Simple adaptive sparse representation based classification schemes for EEG based brain-computer interface applications
Simple adaptive sparse representation based classification schemes for EEG based brain-computer interface applications
复制标题
DOI：
10.1016/j.compbiomed.2015.08.017
复制
发表时间：
2015-11-01
影响因子：
7.7
通讯作者：
Lee, Heung-No
中科院分区：
文献类型：
--
作者：
Shin, Younghak;Lee, Seungchan;Lee, Heung-No
基于脑电（EEG）的脑机接口（BCI）系统的主要问题之一是潜在的EEG信号的非平稳性。这导致在实验会话期间的分类性能的恶化。因此，自适应分类技术是基于脑电的脑机接口应用所必需的。在本文中，我们提出了简单的自适应稀疏表示为基础的分类（SRC）计划。研究了新测试数据的有监督和无监督字典更新技术，以及利用训练数据的不一致性度量进行字典修改的方法。所提出的方法非常简单，不需要额外的计算来重新训练分类器。建议的自适应SRC计划使用两个BCI实验数据集进行评估。通过与传统SRC和其他自适应分类方法的分类结果进行比较，对所提出的方法进行了评估。结果的基础上，我们发现，所提出的自适应计划相比，传统的方法，不需要额外的计算显示出相对提高的分类精度。(C)2015爱思唯尔有限公司版权所有。
One of the main problems related to electroencephalogram (EEG) based brain-computer interface (BCI) systems is the non-stationarity of the underlying EEG signals. This results in the deterioration of the classification performance during experimental sessions. Therefore, adaptive classification techniques are required for EEG based BCI applications. In this paper, we propose simple adaptive sparse representation based classification (SRC) schemes. Supervised and unsupervised dictionary update techniques for new test data and a dictionary modification method by using the incoherence measure of the training data are investigated. The proposed methods are very simple and additional computation for the re-training of the classifier is not needed. The proposed adaptive SRC schemes are evaluated using two BCI experimental datasets. The proposed methods are assessed by comparing classification results with the conventional SRC and other adaptive classification methods. On the basis of the results, we find that the proposed adaptive schemes show relatively improved classification accuracy as compared to conventional methods without requiring additional computation. (C) 2015 Elsevier Ltd. All rights reserved.