Decoding of Walking Imagery and Idle State Using Sparse Representation Based on fNIRS.
Decoding of Walking Imagery and Idle State Using Sparse Representation Based on fNIRS.
复制标题
基于 fNIRS 的稀疏表示对步行图像和空闲状态的解码
DOI：
10.1155/2021/6614112
复制
发表时间：
2021
影响因子：
--
通讯作者：
Fu Y
中科院分区：
文献类型：
--
作者：
Li H;Gong A;Zhao L;Zhang W;Wang F;Fu Y
目的基于功能近红外光谱（fNIRS）的脑-机接口（BCI）有望为严重影响患者生活质量的步行障碍患者提供一种可选择的主动康复训练方法。利用稀疏表示分类（SRC）氧合血红蛋白（HbO）浓度对步行图像和空闲状态进行解码，构建基于步行图像的fNIRS-BCI。方法收集15名受试者在步行和空闲状态下的fNIRS信号。首先对HbO信号进行带通滤波和基线漂移校正，然后提取HbO的均值、峰值和均方根（RMS）及其组合作为分类特征;将SRC方法与支持向量机（SVM）、K近邻（KNN）、线性判别分析（LDA）、Logistic回归（LR）结果实验结果表明，SRC三特征组合对步行意象和空闲状态的平均分类准确率为91.55± 3.30%，显著高于SVM、KNN、LDA和LR（86.37± 4.42%，85.65± 5.01%，86.43± 4.41%，76.14± 5.32%），其他联合特征的分类准确率高于单一特征。结论在fNIRS-BCI中引入SRC，可以有效识别步行想象和空闲状态。不同的特征提取时间窗对分类结果也有影响，2-8 s的时间窗取得了较好的分类准确率（94.33±2.60%）。意义该研究有望为步行功能障碍患者提供一种新的、可选择的主动康复训练方法。此外，本实验也是一项罕见的基于fNIRS-BCI的研究，使用SRC解码步行图像和空闲状态。
Objectives Brain-computer interface (BCI) based on functional near-infrared spectroscopy (fNIRS) is expected to provide an optional active rehabilitation training method for patients with walking dysfunction, which will affect their quality of life seriously. Sparse representation classification (SRC) oxyhemoglobin (HbO) concentration was used to decode walking imagery and idle state to construct fNIRS-BCI based on walking imagery. Methods 15 subjects were recruited and fNIRS signals were collected during walking imagery and idle state. Firstly, band-pass filtering and baseline drift correction for HbO signal were carried out, and then the mean value, peak value, and root mean square (RMS) of HbO and their combinations were extracted as classification features; SRC was used to identify the extracted features and the result of SRC was compared with those of support vector machine (SVM), K-Nearest Neighbor (KNN), linear discriminant analysis (LDA), and logistic regression (LR). Results The experimental results showed that the average classification accuracy for walking imagery and idle state by SRC using three features combination was 91.55±3.30%, which was significantly higher than those of SVM, KNN, LDA, and LR (86.37±4.42%, 85.65±5.01%, 86.43±4.41%, and 76.14±5.32%, respectively), and the classification accuracy of other combined features was higher than that of single feature. Conclusions The study showed that introducing SRC into fNIRS-BCI can effectively identify walking imagery and idle state. It also showed that different time windows for feature extraction have an impact on the classification results, and the time window of 2–8 s achieved a better classification accuracy (94.33±2.60%) than other time windows. Significance. The study was expected to provide a new and optional active rehabilitation training method for patients with walking dysfunction. In addition, the experiment was also a rare study based on fNIRS-BCI using SRC to decode walking imagery and idle state.
登录
查看更多内容
影响因子：
3.8
作者：
Bhutta MR;Hong MJ;Kim YH;Hong KS
通讯作者：
Hong KS
影响因子：
4.3
作者：
Abdalmalak, Androu;Milej, Daniel;St Lawrence, Keith
通讯作者：
St Lawrence, Keith
影响因子：
2.5
作者：
Hong, Keum-Shik;Naseer, Noman;Kim, Yun-Hee
通讯作者：
Kim, Yun-Hee
影响因子：
--
作者：
Khan, Rayyan Azam;Naseer, Noman;Khan, Muhammad Jawad
通讯作者：
Khan, Muhammad Jawad
影响因子：
2.7
作者：
Nishiyori, Ryota;Bisconti, Silvia;Ulrich, Beverly
通讯作者：
Ulrich, Beverly