SIA OpenIR  > 机器人学研究室
基于时空特征学习卷积神经网络的运动想象脑电解码方法
Alternative TitleConvolutional neural network based on temporal-spatial feature learning for motor imagery eeg signal decoding
褚亚奇1,2,3; 朱波1,2,3; 赵新刚1,2; 赵忆文1,2
Department机器人学研究室
Source Publication生物医学工程学杂志
ISSN1001-5515
2021
Volume38Issue:1Pages:1-9
Contribution Rank1
Funding Organization国家自然科学基金(61573340,61773369,U1813214) ; 中国科学院前沿科学重点研究项目(QYZDY-SSWJSC005) ; 辽宁省“兴辽英才计划”项目(XLYC1908030)
Keyword运动想象脑电 脑机接口 时空特征 卷积神经网络 信号解码
Abstract

基于运动想象脑电(EEG)的脑-机接口系统能够为用户提供更为自然、灵活的控制方式,已广泛应用到人机交互领域。然而,由于目前运动想象脑电的信噪比及空间分辨率较低,导致信号解码正确率较低。针对这一问题,本文提出一种基于时空特征学习卷积神经网络(TSCNN)的运动想象脑电解码方法。首先,针对经过带通滤波预处理的脑电信号,依次设计时间和空间维度上的卷积层,构造出运动想象脑电的时空特征;然后,利用2层二维卷积结构对脑电的时空特征进行抽象学习;最后,通过全连接层和Softmax层对TSCNN学习的抽象特征进行解码。利用公开数据集对该方法进行实验测试,结果表明,所提方法的平均解码精度达到80.09%,分别比经典的解码方法共空间模式(CSP)+支持向量机(SVM)和滤波器组CSP(FBCSP)+SVM提高了13.75%和10.99%,显著提升了运动想象脑电解码的可靠性。

Other Abstract

With the advantage of providing more natural and flexible control manner, brain-computer interface systems based on motor imagery electroencephalogram (EEG) have been widely used in the field of human-machine interaction. However, due to the lower signal-noise ratio and poor spatial resolution of EEG signals, the decoding accuracy is relative low. To solve this problem, a novel convolutional neural network based on temporal-spatial feature learning (TSCNN) was proposed for motor imagery EEG decoding. Firstly, for the EEG signals preprocessed by band-pass filtering, a temporal-wise convolution layer and a spatial-wise convolution layer were respectively designed, and temporal-spatial features of motor imagery EEG were constructed. Then, 2-layer two-dimensional convolutional structures were adopted to learn abstract features from the raw temporal-spatial features. Finally, the softmax layer combined with the fully connected layer were used to perform decoding task from the extracted abstract features. The experimental results of the proposed method on the open dataset showed that the average decoding accuracy was 80.09%, which is approximately 13.75% and 10.99% higher than that of the state-of-the-art common spatial pattern (CSP) + support vector machine (SVM) and filter bank CSP (FBCSP) + SVM recognition methods, respectively. This demonstrates that the proposed method can significantly improve the reliability of motor imagery EEG decoding.

Language中文
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/28121
Collection机器人学研究室
Corresponding Author赵新刚
Affiliation1.中国科学院沈阳自动化研究所机器人学国家重点实验室
2.中国科学院机器人与智能制造创新研究院
3.中国科学院大学
Recommended Citation
GB/T 7714
褚亚奇,朱波,赵新刚,等. 基于时空特征学习卷积神经网络的运动想象脑电解码方法[J]. 生物医学工程学杂志,2021,38(1):1-9.
APA 褚亚奇,朱波,赵新刚,&赵忆文.(2021).基于时空特征学习卷积神经网络的运动想象脑电解码方法.生物医学工程学杂志,38(1),1-9.
MLA 褚亚奇,et al."基于时空特征学习卷积神经网络的运动想象脑电解码方法".生物医学工程学杂志 38.1(2021):1-9.
Files in This Item:
File Name/Size DocType Version Access License
基于时空特征学习卷积神经网络的运动想象脑(1469KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[褚亚奇]'s Articles
[朱波]'s Articles
[赵新刚]'s Articles
Baidu academic
Similar articles in Baidu academic
[褚亚奇]'s Articles
[朱波]'s Articles
[赵新刚]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[褚亚奇]'s Articles
[朱波]'s Articles
[赵新刚]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于时空特征学习卷积神经网络的运动想象脑电解码方法.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.