Objective: Electroencephalogram (EEG) signals-based motor kinematics prediction (MKP) has been an active area of research to develop brain-computer interface (BCI) systems such as exosuits, prostheses, and rehabilitation devices. However, EEG source imaging (ESI) based kinematics prediction is sparsely explored in the literature. Approach: In this study, pre-movement EEG features are utilized to predict three-dimensional (3D) hand kinematics for the grasp-and-lift motor task. A public dataset, WAY-EEG-GAL, is utilized for MKP analysis. In particular, sensor-domain (EEG data) and source-domain (ESI data) based features from the frontoparietal region are explored for MKP. Deep learning-based models are explored to achieve efficient kinematics decoding. Various time-lagged and window sizes are analyzed for hand kinematics prediction. Subsequently, intra-subject and inter-subject MKP analysis is performed to investigate the subject-specific and subject-independent motor-learning capabilities of the neural decoders. The Pearson correlation coefficient (PCC) is used as the performance metric for kinematics trajectory decoding. Main results: The rEEGNet neural decoder achieved the best performance with sensor-domain and source-domain features with the time lag and window size of 100 ms and 450 ms, respectively. The highest mean PCC values of 0.790, 0.795, and 0.637 are achieved using sensor-domain features, while 0.769, 0.777, and 0.647 are achieved using source-domain features in x, y, and z-directions, respectively. Significance: This study explores the feasibility of trajectory prediction using EEG sensor-domain and source-domain EEG features for the grasp-and-lift task. Furthermore, inter-subject trajectory estimation is performed using the proposed deep learning decoder with EEG source domain features.

翻译：目的：基于脑电图（EEG）信号的运动学预测（MKP）一直是开发脑机接口（BCI）系统（如外骨骼、假肢和康复设备）的活跃研究领域。然而，基于脑电源成像（ESI）的运动学预测在文献中鲜有探索。方法：本研究利用运动前EEG特征来预测抓握与抬举运动任务中的三维（3D）手部运动学。我们使用公开数据集WAY-EEG-GAL进行MKP分析。具体而言，我们探索了来自额顶叶区域的传感器域（EEG数据）和源域（ESI数据）特征用于MKP。研究采用基于深度学习的模型以实现高效的运动学解码。我们分析了不同时间滞后和窗口大小对手部运动学预测的影响。随后，通过被试内和被试间MKP分析，探究神经解码器的被试特定与被试无关的运动学习能力。皮尔逊相关系数（PCC）被用作运动轨迹解码的性能指标。主要结果：rEEGNet神经解码器在传感器域和源域特征上均取得最佳性能，其最优时间滞后和窗口大小分别为100 ms和450 ms。使用传感器域特征在x、y、z方向获得的最高平均PCC值分别为0.790、0.795和0.637；而使用源域特征获得的对应值分别为0.769、0.777和0.647。意义：本研究探讨了利用EEG传感器域和源域特征进行抓握与抬举任务轨迹预测的可行性。此外，我们使用所提出的深度学习解码器结合EEG源域特征实现了被试间轨迹估计。