Characteristics of Kinematic Parameters in Decoding Intended Reaching Movements Using Electroencephalography (EEG)
Characteristics of Kinematic Parameters in Decoding Intended Reaching Movements Using Electroencephalography (EEG)
复制标题
DOI：
10.3389/fnins.2019.01148
复制
发表时间：
2019-11-01
影响因子：
4.3
通讯作者：
Koike, Yasuharu
中科院分区：
文献类型：
--
作者：
Kim, Hyeonseok;Yoshimura, Natsue;Koike, Yasuharu
运动前脑电图（EEG）在动作意图解码中的应用已经得到证实。然而，在运动准备过程中，大脑所代表的关于预期目标的信息类型仍然未知。在本研究中，我们研究了在运动前脑电图解码中哪些运动参数（即方向、距离和到达的位置）可以被解码。8名被试完成30种触碰动作，包括24种动作方向中的1种、7种动作距离、5种水平目标位置和5种垂直目标位置。使用独立分量提取与事件相关的谱扰动，通过方差分析选择其中一些分量，使用支持向量机进行进一步的二值分类分析。当每个参数用于类标记时，执行所有可能的二值分类。方向和距离的分类精度显著高于机会水平，而位置的分类精度无显著差异。对于将每个动作视为不同类别的分类，分析了由代表每个动作的两个向量组成的参数。在这种情况下，当距离差大、距离和大、角度差大、目标位置差大时，分类精度高。研究结果进一步表明，方向和距离可能对运动的影响最大。此外，无论参数如何，很容易在顶叶和枕叶区域找到有用的分类特征。
The utility of premovement electroencephalography (EEG) for decoding movement intention during a reaching task has been demonstrated. However, the kind of information the brain represents regarding the intended target during movement preparation remains unknown. In the present study, we investigated which movement parameters (i.e., direction, distance, and positions for reaching) can be decoded in premovement EEG decoding. Eight participants performed 30 types of reaching movements that consisted of 1 of 24 movement directions, 7 movement distances, 5 horizontal target positions, and 5 vertical target positions. Event-related spectral perturbations were extracted using independent components, some of which were selected via an analysis of variance for further binary classification analysis using a support vector machine. When each parameter was used for class labeling, all possible binary classifications were performed. Classification accuracies for direction and distance were significantly higher than chance level, although no significant differences were observed for position. For the classification in which each movement was considered as a different class, the parameters comprising two vectors representing each movement were analyzed. In this case, classification accuracies were high when differences in distance were high, the sum of distances was high, angular differences were large, and differences in the target positions were high. The findings further revealed that direction and distance may provide the largest contributions to movement. In addition, regardless of the parameter, useful features for classification are easily found over the parietal and occipital areas.