Variable Down-Selection for Brain-Computer Interfaces

Variable Down-Selection for Brain-Computer Interfaces
复制标题

脑机接口的可变向下选择

DOI:
10.1007/978-3-642-11721-3_12
复制
发表时间:
2009
期刊:
Journal of Clinical Engineering
影响因子:
--
通讯作者:
Jose H. Correia
Jose H. Correia
中科院分区:
--
文献类型:
--
作者:
Nuno Dias;M. Kamrunnahar;Paulo M. Mendes;Steven J. Schiff;Jose H. Correia

文献摘要

参考文献

相似文献

提出了一种新的主成分分析(PCA),考虑组结构的数据作为变量向下选择方法。电极通道优化是脑-机接口(BCI)中的一个关键问题。由于EEG会话中的时间限制,BCI实验生成与样本大小相比较大的特征空间。为了设计高性能而又现实的BCI,必须了解物理电极通道方面的特征的重要性。所提出的算法产生的原始变量(电极通道或功能)的排名列表,根据他们的能力来区分运动图像任务。将线性判别分析(LDA)分类器应用于所选择的变量子集。使用合成数据集的向下选择方法的评估选择了超过83%的相关变量。使用真实的BCI数据集对图像任务进行分类,分类误差小于19%。与其他常用的分类算法相比,跨组方差(AGV)具有最好的分类性能和最大的降维。
A new formulation of principal component analysis (PCA) that considers group structure in the data is proposed as a variable down-selection method. Optimization of electrode channels is a key problem in brain-computer interfaces (BCI). BCI experiments generate large feature spaces compared to the sample size due to time limitations in EEG sessions. It is essential to understand the importance of the features in terms of physical electrode channels in order to design a high performance yet realistic BCI. The proposed algorithm produces a ranked list of original variables (electrode channels or features), according to their ability to discriminate movement imagery tasks. A linear discrimination analysis (LDA) classifier is applied to the selected variable subset. Evaluation of the down-selection method using synthetic datasets selected more than 83% of relevant variables. Classification of imagery tasks using real BCI datasets resulted in less than 19% classification error. Across-Group Variance (AGV) showed the best classification performance with the largest dimensionality reduction in comparison with other algorithms in common use.
DOI: 10.1109/86.847808
发表时间: 2000-06-01
期刊: IEEE TRANSACTIONS ON REHABILITATION ENGINEERING
影响因子: --
作者:
Donchin, E;Spencer, KM;Wijesinghe, R
通讯作者: Wijesinghe, R
DOI: 10.1073/pnas.0403504101
发表时间: 2004-12-21
影响因子: 11.1
作者:
Wolpaw, JR;McFarland, DJ
通讯作者: McFarland, DJ
DOI: 10.1109/86.847823
发表时间: 2000-06-01
期刊: IEEE TRANSACTIONS ON REHABILITATION ENGINEERING
影响因子: --
作者:
Wolpaw, JR;McFarland, DJ;Vaughan, TM
通讯作者: Vaughan, TM