采用源空间套索分析和卷积神经网络方法的高频脑电动作模式识别方法

陶怡; 徐维维; 朱家林; 袁子文; 王茂德; 王刚

doi:10.7652/xjtuxb202401018

您当前的位置：

首页 >

文章列表页 >

采用源空间套索分析和卷积神经网络方法的高频脑电动作模式识别方法

更新时间：2025-05-13

- 采用源空间套索分析和卷积神经网络方法的高频脑电动作模式识别方法
- Movement Patten Recognition Using Group LASSO and CNN Based on HighFrequency Signal in Source Space
- 西安交通大学学报 2024年58卷第1期页码：187-196
- 作者机构：
  
  1. 西安交通大学生物医学信息工程教育部重点实验室,西安,710049
  2. 西安交通大学第一附属医院康复医学科,西安,710061
  3. 西安交通大学第一附属医院神经外科,西安,710061
- 作者简介：
  
  : 2022-12-29。作者简介: 陶怡(1997—),女,博士生
  王刚(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(32071372, 62271385)
- 基金信息：
  
  : 2022-12-29。作者简介: 陶怡(1997—),女,博士生;王刚(通信作者),男,教授,博士生导师。基金项目: 国家自然科学基金资助项目(32071372, 62271385);四川省科技计划资助项目(2022YFS0030)。
- DOI：10.7652/xjtuxb202401018
  中图分类号： TP391.4
- 网络首发：2024-01-10，
  
  纸质出版：2024
- 稿件说明：
移动端阅览
陶怡, 徐维维, 朱家林, 等. 采用源空间套索分析和卷积神经网络方法的高频脑电动作模式识别方法[J]. 西安交通大学学报, 2024,58(1):187-196.

TAO Yi, XU Weiwei, ZHU Jialin, et al. Movement Patten Recognition Using Group LASSO and CNN Based on HighFrequency Signal in Source Space[J]. 2024, 58(1): 187-196.
陶怡, 徐维维, 朱家林, 等. 采用源空间套索分析和卷积神经网络方法的高频脑电动作模式识别方法[J]. 西安交通大学学报, 2024,58(1):187-196. DOI： 10.7652/xjtuxb202401018.

TAO Yi, XU Weiwei, ZHU Jialin, et al. Movement Patten Recognition Using Group LASSO and CNN Based on HighFrequency Signal in Source Space[J]. 2024, 58(1): 187-196. DOI： 10.7652/xjtuxb202401018.

摘要

针对目前同侧手部运动意图识别率低的问题

提出了一种基于源空间套索分析和卷积神经网络(source-Lasso-CNN

SLC)的高频脑电动作模式识别方法。该方法运用空间源定位分析与握拳、展拳、二指对捏、三指对捏4种动作相关的脑电信号

使用组Lasso进行感兴趣区域(ROI)选择

再输入到卷积神经网络进行单手多类动作模式识别。采集13名被试者在4种手部动作模式下的脑电和肌电信号并进行预处理

采用基于核磁共振图像的边界元模型建立头模型、使用最小范数估计解决脑电源成像逆问题

将传感器空间的脑电信号映射至源空间。将源空间脑电序列按照布罗德曼分区进行划分

提取每个脑区的3个时域特征并基于特征采用组Lasso方法进行ROI选择

将挑选出的ROI及其对应源空间序列输入卷积神经网络中进行四分类。实验结果表明:采用source-Lasso-CNN的方法在高频(γ频带)脑电的识别准确率可达(82.23±12.71)%

优于在δ(1～3 Hz)、θ(4～7 Hz)、α(8～13 Hz)、β(14～30 Hz)以及全频带(1～100 Hz)上的结果。与其他先进方法相比

其准确率也有显著性的提升

显示了该方法在同侧手部运动意图识别中的有效性。

Abstract

Addressing the challenge of low classification accuracy in ipsilateral hand movements

this paper presents a novel method named source-Lasso-CNN(SLC). The approach involves analyzing electroencephalogram(EEG)signals before movement onset in the gamma band(30—100 Hz)that are associated with four specific hand movements(tip pinch

multiple tip pinch

hand close and hand open)using spatial source localization. Region of interest(ROI)was selected using group Lasso

and then the selected signals were input into convolutional neural network(CNN)for multi-class hand movement pattern recognition. The specific steps are as follows. Firstly

EEG and EMG signals were simultaneously collected from 13 subjects during the execution of the four hand movements

followed by preprocessing. Next

a head model was established using a boundary element model based on magnetic resonance image

and the inverse problem of EEG imaging was solved by using the minimum norm estimation method. The EEG sequences in the source space were divided into 79 regions based on Brodmann area. Three time-domain features were extracted from each brain region and a group Lasso algorithm was employed to select the ROI. Finally

the selected ROI and its corresponding source space sequences were input into the CNN for classification. The results show that the LASSO-CNN method

utilizing high frequency(γ band)source space signals

achieves a superior classification accuracy of(82.23+12.71)%

which is better than that in δ(1—3 Hz)

θ(4—7 Hz)

α(8—13 Hz)

β(14—30 Hz)and full frequency band(1—100 Hz). Furthermore

the results also show a significant improvement in accuracy compared to other advanced algorithms

highlighting its effectiveness in recognizing identical hand motion pattern.

关键词

Keywords

references

CHOI W S, YEOM H G. Studies to overcome brain-computer interface challenges [J]. Applied Sciences, 2022, 12(5): 2598.

SHAFIUL HASAN S M, SIDDIQUEE M R, ATRI R, et al. Prediction of gait intention from pre-movement EEG signals: a feasibility study [J]. Journal of NeuroEngineering and Rehabilitation, 2020, 17(1): 50.

HUANG Chenxi, XIAO Yutian, XU Gaowei. Predicting human intention-behavior through EEG signal analysis using multi-scale CNN [J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2021, 18(5): 1722-1729.

CLAYTON M S, YEUNG N, COHEN KADOSH R. The roles of cortical oscillations in sustained attention [J]. Trends in Cognitive Sciences, 2015, 19(4): 188-195.

BUZSÁKI G. Rhythms of the brain [M]. New York, USA: Oxford University Press, 2006.

CAMPBELL I G, FEINBERG I. Longitudinal trajectories of non-rapid eye movement delta and theta EEG as indicators of adolescent brain maturation [J]. Proceedings of the National Academy of Sciences of the United States of America, 2009, 106(13): 5177-5180.

HARMONY T. The functional significance of Delta oscillations in cognitive processing [J]. Frontiers in Integrative Neuroscience, 2013, 7: 83.

KNYAZEV G G. EEG delta oscillations as a correlate of basic homeostatic and motivational processes [J]. Neuroscience Biobehavioral Reviews, 2012, 36(1): 677-695.

SAUSENG P, GRIESMAYR B, FREUNBERGER R, et al. Control mechanisms in working memory: a possible function of EEG theta oscillations [J]. Neuroscience Biobehavioral Reviews, 2010, 34(7): 1015-1022.

KLIMESCH W. Alpha-band oscillations, attention, and controlled access to stored information [J]. Trends in Cognitive Sciences, 2012, 16(12): 606-617.

WOLPAW J R, BIRBAUMER N, MCFARLAND D J, et al. Brain-computer interfaces for communication and control [J]. Clinical Neurophysiology, 2002, 113(6): 767-791.

JUREWICZ K, PALUCH K, KUBLIK E, et al. EEG-neurofeedback training of beta band(12—22 Hz)affects alpha and beta frequencies: a controlled study of a healthy population [J]. Neuropsychologia, 2018, 108: 13-24.

GOLA M, MAGNUSKI M, SZUMSKA I, et al. EEG beta band activity is related to attention and attentional deficits in the visual performance of elderly subjects [J]. International Journal of Psychophysiology, 2013, 89(3): 334-341.

JIA Xiaoxuan, KOHN A. Gamma rhythms in the brain [J]. PLOS Biology, 2011, 9(4): e1001045.

ZHANG Mingming, WU Junde, SONG J, et al. Decoding coordinated directions of bimanual movements from EEG signals [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023, 31: 248-259.

MOHSENI M, SHALCHYAN V, JOCHUMSEN M, et al. Upper limb complex movements decoding from pre-movement EEG signals using wavelet common spatial patterns [J]. Computer Methods and Programs in Biomedicine, 2020, 183: 105076.

THÜRER B, STOCKINGER C, FOCKE A, et al. Increased gamma band power during movement planning coincides with motor memory retrieval [J]. NeuroImage, 2016, 125: 172-181.

TAO Yi, YAN Nong, WANG Gang. Hand movement prediction based on EEG signals by combining MEMD and CSP [C]//Proceedings of the 2020 2nd International Conference on Image Processing and Machine Vision. New York, NY, USA: Association for Computing Machinery, 2020: 105-112.

TAO Yi, XU Weiwei, WANG Guangming, et al. Decoding multi-class EEG signals of hand movement using multivariate empirical mode decomposition and convolutional neural network [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 2754-2763.

MAMMONE N, IERACITANO C, MORABITO F C. A deep CNN approach to decode motor preparation of upper limbs from time-frequency maps of EEG signals at source level [J]. Neural Networks, 2020, 124: 357-372.

唐肖芳, 周金治. 基于散度分析的脑电信号特征选择 [J]. 计算机工程, 2015, 41(5): 290-294.

TANG Xiaofang, ZHOU Jinzhi. Electroencephalogram feature selection based on divergence analysis [J]. Computer Engineering, 2015, 41(5): 290-294.

LIU Aiming, CHEN Kun, LIU Quan, et al. Feature selection for motor imagery EEG classification based on firefly algorithm and learning automata [J]. Sensors, 2017, 17(11): 2576.

杨鹏圆, 李海芳, 陈东伟. 脑电信号特征的归一化方式与选择方法研究 [J]. 计算机应用与软件, 2015, 32(2): 48-52.

YANG Pengyuan, LI Haifang, CHEN Dongwei. Research on normalisation manner and selection method for EEG features [J]. Computer Applications and Software, 2015, 32(2): 48-52.

孟明, 胡家豪, 高云园, 等. 结合互信息通道选择与混合深度神经网络的脑电情感识别方法 [J]. 传感技术学报, 2021, 34(8): 1089-1095.

MENG Ming, HU Jiahao, GAO Yunyuan, et al. EEG emotion recognition based on normalized mutual information channel selection and hybrid deep neural network [J]. Chinese Journal of Sensors and Actuators, 2021, 34(8): 1089-1095.

曹玉珍, 高晨阳, 余辉, 等. 基于深度学习的癫痫脑电通道选择与发作检测 [J]. 天津大学学报(自然科学与工程技术版), 2020, 53(4): 426-432.

CAO Yuzhen, GAO Chenyang, YU Hui, et al. Epileptic EEG channel selection and seizure detection based on deep learning [J].Journal of Tianjin University(Science and Technology), 2020, 53(4): 426-432.

TIBSHIRANI R. Regression shrinkage and selection via the lasso [J]. Journal of the Royal Statistical Society: Series B(Methodological), 1996, 58(1): 267-288.

王金甲, 薛芳, 李慧. 基于稀疏组lasso的脑机接口通道和特征选择研究 [J]. 仪器仪表学报, 2015, 36(8): 1831-1837.WANG Jinjia, XUE Fang, LI Hui. Research on channel and feature selection for brain-computer interface based on sparse group lasso [J]. Chinese Journal of Scientific Instrument, 2015, 36(8): 1831-1837.

AMIN S U, ALSULAIMAN M, MUHAMMAD G, et al. Deep learning for EEG motor imagery classification based on multi-layer CNNs feature fusion [J]. Future Generation Computer Systems, 2019, 101: 542-554.

FUJIWARA Y, USHIBA J. Deep residual convolutional neural networks for brain: computer interface to visualize neural processing of hand movements in the human brain [J]. Frontiers in Computational Neuroscience, 2022, 16: 882290.

WANG Gang, REN Doutian. Classification of surface electromyographic signals by means of multifractal singularity spectrum [J]. Medical Biological Engineering Computing, 2013, 51(3): 277-284.

HÄMÄLÄINEN M S, ILMONIEMI R J. Interpreting magnetic fields of the brain: minimum norm estimates [J]. Medical Biological Engineering Computing, 1994, 32(1): 35-42.

SCHIRRMEISTER R T, SPRINGENBERG J T, FIEDERER L D J, et al. Deep learning with convolutional neural networks for EEG decoding and visualization [J]. Human Brain Mapping, 2017, 38(11): 5391-5420.

ZHANG Tong, WANG Xuehan, XU Xiangmin, et al. GCB-net: graph convolutional broad network and its application in emotion recognition [J]. IEEE Transactions on Affective Computing, 2022, 13(1): 379-388.

LAWHERN V J, SOLON A J, WAYTOWICH N R, et al. EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces [J]. Journal of Neural Engineering, 2018, 15(5): 056013.

TANG Zhichuan, LI Chao, SUN Shouqian. Single-trial EEG classification of motor imagery using deep convolutional neural networks [J]. Optik, 2017, 130: 11-18.

ANG Kaikeng, CHIN Z Y, ZHANG Haihong, et al. Filter bank common spatial pattern(FBCSP)in brain-computer interface [C]//2008 IEEE International Joint Conference on Neural Networks. Piscataway, NJ, USA: IEEE, 2008: 2390-2397.

GAUR P, PACHORI R B, WANG Hui, et al. An automatic subject specific intrinsic mode function selection for enhancing two-class EEG-based motor imagery-brain computer interface [J]. IEEE Sensors Journal, 2019, 19(16): 6938-6947.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

蜉蝣优化双通道网络在齿轮箱故障诊断中的应用

一种适用于混合三端直流输电线路的故障定位方法

采用格拉姆角场-卷积神经网络-时序卷积网络混合模型的锂离子电池健康状态估计

一种基于FPGA的卷积神经网络协处理器设计

一种高分辨率遥感图像视感知目标检测算法