Li Ketong, Chen Peng, Chen Qian, Li Xiangyun
School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, People's Republic of China.
West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu 610041, People's Republic of China.
J Neural Eng. 2025 Jan 6;21(6). doi: 10.1088/1741-2552/ada30b.
. Brain-computer interface(BCI) is leveraged by artificial intelligence in EEG signal decoding, which makes it possible to become a new means of human-machine interaction. However, the performance of current EEG decoding methods is still insufficient for clinical applications because of inadequate EEG information extraction and limited computational resources in hospitals. This paper introduces a hybrid network that employs a transformer with modified locally linear embedding and sliding window convolution for EEG decoding.. This network separately extracts channel and temporal features from EEG signals, subsequently fusing these features using a cross-attention mechanism. Simultaneously, manifold learning is employed to lower the computational burden of the model by mapping the high-dimensional EEG data to a low-dimensional space by its dimension reduction function.. The proposed model achieves accuracy rates of 84.44%, 94.96%, and 82.79% on the BCI Competition IV dataset 2a, high gamma dataset, and a self-constructed motor imagery (MI) dataset from the left and right hand fist-clenching tests respectively. The results indicate our model outperforms the baseline models by EEG-channel transformer with dimension-reduced EEG data and window attention with sliding window convolution. Additionally, to enhance the interpretability of the model, features preceding the temporal feature extraction network were visualized. This visualization promotes the understanding of how the model prefers task-related channels.. The transformer-based method makes the MI-EEG decoding more practical for further clinical applications.
脑机接口（BCI）在脑电图（EEG）信号解码中借助人工智能技术，这使其有可能成为人机交互的一种新方式。然而，由于EEG信息提取不足以及医院计算资源有限，当前EEG解码方法的性能在临床应用中仍显不足。本文介绍了一种混合网络，该网络采用带有改进局部线性嵌入的变压器和滑动窗口卷积进行EEG解码。该网络分别从EEG信号中提取通道特征和时间特征，随后使用交叉注意力机制融合这些特征。同时，采用流形学习通过其降维功能将高维EEG数据映射到低维空间来降低模型的计算负担。所提出的模型在BCI竞赛IV数据集2a、高伽马数据集以及来自左右手握拳测试的自建运动想象（MI）数据集上分别实现了84.44%、94.96%和82.79%的准确率。结果表明，我们的模型优于具有降维EEG数据的EEG通道变压器和带有滑动窗口卷积的窗口注意力等基线模型。此外，为了提高模型的可解释性，对时间特征提取网络之前的特征进行了可视化。这种可视化有助于理解模型如何偏好与任务相关的通道。基于变压器的方法使MI-EEG解码在进一步的临床应用中更具实用性。
