Department of Biomedical Engineering, Tarbiat Modares University, Tehran, Iran.
Department of Medical Physics, Tarbiat Modares University, Tehran, Iran.
Neural Netw. 2021 Jan;133:193-206. doi: 10.1016/j.neunet.2020.11.002. Epub 2020 Nov 10.
Motor imagery (MI) brain-computer interface (BCI) and neurofeedback (NF) with electroencephalogram (EEG) signals are commonly used for motor function improvement in healthy subjects and to restore neurological functions in stroke patients. Generally, in order to decrease noisy and redundant information in unrelated EEG channels, channel selection methods are used which provide feasible BCI and NF implementations with better performances. Our assumption is that there are causal interactions between the channels of EEG signal in MI tasks that are repeated in different trials of a BCI and NF experiment. Therefore, a novel method for EEG channel selection is proposed which is based on Granger causality (GC) analysis. Additionally, the machine-learning approach is used to cluster independent component analysis (ICA) components of the EEG signal into artifact and normal EEG clusters. After channel selection, using the common spatial pattern (CSP) and regularized CSP (RCSP), features are extracted and with the k-nearest neighbor (k-NN), support vector machine (SVM) and linear discriminant analysis (LDA) classifiers, MI tasks are classified into left and right hand MI. The goal of this study is to achieve a method resulting in lower EEG channels with higher classification performance in MI-based BCI and NF by causal constraint. The proposed method based on GC, with only eight selected channels, results in 93.03% accuracy, 92.93% sensitivity, and 93.12% specificity, with RCSP feature extractor and best classifier for each subject, after being applied on Physionet MI dataset, which is increased by 3.95%, 3.73%, and 4.13%, in comparison with correlation-based channel selection method.
基于脑电图 (EEG) 信号的运动想象 (MI) 脑机接口 (BCI) 和神经反馈 (NF) 常用于改善健康受试者的运动功能，并恢复中风患者的神经功能。通常，为了减少无关 EEG 通道中的噪声和冗余信息，会使用通道选择方法，这些方法为 BCI 和 NF 实现提供了更好的性能。我们假设在 MI 任务中，EEG 信号的通道之间存在因果相互作用，这些相互作用在 BCI 和 NF 实验的不同试验中重复出现。因此，提出了一种基于格兰杰因果关系 (GC) 分析的 EEG 通道选择新方法。此外，还使用机器学习方法将 EEG 信号的独立成分分析 (ICA) 组件聚类为伪迹和正常 EEG 聚类。通道选择后，使用共空间模式 (CSP) 和正则化 CSP (RCSP) 提取特征，并使用 k-最近邻 (k-NN)、支持向量机 (SVM) 和线性判别分析 (LDA) 分类器对手动 MI 任务进行分类。本研究的目的是通过因果约束实现一种方法，该方法在基于 MI 的 BCI 和 NF 中使用较少的 EEG 通道，从而获得更高的分类性能。基于 GC 的方法，仅选择了 8 个通道，在应用于 Physionet MI 数据集后，使用 RCSP 特征提取器和每个受试者的最佳分类器，得到 93.03%的准确率、92.93%的灵敏度和 93.12%的特异性，与基于相关的通道选择方法相比，分别提高了 3.95%、3.73%和 4.13%。
