理。其次，生成更多的训练数据。这里设计了一种基于 LGAN 的数据增强方法。最后，提出了 MoCNN 以提高分类性能。
使用 BCI 竞赛 IV 数据集 2a 和 2b 评估所提出方法的性能。通过多个评估指标，所提出的生成模型可以生成更真实的数据。扩展的训练集提高了分类模型的性能。
结果表明，所提出的方法提高了 MI 数据的分类能力，有助于运动想象。
