School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an, People's Republic of China.
Shaanxi Key Laboratory of Intelligent Robots, Xi'an, People's Republic of China.
J Neural Eng. 2022 Jul 26;19(4). doi: 10.1088/1741-2552/ac7d73.
Multi-channel electroencephalogram data containing redundant information and noise may result in low classification accuracy and high computational complexity, which limits the practicality of motor imagery (MI)-based brain-computer interface (BCI) systems. Therefore, channel selection can improve BCI performance and contribute to user convenience. Additionally, cross-subject generalization is a key topic in the channel selection of MI-based BCI.In this study, an adaptive binary multi-objective harmony search (ABMOHS) algorithm is proposed to select the optimal set of channels. Furthermore, a new adaptive cross-subject generalization model (ACGM) is proposed. Three public MI datasets were used to validate the effectiveness of the proposed method.The Wilcoxon signed-rank test was performed on the test accuracies, and the results indicated that the ABMOHS method significantly outperformed all channels (< 0.001), the C3-Cz-C4 channels (< 0.001), and 20 channels (< 0.001) in the sensorimotor cortex. The ABMOHS algorithm based on Fisher's linear discriminant analysis (FLDA) and support vector machine (SVM) classifiers greatly reduces the number of selected channels, especially for larger channel sizes (Dataset 2), and obtains a comparative classification performance. Although there was no significant difference in test classification performance between ABMOHS and non-dominated sorting genetic algorithm II (NSGA-II) when FLDA and SVM were used, ABMOHS required less computational time than NSGA-II. Furthermore, the number of channels obtained by ABMOHS algorithm were significantly smaller than those obtained by common spatial pattern-Rank and correlation-based channel selection algorithm. Additionally, the generalization of ACGM to untrained subjects shows that the mean test classification accuracy of ACGM created by a small sample of trained subjects is significantly better than that of Special-16 and Special-32.The proposed method can reduce the calibration time in the training phase and improve the practicability of MI-BCI.
多通道脑电数据中可能包含冗余信息和噪声，这会导致分类精度低、计算复杂度高，从而限制了基于运动想象（MI）的脑机接口（BCI）系统的实用性。因此，通道选择可以提高 BCI 的性能，并有助于用户的便利性。此外，跨被试泛化是 MI 基 BCI 通道选择中的一个关键问题。
在这项研究中，提出了一种自适应二进制多目标和声搜索（ABMOHS）算法来选择最佳的通道集。此外，还提出了一种新的自适应跨被试泛化模型（ACGM）。使用三个公共的 MI 数据集来验证所提出方法的有效性。
对测试准确率进行了 Wilcoxon 符号秩检验，结果表明，ABMOHS 方法明显优于所有通道（<0.001）、C3-Cz-C4 通道（<0.001）和感觉运动皮层的 20 个通道（<0.001）。基于 Fisher 线性判别分析（FLDA）和支持向量机（SVM）分类器的 ABMOHS 算法大大减少了所选通道的数量，特别是对于较大的通道尺寸（数据集 2），并获得了可比的分类性能。虽然当使用 FLDA 和 SVM 时，ABMOHS 与非支配排序遗传算法 II（NSGA-II）在测试分类性能上没有显著差异，但 ABMOHS 所需的计算时间比 NSGA-II 少。此外，ABMOHS 算法获得的通道数量明显小于常用的空间模式-Rank 和基于相关的通道选择算法获得的通道数量。此外，ACGM 对未训练被试的泛化表明，由少数训练被试创建的 ACGM 的平均测试分类准确率明显优于 Special-16 和 Special-32。
该方法可以减少训练阶段的校准时间，提高 MI-BCI 的实用性。
