Internal Feature Selection Method of CSP Based on L1-Norm and Dempster-Shafer Theory
Internal Feature Selection Method of CSP Based on L1-Norm and Dempster-Shafer Theory
复制标题
DOI：
10.1109/tnnls.2020.3015505
复制
发表时间：
2021-11-01
影响因子：
10.4
通讯作者：
Cichocki, Andrzej
中科院分区：
文献类型：
--
作者：
Jin, Jing;Xiao, Ruocheng;Cichocki, Andrzej
公共空间模式（CSP）算法是一种公认的空间滤波方法，用于基于运动想象（MI）的脑机接口（BCI）特征提取。然而，由于脑电（EEG）的非平稳性和CSP目标函数的固有缺陷的影响，空间滤波器，以及它们相应的功能，不一定是最佳的特征空间内使用CSP。在这项工作中，我们设计了一个新的特征选择方法来解决这个问题，选择功能的基础上改进的目标函数。特别是在抑制离群值和发现类间距离较大的特征方面做出了改进。在此基础上，提出了一种基于Dempster-Shafer理论的融合算法，该算法考虑了特征的分布性。两个竞争数据集，我们首先评估的分类精度，特征分布和嵌入方面的改进的目标函数的性能。然后，与其他特征选择方法进行了比较，在精度和计算时间。实验结果表明，所提出的方法消耗较少的额外的计算成本，并导致在基于MI的BCI系统的性能显着提高。
The common spatial pattern (CSP) algorithm is a well-recognized spatial filtering method for feature extraction in motor imagery (MI)-based brain-computer interfaces (BCIs). However, due to the influence of nonstationary in electroencephalography (EEG) and inherent defects of the CSP objective function, the spatial filters, and their corresponding features are not necessarily optimal in the feature space used within CSP. In this work, we design a new feature selection method to address this issue by selecting features based on an improved objective function. Especially, improvements are made in suppressing outliers and discovering features with larger interclass distances. Moreover, a fusion algorithm based on the Dempster-Shafer theory is proposed, which takes into consideration the distribution of features. With two competition data sets, we first evaluate the performance of the improved objective functions in terms of classification accuracy, feature distribution, and embeddability. Then, a comparison with other feature selection methods is carried out in both accuracy and computational time. Experimental results show that the proposed methods consume less additional computational cost and result in a significant increase in the performance of MI-based BCI systems.