Pan Lincong, Wang Kun, Huang Yongzhi, Sun Xinwei, Meng Jiayuan, Yi Weibo, Xu Minpeng, Jung Tzyy-Ping, Ming Dong
Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, PR China; School of Precision Instruments and Optoelectronics Engineering, Tianjin University, Tianjin 300072, PR China.
Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin 300072, PR China; Haihe Laboratory of Brain-computer Interaction and Human-machine Integration, Tianjin 300392, PR China; Tianjin Key Laboratory of Brain Science and Neuroengineering, Tianjin 300072, PR China.
Neural Netw. 2025 Apr 22;188:107511. doi: 10.1016/j.neunet.2025.107511.
Motor imagery (MI) refers to the mental simulation of movements without physical execution, and it can be captured using electroencephalography (EEG). This area has garnered significant research interest due to its substantial potential in brain-computer interface (BCI) applications, especially for individuals with physical disabilities. However, accurate classification of MI EEG signals remains a major challenge due to their non-stationary nature, low signal-to-noise ratio, and sensitivity to both external and physiological noise. Traditional classification methods, such as common spatial pattern (CSP), often assume that the data is stationary and Gaussian, which limits their applicability in real-world scenarios where these assumptions do not hold. These challenges highlight the need for more robust methods to improve classification accuracy in MI-BCI systems. To address these issues, this study introduces a Riemannian geometry-based spatial filtering (RSF) method that projects EEG signals into a lower-dimensional subspace, maximizing the Riemannian distance between covariance matrices from different classes. By leveraging the inherent geometric properties of EEG data, RSF enhances the discriminative power of the features while maintaining robustness against noise. The performance of RSF was evaluated in combination with ten commonly used MI decoding algorithms, including CSP with linear discriminant analysis (CSP-LDA), Filter Bank CSP (FBCSP), Minimum Distance to Riemannian Mean (MDM), Tangent Space Mapping (TSM), EEGNet, ShallowConvNet (sCNN), DeepConvNet (dCNN), FBCNet, Graph-CSPNet, and LMDA-Net, using six publicly available MI-BCI datasets. The results demonstrate that RSF significantly improves classification accuracy and reduces computational time, particularly for deep learning models with high computational complexity. These findings underscore the potential of RSF as an effective spatial filtering approach for MI EEG classification, providing new insights and opportunities for the development of robust MI-BCI systems. The code for this research is available at https://github.com/PLC-TJU/RSF.
运动想象（MI）是指在不进行身体执行的情况下对运动进行心理模拟，并且可以使用脑电图（EEG）来捕捉。由于其在脑机接口（BCI）应用中的巨大潜力，特别是对于身体有残疾的个体，该领域已经引起了重大的研究兴趣。然而，由于MI脑电信号具有非平稳性、低信噪比以及对外部和生理噪声的敏感性，准确分类这些信号仍然是一个重大挑战。传统的分类方法，如共同空间模式（CSP），通常假设数据是平稳的且呈高斯分布，这限制了它们在这些假设不成立的实际场景中的适用性。这些挑战凸显了需要更强大的方法来提高MI-BCI系统中的分类准确性。为了解决这些问题，本研究引入了一种基于黎曼几何的空间滤波（RSF）方法，该方法将脑电信号投影到一个低维子空间中，最大化不同类别协方差矩阵之间的黎曼距离。通过利用脑电数据固有的几何特性，RSF增强了特征的判别能力，同时保持了对噪声的鲁棒性。结合十种常用的MI解码算法，包括带线性判别分析的CSP（CSP-LDA）、滤波器组CSP（FBCSP）、到黎曼均值的最小距离（MDM）、切空间映射（TSM）、EEGNet、浅卷积网络（sCNN）、深度卷积网络（dCNN）、FBCNet、图-CSPNet和LMDA-Net，使用六个公开可用的MI-BCI数据集对RSF的性能进行了评估。结果表明，RSF显著提高了分类准确性并减少了计算时间，特别是对于具有高计算复杂度的深度学习模型。这些发现强调了RSF作为一种有效的MI脑电分类空间滤波方法的潜力，为开发强大的MI-BCI系统提供了新的见解和机会。本研究的代码可在https://github.com/PLC-TJU/RSF获取。
