期刊
JOURNAL OF NEURAL ENGINEERING
卷 18, 期 1, 页码 -出版社
IOP Publishing Ltd
DOI: 10.1088/1741-2552/abca16
关键词
brain computer interfaces (BCI); motor imagery (MI); channel selection; convolutional neural network (CNN)
资金
- National Natural Science Foundation of China [61971303, 81971660, 61675039]
- CAMS Innovation Fund for Medical Sciences [2016-I2M-3-023]
- Beijing Major Science & Technology project [Z191100010618004]
- Tianjin Special Branch Plan High Level Innovation Team Grant
- Tianjin Key Projects of Natural Science foundation [18JCZDJC32700]
- NVIDIA Corporation
This study introduces a deep learning-based approach to automatically recognize different MI states by selecting relevant EEG channels. By utilizing a sparse squeeze-and-excitation module and a convolutional neural network, the proposed method outperforms traditional classification methods in terms of accuracy and robustness.
Objective. Modern motor imagery (MI)-based brain computer interface systems often entail a large number of electroencephalogram (EEG) recording channels. However, irrelevant or highly correlated channels would diminish the discriminatory ability, thus reducing the control capability of external devices. How to optimally select channels and extract associated features remains a big challenge. This study aims to propose and validate a deep learning-based approach to automatically recognize two different MI states by selecting the relevant EEG channels. Approach. In this work, we make use of a sparse squeeze-and-excitation module to extract the weights of EEG channels based on their contribution to MI classification, by which an automatic channel selection (ACS) strategy is developed. Further, we propose a convolutional neural network to fully exploit the time-frequency features, thus outperforming traditional classification methods both in terms of accuracy and robustness. Main results. We execute the experiments using EEG signals recorded at MI where 25 healthy subjects performed MI movements of the right hand and feet to generate motor commands. An average accuracy of 87.2 +/- 5.0% (mean +/- std)
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