• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于强去相关变换的复数公共空间模式，利用脑电图的μ波和β波节律进行运动想象分类。

Motor Imagery Classification Using Mu and Beta Rhythms of EEG with Strong Uncorrelating Transform Based Complex Common Spatial Patterns.

作者信息

Kim Youngjoo, Ryu Jiwoo, Kim Ko Keun, Took Clive C, Mandic Danilo P, Park Cheolsoo

机构信息

Department of Computer Engineering, Kwangwoon University, 20 Gwangun Rd, Nowon-gu, Seoul 01897, Republic of Korea.

LG, 38 Baumoe-ro, Seocho-gu, Seoul 137724, Republic of Korea.

出版信息

Comput Intell Neurosci. 2016;2016:1489692. doi: 10.1155/2016/1489692. Epub 2016 Oct 3.

DOI:10.1155/2016/1489692
PMID:27795702
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC5066028/
Abstract

Recent studies have demonstrated the disassociation between the mu and beta rhythms of electroencephalogram (EEG) during motor imagery tasks. The proposed algorithm in this paper uses a fully data-driven multivariate empirical mode decomposition (MEMD) in order to obtain the mu and beta rhythms from the nonlinear EEG signals. Then, the strong uncorrelating transform complex common spatial patterns (SUTCCSP) algorithm is applied to the rhythms so that the complex data, constructed with the mu and beta rhythms, becomes uncorrelated and its pseudocovariance provides supplementary power difference information between the two rhythms. The extracted features using SUTCCSP that maximize the interclass variances are classified using various classification algorithms for the separation of the left- and right-hand motor imagery EEG acquired from the Physionet database. This paper shows that the supplementary information of the power difference between mu and beta rhythms obtained using SUTCCSP provides an important feature for the classification of the left- and right-hand motor imagery tasks. In addition, MEMD is proved to be a preferred preprocessing method for the nonlinear and nonstationary EEG signals compared to the conventional IIR filtering. Finally, the random forest classifier yielded a high performance for the classification of the motor imagery tasks.

摘要

最近的研究表明，在运动想象任务期间，脑电图（EEG）的μ波和β波之间存在解离。本文提出的算法使用完全数据驱动的多变量经验模式分解（MEMD），以便从非线性EEG信号中获得μ波和β波。然后，将强去相关变换复共空间模式（SUTCCSP）算法应用于这些节律，使由μ波和β波构成的复杂数据变得不相关，并且其伪协方差提供了两种节律之间的补充功率差异信息。使用SUTCCSP提取的最大化类间方差的特征，使用各种分类算法对从Physionet数据库获取的左手和右手运动想象EEG进行分离分类。本文表明，使用SUTCCSP获得的μ波和β波之间功率差异的补充信息为左手和右手运动想象任务的分类提供了重要特征。此外，与传统的IIR滤波相比，MEMD被证明是用于非线性和非平稳EEG信号的首选预处理方法。最后，随机森林分类器在运动想象任务的分类中表现出高性能。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/916a70df6085/CIN2016-1489692.010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/78173a3508bd/CIN2016-1489692.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/221292e59ef1/CIN2016-1489692.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/cf153872997f/CIN2016-1489692.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/782dcb4fee51/CIN2016-1489692.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/a8f8485f2882/CIN2016-1489692.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/1b70d416669c/CIN2016-1489692.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/65d4eb4e0cbc/CIN2016-1489692.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/53281c433f61/CIN2016-1489692.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/f2d29fca2664/CIN2016-1489692.009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/916a70df6085/CIN2016-1489692.010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/78173a3508bd/CIN2016-1489692.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/221292e59ef1/CIN2016-1489692.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/cf153872997f/CIN2016-1489692.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/782dcb4fee51/CIN2016-1489692.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/a8f8485f2882/CIN2016-1489692.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/1b70d416669c/CIN2016-1489692.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/65d4eb4e0cbc/CIN2016-1489692.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/53281c433f61/CIN2016-1489692.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/f2d29fca2664/CIN2016-1489692.009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/5dfc/5066028/916a70df6085/CIN2016-1489692.010.jpg

相似文献

1
Motor Imagery Classification Using Mu and Beta Rhythms of EEG with Strong Uncorrelating Transform Based Complex Common Spatial Patterns.基于强去相关变换的复数公共空间模式，利用脑电图的μ波和β波节律进行运动想象分类。
Comput Intell Neurosci. 2016;2016:1489692. doi: 10.1155/2016/1489692. Epub 2016 Oct 3.
2
Augmented Complex Common Spatial Patterns for Classification of Noncircular EEG From Motor Imagery Tasks.用于运动想象任务中非圆形脑电图分类的增强复数公共空间模式
IEEE Trans Neural Syst Rehabil Eng. 2014 Jan;22(1):1-10. doi: 10.1109/TNSRE.2013.2294903.
3
Correlation Assisted Strong Uncorrelating Transform Complex Common Spatial Patterns for Spatially Distant Channel Data.相关辅助强去相关变换复杂公共空间模式用于空间上遥远通道数据。
Comput Intell Neurosci. 2018 May 15;2018:4281230. doi: 10.1155/2018/4281230. eCollection 2018.
4
Embedded grey relation theory in Hopfield neural network: application to motor imagery EEG recognition.嵌入灰色关联理论的 Hopfield 神经网络：在运动想象脑电识别中的应用。
Clin EEG Neurosci. 2013 Oct;44(4):257-64. doi: 10.1177/1550059413477090. Epub 2013 Mar 26.
5
Classification of motor imagery BCI using multivariate empirical mode decomposition.使用多元经验模态分解对运动想象脑-机接口进行分类。
IEEE Trans Neural Syst Rehabil Eng. 2013 Jan;21(1):10-22. doi: 10.1109/TNSRE.2012.2229296. Epub 2012 Nov 27.
6
Enhancing the performance of motor imagery EEG classification using phase features.利用相位特征提高运动想象脑电信号分类性能。
Clin EEG Neurosci. 2015 Apr;46(2):113-8. doi: 10.1177/1550059414555123. Epub 2014 Nov 16.
7
An efficient rhythmic component expression and weighting synthesis strategy for classifying motor imagery EEG in a brain-computer interface.一种用于脑机接口中运动想象脑电信号分类的高效节律成分表达与加权合成策略。
J Neural Eng. 2004 Mar;1(1):1-7. doi: 10.1088/1741-2560/1/1/001. Epub 2004 Jan 20.
8
Time-variant spatial filtering for motor imagery classification.用于运动想象分类的时变空间滤波
Annu Int Conf IEEE Eng Med Biol Soc. 2007;2007:3124-7. doi: 10.1109/IEMBS.2007.4352991.
9
EEG rhythm separation and time-frequency analysis of fast multivariate empirical mode decomposition for motor imagery BCI.脑-机接口中运动想象的快速多变量经验模态分解的 EEG 节律分离和时频分析。
Biol Cybern. 2024 Apr;118(1-2):21-37. doi: 10.1007/s00422-024-00984-1. Epub 2024 Mar 12.
10
A new discriminative common spatial pattern method for motor imagery brain-computer interfaces.一种新的运动想象脑-机接口的判别式公共空间模式方法。
IEEE Trans Biomed Eng. 2009 Nov;56(11 Pt 2):2730-3. doi: 10.1109/TBME.2009.2026181. Epub 2009 Jul 14.

引用本文的文献

1
Enhanced EEG signal classification in brain computer interfaces using hybrid deep learning models.使用混合深度学习模型增强脑机接口中的脑电图信号分类
Sci Rep. 2025 Jul 25;15(1):27161. doi: 10.1038/s41598-025-07427-2.
2
A Combined Virtual Electrode-Based ESA and CNN Method for MI-EEG Signal Feature Extraction and Classification.基于虚拟电极的组合 ESA 和 CNN 方法在 MI-EEG 信号特征提取和分类中的应用。
Sensors (Basel). 2023 Nov 1;23(21):8893. doi: 10.3390/s23218893.
3
Temporal-frequency-phase feature classification using 3D-convolutional neural networks for motor imagery and movement.

本文引用的文献

1
A novel channel selection method for optimal classification in different motor imagery BCI paradigms.一种用于不同运动想象脑机接口范式中最优分类的新型通道选择方法。
Biomed Eng Online. 2015 Oct 21;14:93. doi: 10.1186/s12938-015-0087-4.
2
Augmented Complex Common Spatial Patterns for Classification of Noncircular EEG From Motor Imagery Tasks.用于运动想象任务中非圆形脑电图分类的增强复数公共空间模式
IEEE Trans Neural Syst Rehabil Eng. 2014 Jan;22(1):1-10. doi: 10.1109/TNSRE.2013.2294903.
3
Random forests in non-invasive sensorimotor rhythm brain-computer interfaces: a practical and convenient non-linear classifier.
使用三维卷积神经网络进行运动想象和运动的时间频率相位特征分类。
Front Neurosci. 2023 Aug 28;17:1250991. doi: 10.3389/fnins.2023.1250991. eCollection 2023.
4
Recognize enhanced temporal-spatial-spectral features with a parallel multi-branch CNN and GRU.利用并行多分支卷积神经网络和门控循环单元识别增强的时-空-谱特征。
Med Biol Eng Comput. 2023 Aug;61(8):2013-2032. doi: 10.1007/s11517-023-02857-4. Epub 2023 Jun 9.
5
Beyond passive observation: feedback anticipation and observation activate the mirror system in virtual finger movement control via P300-BCI.超越被动观察：反馈预期与观察通过P300脑机接口在虚拟手指运动控制中激活镜像系统。
Front Hum Neurosci. 2023 May 4;17:1180056. doi: 10.3389/fnhum.2023.1180056. eCollection 2023.
6
[Research on the feature representation of motor imagery electroencephalogram signal based on individual adaptation].基于个体适应性的运动想象脑电信号特征表征研究
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2022 Dec 25;39(6):1173-1180. doi: 10.7507/1001-5515.202112023.
7
Effective Connectivity for Decoding Electroencephalographic Motor Imagery Using a Probabilistic Neural Network.使用概率神经网络对脑电运动想象进行解码的有效连通性。
Sensors (Basel). 2021 Sep 30;21(19):6570. doi: 10.3390/s21196570.
8
Mapping causal circuit dynamics in stroke using simultaneous electroencephalography and transcranial magnetic stimulation.利用同步脑电图和经颅磁刺激绘制中风中的因果回路动力学
BMC Neurol. 2021 Jul 16;21(1):280. doi: 10.1186/s12883-021-02319-0.
9
A Simplified CNN Classification Method for MI-EEG via the Electrode Pairs Signals.一种基于电极对信号的心肌梗死脑电图简化卷积神经网络分类方法。
Front Hum Neurosci. 2020 Sep 15;14:338. doi: 10.3389/fnhum.2020.00338. eCollection 2020.
10
Parallel Mechanism of Spectral Feature-Enhanced Maps in EEG-Based Cognitive Workload Classification.基于脑电的认知负荷分类中的光谱特征增强图谱的并行机制。
Sensors (Basel). 2019 Feb 16;19(4):808. doi: 10.3390/s19040808.
用于非侵入式感觉运动节律脑机接口的随机森林：一种实用便捷的非线性分类器。
Biomed Tech (Berl). 2016 Feb;61(1):77-86. doi: 10.1515/bmt-2014-0117.
4
Performance variation in motor imagery brain-computer interface: a brief review.运动想象脑机接口中的性能差异：简要综述
J Neurosci Methods. 2015 Mar 30;243:103-10. doi: 10.1016/j.jneumeth.2015.01.033. Epub 2015 Feb 8.
5
Distinct roles for alpha- and beta-band oscillations during mental simulation of goal-directed actions.在目标导向行为的心理模拟过程中，α波段和β波段振荡发挥着不同作用。
J Neurosci. 2014 Oct 29;34(44):14783-92. doi: 10.1523/JNEUROSCI.2039-14.2014.
6
Classification of functional near-infrared spectroscopy signals corresponding to the right- and left-wrist motor imagery for development of a brain-computer interface.用于开发脑机接口的右腕和左腕运动想象对应的功能近红外光谱信号分类。
Neurosci Lett. 2013 Oct 11;553:84-9. doi: 10.1016/j.neulet.2013.08.021. Epub 2013 Aug 20.
7
L1 norm based common spatial patterns decomposition for scalp EEG BCI.基于 L1 范数的头皮 EEG BCI 共空间模式分解。
Biomed Eng Online. 2013 Aug 6;12:77. doi: 10.1186/1475-925X-12-77.
8
Emotional information processing in major depression remission and partial remission: faces come first.重度抑郁症缓解期和部分缓解期的情绪信息处理：面部信息优先处理
Appl Neuropsychol Adult. 2013;20(2):110-9. doi: 10.1080/09084282.2012.670159. Epub 2012 Dec 14.
9
Classification of motor imagery BCI using multivariate empirical mode decomposition.使用多元经验模态分解对运动想象脑-机接口进行分类。
IEEE Trans Neural Syst Rehabil Eng. 2013 Jan;21(1):10-22. doi: 10.1109/TNSRE.2012.2229296. Epub 2012 Nov 27.
10
Complex-valued spatial filters for task discrimination.用于任务辨别的复值空间滤波器。
Annu Int Conf IEEE Eng Med Biol Soc. 2010;2010:4707-10. doi: 10.1109/IEMBS.2010.5626381.