期刊
SCIENTIFIC DATA
卷 9, 期 1, 页码 -出版社
NATURE PORTFOLIO
DOI: 10.1038/s41597-022-01647-1
关键词
-
资金
- National Natural Science Foundation of China [61976133]
- Shanghai Science and Technology Major Project [2021SHZDZX]
- Shanghai Industrial Collaborative Technology Innovation Project [2021-cyxt1-kj14]
- National Defense Basic Scientific Research Program of China (Defense Industrial Technology Development Program) [JCKY2021413B005]
Building a practical and robust brain-computer interface (BCI) faces the challenge of classifying motor imagery (MI) from electroencephalography (EEG) signals due to their large variability. This study collected a large dataset of MI from 25 subjects across 5 different days, presenting benchmarking classification accuracy for within-session classification, cross-session classification, and cross-session adaptation. The results show that cross-session adaptation improves the accuracy significantly, which is important for addressing challenges in BCI research.
In building a practical and robust brain-computer interface (BCI), the classification of motor imagery (MI) from electroencephalography (EEG) across multiple days is a long-standing challenge due to the large variability of the EEG signals. We collected a large dataset of MI from 5 different days with 25 subjects, the first open-access dataset to address BCI issues across 5 different days with a large number of subjects. The dataset includes 5 session data from 5 different days (2-3 days apart) for each subject. Each session contains 100 trials of left-hand and right-hand MI. In this report, we provide the benchmarking classification accuracy for three conditions, namely, within-session classification (WS), cross-session classification (CS), and cross-session adaptation (CSA), with subject-specific models. WS achieves an average classification accuracy of up to 68.8%, while CS degrades the accuracy to 53.7% due to the cross-session variability. However, by adaptation, CSA improves the accuracy to 78.9%. We anticipate this new dataset will significantly push further progress in MI BCI research in addressing the cross-session and cross-subject challenge.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据