Plucknett William, Sanchez Giraldo Luis G, Bae Jihye
Department of Electrical and Computer Engineering, University of Kentucky, Lexington, KY, United States.
Front Hum Neurosci. 2022 Jul 1;16:902183. doi: 10.3389/fnhum.2022.902183. eCollection 2022.
Decoding movement related intentions is a key step to implement BMIs. Decoding EEG has been challenging due to its low spatial resolution and signal to noise ratio. Metric learning allows finding a representation of data in a way that captures a desired notion of similarity between data points. In this study, we investigate how metric learning can help finding a representation of the data to efficiently classify EEG movement and pre-movement intentions. We evaluate the effectiveness of the obtained representation by comparing classification the performance of a Support Vector Machine (SVM) as a classifier when trained on the original representation, called Euclidean, and representations obtained with three different metric learning algorithms, including Conditional Entropy Metric Learning (CEML), Neighborhood Component Analysis (NCA), and the Entropy Gap Metric Learning (EGML) algorithms. We examine different types of features, such as time and frequency components, which input to the metric learning algorithm, and both linear and non-linear SVM are applied to compare the classification accuracies on a publicly available EEG data set for two subjects (Subject B and C). Although metric learning algorithms do not increase the classification accuracies, their interpretability using an measure we define here, helps understanding data organization and how much each EEG channel contributes to the classification. In addition, among the metric learning algorithms we investigated, EGML shows the most robust performance due to its ability to compensate for differences in scale and correlations among variables. Furthermore, from the observed variations of the maps on the scalp and the classification accuracy, selecting an appropriate feature such as clipping the frequency range has a significant effect on the outcome of metric learning and subsequent classification. In our case, reducing the range of the frequency components to 0-5 Hz shows the best interpretability in both Subject B and C and classification accuracy for Subject C. Our experiments support potential benefits of using metric learning algorithms by providing visual explanation of the data projections that explain the inter class separations, using . This visualizes the contribution of features that can be related to brain function.
解码与运动相关的意图是实现脑机接口（BMI）的关键一步。由于脑电图（EEG）的空间分辨率低和信噪比低，对其进行解码一直具有挑战性。度量学习允许以一种捕获数据点之间所需相似性概念的方式找到数据的表示。在本研究中，我们研究度量学习如何有助于找到数据的表示，以有效地对EEG运动和运动前意图进行分类。我们通过比较支持向量机（SVM）作为分类器在基于原始表示（称为欧几里得表示）训练时的分类性能，以及使用三种不同度量学习算法（包括条件熵度量学习（CEML）、邻域成分分析（NCA）和熵差距度量学习（EGML）算法）获得的表示的分类性能，来评估所获得表示的有效性。我们检查了不同类型的特征，如时间和频率成分，这些特征输入到度量学习算法中，并且应用线性和非线性SVM来比较两个受试者（受试者B和C）在公开可用的EEG数据集上的分类准确率。尽管度量学习算法没有提高分类准确率，但它们使用我们在此定义的一种度量的可解释性有助于理解数据组织以及每个EEG通道对分类的贡献程度。此外，在我们研究的度量学习算法中，EGML由于能够补偿变量之间的尺度差异和相关性，表现出最稳健的性能。此外，从头皮上观察到的度量映射变化和分类准确率来看，选择合适的特征（如裁剪频率范围）对度量学习和后续分类的结果有显著影响。在我们的案例中，将频率成分的范围缩小到0 - 5Hz在受试者B和C中都显示出最佳的可解释性，并且对受试者C的分类准确率最高。我们的实验通过使用一种度量对解释类间分离的数据投影进行可视化解释，支持了使用度量学习算法的潜在好处。这可视化了与脑功能相关的特征的贡献。
