Fan Chengcheng, Yang Banghua, Li Xiaoou, Zan Peng
School of Mechatronic Engineering and Automation, School of Medicine, Research Center of Brain Computer Engineering, Shanghai University, Shanghai, China.
School of Medical Instrument, Shanghai University of Medicine & Health Science, Shanghai, China.
Front Neurosci. 2023 Aug 28;17:1250991. doi: 10.3389/fnins.2023.1250991. eCollection 2023.
Recently, convolutional neural networks (CNNs) have been widely applied in brain-computer interface (BCI) based on electroencephalogram (EEG) signals. Due to the subject-specific nature of EEG signal patterns and the multi-dimensionality of EEG features, it is necessary to employ appropriate feature representation methods to enhance the decoding accuracy of EEG. In this study, we proposed a method for representing EEG temporal, frequency, and phase features, aiming to preserve the multi-domain information of EEG signals. Specifically, we generated EEG temporal segments using a sliding window strategy. Then, temporal, frequency, and phase features were extracted from different temporal segments and stacked into 3D feature maps, namely temporal-frequency-phase features (TFPF). Furthermore, we designed a compact 3D-CNN model to extract these multi-domain features efficiently. Considering the inter-individual variability in EEG data, we conducted individual testing for each subject. The proposed model achieved an average accuracy of 89.86, 78.85, and 63.55% for 2-class, 3-class, and 4-class motor imagery (MI) classification tasks, respectively, on the PhysioNet dataset. On the GigaDB dataset, the average accuracy for 2-class MI classification was 91.91%. For the comparison between MI and real movement (ME) tasks, the average accuracy for the 2-class were 87.66 and 80.13% on the PhysioNet and GigaDB datasets, respectively. Overall, the method presented in this paper have obtained good results in MI/ME tasks and have a good application prospect in the development of BCI systems based on MI/ME.
最近，卷积神经网络（CNN）已被广泛应用于基于脑电图（EEG）信号的脑机接口（BCI）。由于EEG信号模式的个体特异性和EEG特征的多维度性，有必要采用适当的特征表示方法来提高EEG的解码精度。在本研究中，我们提出了一种表示EEG时间、频率和相位特征的方法，旨在保留EEG信号的多域信息。具体而言，我们使用滑动窗口策略生成EEG时间片段。然后，从不同的时间片段中提取时间、频率和相位特征，并堆叠成3D特征图，即时间-频率-相位特征（TFPF）。此外，我们设计了一个紧凑的3D-CNN模型来有效地提取这些多域特征。考虑到EEG数据的个体间变异性，我们对每个受试者进行了个体测试。在PhysioNet数据集上，所提出的模型在2类、3类和4类运动想象（MI）分类任务中的平均准确率分别达到了89.86%、78.85%和63.55%。在GigaDB数据集上，2类MI分类的平均准确率为91.91%。对于MI与真实运动（ME）任务的比较，在PhysioNet和GigaDB数据集上，2类任务的平均准确率分别为87.66%和80.13%。总体而言，本文提出的方法在MI/ME任务中取得了良好的结果，在基于MI/ME的BCI系统开发中具有良好的应用前景。
