Phase synchronization phenomena are directly connected with the underlying neural mechanisms of certain cognitive processes. However, only the amplitude information is utilized in most electroencephalogram (EEG)-based brain-computer interfaces (BCIs). Few of the existing methods can simultaneously measure the amplitude and phase information required for classification. In this study, a novel common amplitude-phase measurement (CAPM) method is proposed. This method is capable of jointly measuring the phase and amplitude information of EEG signals on the Riemannian manifold. The proposed CAPM method comprises a two-step approach. First, a novel Riemannian graph embedding is proposed for dimensionality reduction while performing spatial-spectral filtering. The graph embedding is excellent in capturing the intrinsic features contained by the physiological signal. Second, to enhance robustness, a novel classifier is designed to incorporate the regularized linear regression in the computation of Riemannian distance. Experimental results on two BCI competition datasets demonstrate CAPM can yield high classification performance. The proposed CAPM method is a promising tool in analyzing EEG amplitude-phase characteristics and exhibits great potential in BCI applications.

中文翻译：

---

基于运动想象的 BCI 黎曼流形的幅相信息测量


相位同步现象与某些认知过程的潜在神经机制直接相关。然而，大多数基于脑电图 (EEG) 的脑机接口 (BCI) 只利用幅度信息。现有的方法很少能够同时测量分类所需的幅度和相位信息。在本研究中，提出了一种新颖的通用幅度相位测量（CAPM）方法。该方法能够联合测量黎曼流形上脑电信号的相位和幅度信息。所提出的 CAPM 方法包括两步方法。首先，提出了一种新颖的黎曼图嵌入，用于在执行空间谱滤波时降维。图嵌入在捕获生理信号所包含的内在特征方面非常出色。其次，为了增强鲁棒性，设计了一种新颖的分类器，将正则化线性回归纳入黎曼距离的计算中。两个 BCI 竞赛数据集的实验结果表明 CAPM 可以产生较高的分类性能。所提出的CAPM方法是分析EEG振幅-相位特征的有前途的工具，并且在BCI应用中展现出巨大的潜力。