Motor imagery brain-computer interface (MI-BCI) has many promising applications but there are problems such as poor classification accuracy and robustness which need to be addressed. We propose a novel approach called time-frequency common spatial patterns (TFCSP) to enhance the robustness and accuracy of the electroencephalogram (EEG) signal classification. The proposed approach decomposes the EEG signal into time stages and frequency components to find the most robust and discriminative features. Common spatial patterns (CSP) are extracted from every decomposed time-frequency cell and unreliable features are removed while remaining features are weighted and regularized for the classification. Comparison on three publicly available datasets from BCI competition III and IV shows that the proposed TFCSP outperforms state-of-the-art methods. This demonstrates that adopting subject reaction time paradigm is useful to enhance the classification performance. It also shows that the complex CSP in the frequency domain significantly effective than the commonly used bandpass-filters in time domain. Finally, this work proves that weighting and regularizing CSP features are better techniques than selecting the leading CSP features because the former alleviates information loss.

运动图像脑机接口（MI-BCI）有许多有希望的应用，但存在诸如分类精度和鲁棒性较差等问题需要解决。我们提出一种称为时频公共空间模式（TFCSP）的新颖方法，以增强脑电图（EEG）信号分类的鲁棒性和准确性。所提出的方法将脑电信号分解为时间段和频率分量，以找到最鲁棒和最有区别的特征。从每个分解的时频单元中提取公共空间模式（CSP），并删除不可靠的特征，同时对其余特征进行加权和正则化以进行分类。对BCI竞赛III和IV的三个公开可用数据集的比较表明，所提出的TFCSP优于最新方法。这表明采用主题反应时间范式有助于提高分类性能。它还表明，在频域中，复杂的CSP在时域方面比常用的带通滤波器有效。最后，这项工作证明，加权和正则化CSP功能是比选择领先的CSP功能更好的技术，因为前者可以减轻信息丢失。