Extracting features from phase space of EEG signals in brain-computer interfaces
Extracting features from phase space of EEG signals in brain-computer interfaces
复制标题
DOI：
10.1016/j.neucom.2014.10.038
复制
发表时间：
2015-03-03
期刊：
影响因子：
6
通讯作者：
Zheng, Xufei
中科院分区：
文献类型：
--
作者：
Fang, Yonghui;Chen, Minyou;Zheng, Xufei
在脑机接口(BCI)研究中，传统的基于自回归和幅频分析的特征提取方法假定脑电信号在短时间间隔内是平稳的。提出了一种基于相空间的运动想象任务识别特征提取方法。对单个非线性序列进行重构，就是通过相空间重构，在保持原始信息连续性的前提下，揭示隐藏在原始序列中的各种信息。使用三相空间特征(PSF)数据集对两个Graz BC！数据集。仿真表明，基于PSF的线性判别分析(LDA)分类器在互信息(MI)或错误分类率的竞争标准方面优于2003年BCI竞赛的所有获胜者以及同一GRAZ数据集上的其他类似研究。使用组合PSF对Graz2003数据集进行分类，最大MI为0.67，最小误识率为9.29%。根据最大MI陡度的竞争准则，基于PSF的LDA分类器的性能优于2005年BCI竞赛的获胜者和其他类似研究的获胜者，该研究基于相同的Graz数据集针对主题03。03的最大MI陡度为0.7355。(C)2014爱思唯尔B.V.保留所有权利。
Conventional feature extraction methods based on autoregressive and amplitude-frequency analysis assume stationarity in the Electroencephalogram signal along short time intervals in Brain-Computer Interface (BCI) studies. This paper proposes a feature extraction method based on phase space for motor imagery tasks recognition. To remodel the single nonlinear sequence is to reveal variety information hidden in the original series by its phase space reconstruction, and maintaining the original information continuity. Three phase space features (PSF) datasets are used to classify two Graz BC! datasets. The simulation has shown that the linear discriminant analysis (LDA) classifiers based on the PSF outperform all the winners of the BCI Competition 2003 and other similar studies on the same Graz dataset in terms of the competition criterion of the mutual information (MI) or misclassification rate. The maximal MI was 0.67 and the minimal misclassification rate was 9.29% for Graz2003 dataset by using the combined PSF. According to the competition criterion of the maximal MI steepness, the LDA classifier based on PSF yielded a better performance than the winner of the BCI Competition 2005 and other similar research on the same Graz dataset for subject 03. The maximal MI steepness of 03 is 0.7355. (C) 2014 Elsevier B.V. All rights reserved.