IEEE Trans Neural Syst Rehabil Eng. 2019 Jul;27(7):1378-1388. doi: 10.1109/TNSRE.2019.2922713. Epub 2019 Jun 13.
This paper presents a novel feature extraction approach for motor imagery classification overcoming the weakness of conventional common spatial pattern (CSP) methods, especially for small sample settings. We consider local CSPs generated from individual channels and their neighbors (termed "local regions") rather than a global CSP generated from all channels. The novelty is to select a few good local regions using interquartile range (IQR) or an "above the mean" rule based on variance ratio dispersion score (VRDS) and inter-class feature distance (ICFD); instead of computationally expensive cross-validation method. Furthermore, we develop frequency optimization using filter banks by extending the VRDS and ICFD to frequency-optimized local CSPs. The proposed methods are tested on three publicly available brain-computer interface (BCI) datasets: BCI competition III dataset IVa, BCI competition IV dataset I, and BCI competition IV dataset IIb. The proposed method exhibits substantially improved classification accuracy compared to recent related motor imagery (MI) classification methods.
本文提出了一种新的特征提取方法，用于克服传统公共空间模式 (CSP) 方法的弱点，特别是在小样本设置下。我们考虑从单个通道及其邻居（称为“局部区域”）生成的局部 CSP，而不是从所有通道生成的全局 CSP。新颖之处在于使用基于方差比分散得分 (VRDS) 和类间特征距离 (ICFD) 的四分位距 (IQR) 或“高于平均值”规则选择少数几个好的局部区域；而不是使用计算成本高昂的交叉验证方法。此外，我们通过将 VRDS 和 ICFD 扩展到频率优化的局部 CSP 来进行频率优化。所提出的方法在三个公开的脑机接口 (BCI) 数据集上进行了测试：BCI 竞赛 III 数据集 IVa、BCI 竞赛 IV 数据集 I 和 BCI 竞赛 IV 数据集 IIb。与最近的相关运动想象 (MI) 分类方法相比，所提出的方法表现出显著提高的分类准确性。
