An Efficient Shallow Convolutional Decoding Network for Motor Imagery Electroencephalography Signals

LI Wenping; XU Guanghua; ZHANG Kai; ZHANG Sicong; ZHAO Lijiao; LI Hui

doi:10.7652/xjtuxb202310002

您当前的位置：

首页 >

文章列表页 >

An Efficient Shallow Convolutional Decoding Network for Motor Imagery Electroencephalography Signals

更新时间：2025-05-08

- An Efficient Shallow Convolutional Decoding Network for Motor Imagery Electroencephalography Signals
- Vol. 57, Issue 10, Pages: 11-19(2023)
- 作者机构：
  
  1. 西安交通大学机械工程学院,西安,710049
  2. 西安交通大学机械制造系统工程国家重点实验室,西安,710054
  3. 西安交通大学经济与金融学院,西安,710061
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202310002
  CLC： Q983.5;TP242
- Online First：10 October 2023，
  
  Published：2023
- 稿件说明：
移动端阅览
LI Wenping, XU Guanghua, ZHANG Kai, et al. An Efficient Shallow Convolutional Decoding Network for Motor Imagery Electroencephalography Signals[J]. 2023, 57(10): 11-19.
DOI：

LI Wenping, XU Guanghua, ZHANG Kai, et al. An Efficient Shallow Convolutional Decoding Network for Motor Imagery Electroencephalography Signals[J]. 2023, 57(10): 11-19. DOI： 10.7652/xjtuxb202310002.

摘要

针对现有运动想象脑机接口(MI-BCIs)中

基于深度学习的脑电信号解码网络(EEGNet)时域-空域-频域耦合特征学习能力差、模型训练与推理时间长的问题

提出了一种高效运动想象脑电信号浅层卷积解码网络(Faster-EEGNet)。该网络将第1层二维平面串行卷积优化为所有通道同时进行的串行卷积

完成了各通道信号的时域滤波与空间滤波; 在中间深度卷积层对空间模式提取信号进行时域卷积特征提取

然后由深度分离卷积再次提取信号的时间-空间耦合特征

并对其进行模式识别。采用公开数据集进行仿真实验验证

结果表明:Faster-EEGNet网络的运动想象识别准确率与信息传输率相较于EEGNet网络有更好的表现

在本实验的小样本训练场景下也能够取得较好的识别效果; 相较于EEGNet网络

Faster-EEGNet网络的训练时间减少了44.8%

模型推理时间减少了43.6%以上。实验结果证明所提Faster-EEGNet网络能够提升运动想象脑机接口系统的识别准确性、便捷性及快速响应性能。

Abstract

To address the problems of poor temporal-spatial-frequency coupling feature learning and lengthy model training and inference of deep learning-based electroencephalography signal decoding networks(EEGNet)in existing motor imagery-based brain-computer interfaces(MI-BCIs)

an efficient shallow convolutional decoding network called Faster-EEGNet was proposed. In this network

the first layer of two-dimensional serial convolution was optimized to perform parallel convolution on all channels simultaneously. This enabled the completion of temporal filtering and spatial filtering of signals across all channels. Temporal convolutional features were captured from spatial pattern-extracted signals at the intermediate deep convolutional layers. Then

the depthwise separable convolution was used to capture the temporal-spatial coupling features of the signals for pattern recognition. Experimental validation was conducted using publicly available datasets. The results demonstrate that the Faster-EEGNet exhibits better performance than the EEGNet in motor imagery recognition accuracy and information transfer rate. This network also achieves good recognition results in small-sample training scenarios. Furthermore

the Faster-EEGNet reduces training time by 44.8% and model inference time by more than 43.6% compared to the EEGNet. These findings demonstrate that the proposed Faster-EEGNet can enhance the recognition accuracy

convenience

and rapid response performance of the motor imagery brain-computer interface system.

关键词

Keywords

references

WOLPAW J R, BIRBAUMER N, HEETDERKS W J, et al. Brain-computer interface technology: a review of the first international meeting [J]. IEEE Transactions on Rehabilitation Engineering, 2000, 8(2): 164-173.

王维振, 曲皓, 雷杨浩, 等. 下肢运动想象脑机接口的研究进展及康复应用 [J]. 北京生物医学工程, 2023, 42(2): 204-211.

WANG Weizhen, QU Hao, LEI Yanghao, et al. Research progress and rehabilitation application of brain-computer interface based on lower-limb motor imagery [J]. Beijing Biomedical Engineering, 2023, 42(2): 204-211.

张海军, 王浩川. 多导联EEG信号分类识别研究 [J]. 计算机工程与应用, 2008, 44(24): 228-230.

ZHANG Haijun, WANG Haochuan. Research on classification and recognition of multi-channel EEG signal [J]. Computer Engineering and Applications, 2008, 44(24): 228-230.

KUMAR J S, BHUVANESWARI P. Analysis of electroencephalography(EEG)signals and its categorization-a study [J]. Procedia Engineering, 2012, 38: 2525-2536.

LI Zheng, O'DOHERTY J E, HANSON T L, et al. Unscented Kalman filter for brain-machine interfaces [J]. PLOS One, 2009, 4(7): e6243.

VAN ERP J, LOTTE F, TANGERMANN M. Brain-computer interfaces: beyond medical applications [J]. Computer, 2012, 45(4): 26-34.

王迪, 陶庆, 张小栋, 等. 采用改进共空间模式算法的四类表情辅助脑电信号识别方法 [J]. 西安交通大学学报, 2022, 56(12): 136-143.

WANG Di, TAO Qing, ZHANG Xiaodong, et al. Recognition of four-class facial expression electroencephalogram data using improved common spatial pattern algorithm [J]. Journal of Xi'an Jiaotong University, 2022, 56(12): 136-143.

MÜLLER-GERKING J, PFURTSCHELLER G, FLYVBJERG H. Designing optimal spatial filters for single-trial EEG classification in a movement task [J]. Clinical Neurophysiology, 1999, 110(5): 787-798.

SONG Xiaomu, YOON S C, PERERA V. Adaptive common spatial pattern for single-trial EEG classification in multisubject BCI [C]//2013 6th International IEEE/EMBS Conference on Neural Engineering(NER). Piscataway, NJ, USA: IEEE, 2013: 411-414.

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(IEEE World Congress on Computational Intelligence). [S.l.]: IEEE, 2008: 2390-2397.

HIGASHI H, TANAKA T. Simultaneous design of FIR filter banks and spatial patterns for EEG signal classification [J]. IEEE Transactions on Biomedical Engineering, 2013, 60(4): 1100-1110.

MIAO Yangyang, JIN Jing, DALY I, et al. Learning common Time-Frequency-Spatial patterns for motor imagery classification [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021, 29: 699-707.

HOU Yimin, CHEN Tao, LUN Xiangmin, et al. A novel method for classification of multi-class motor imagery tasks based on feature fusion [J]. Neuroscience Research, 2022, 176: 40-48.

VOULODIMOS A, DOULAMIS N, DOULAMIS A, et al. Deep learning for computer vision: a brief review [J]. Computational Intelligence and Neuroscience, 2018, 2018: 7068349.

GAVAT I, MILITARU Diana. Deep learning in acoustic modeling for automatic speech recognition and understanding: an overview [C]//2015 International Conference on Speech Technology and Human-Computer Dialogue(SpeD). Piscataway, NJ, USA: IEEE, 2015: 1-8.

ANTONIADES A, SPYROU L, TOOK C C, et al. Deep learning for epileptic intracranial EEG data [C]//2016 IEEE 26th International Workshop on Machine Learning for Signal Processing(MLSP). Piscataway, NJ, USA: IEEE, 2016: 1-6.

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.

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.

LIU Xiaolin, SHI Rongye, HUI Qianxin, et al. TCACNet: temporal and channel attention convolutional network for motor imagery classification of EEG-based BCI [J]. Information Processing Management, 2022, 59(5): 103001.

宋耀莲, 殷喜喆, 杨俊. 基于时空特征学习Transformer的运动想象脑电解码方法 [J]. 南京大学学报(自然科学), 2023, 59(2): 313-321.

SONG Yaolian, YIN Xizhe, YANG Jun. Transformer based on temporal-spatial feature learning for motor imagery electroencephalogram signal decoding [J]. Journal of Nanjing University(Natural Science), 2023, 59(2): 313-321.

NIU Xiaochen, WU Xiaoguang, XIE Ping, et al. A time-frequency analysis of event-related desynchronization/synchronization based on Gabor filter [C]//Proceeding of the 11th World Congress on Intelligent Control and Automation. Piscataway, NJ, USA: IEEE, 2014: 5179-5184.

PADFIELD N, ZABALZA J, ZHAO Huimin, et al. EEG-based brain-computer interfaces using motor-imagery: techniques and challenges [J]. Sensors, 2019, 19(6): 1423.

WU C W. ProdSumNet: reducing model parameters in deep neural networks via product-of-sums matrix decompositions [EB/OL].(2019-05-23)[2022-10-20]. https://arxiv.org/abs/1809.02209.

FLESHER S N, DOWNEY J E, WEISS J M, et al. A brain-computer interface that evokes tactile sensations improves robotic arm control [J]. Science, 2021, 372(6544): 831-836.

CHOLLET F. Xception: deep learning with depthwise separable convolutions [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Piscataway, NJ, USA: IEEE, 2017: 1800-1807.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Intelligent Quantitative Non-Destructive Evaluation Method for Delamination of Carbon Fiber Composite Tube with Mirror-Reflection Infrared Thermography

Model Predictive Control-Oriented Deep Koopman Global Linear Modeling Method for Wind Turbines

Dynamic Liquid Level Prediction of Steam Generator under Main Steam Pipe Rupture Accidents

A Pure Convolutional Model Fused with U-net Network for Video Prediction

Application of Interpretable Convolutional Neural Network Enabled by Bi-Damped Wavelets in Bearing Fault Diagnosis

Related Author

YANG Yang

CHEN Hongen

LIU Bofan

TONG Zongfei

PEI Cuixiang

CHEN Zhenmao

TIAN Runze

KOU Peng

Related Institution

School of Aerospace Engineering，Xi’an Jiaotong University

State Key Laboratory for Strength and Vibration of Mechanical Structures，Xi’an Jiaotong University

Shaanxi Engineering Research Center of Nondestructive Testing and Structural Integrity Evaluation，Xi’an Jiaotong University

Northern Branch, Beijing Jingneng International Holding Co., Ltd.

State Key Laboratory of Electrical Insulation and Power Equipment, Xi'an Jiaotong University

⁰