用于运动单元活动追踪的动作电位卷积神经网络分类方法仿真研究

李怡欣; 郑杨

doi:10.7652/xjtuxb202306002

您当前的位置：

首页 >

文章列表页 >

用于运动单元活动追踪的动作电位卷积神经网络分类方法仿真研究

专题医工交叉与人机交互 | 更新时间：2025-05-08

- 用于运动单元活动追踪的动作电位卷积神经网络分类方法仿真研究
- Simulation Study on CNN-Based Motor Unit Action Potential Classification Method for Activity Tracking of Motor Unit
- 西安交通大学学报 2023年57卷第6期页码：10-17
- 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,710049
- 作者简介：
  
  : 2022-11-16。作者简介: 李怡欣(1999—),女,硕士生
  郑杨(通信作者),男,副教授,博士生导师。基金项目: 科技创新2030基金资助项目(2022ZD0209800)
- 基金信息：
  
  : 2022-11-16。作者简介: 李怡欣(1999—),女,硕士生;郑杨(通信作者),男,副教授,博士生导师。基金项目: 科技创新2030基金资助项目(2022ZD0209800);国家自然科学基金资助项目(52105309);陕西省秦创原引用高层次创新创业人才资助项目(QCYRCXM-2022-34)。
- DOI：10.7652/xjtuxb202306002
  中图分类号： R318.04
- 网络首发：2023-06-10，
  
  纸质出版：2023
- 稿件说明：
移动端阅览
李怡欣, 郑杨. 用于运动单元活动追踪的动作电位卷积神经网络分类方法仿真研究[J]. 西安交通大学学报, 2023,57(6):10-17.

LI Yixin, ZHENG Yang. Simulation Study on CNN-Based Motor Unit Action Potential Classification Method for Activity Tracking of Motor Unit[J]. 2023, 57(6): 10-17.
李怡欣, 郑杨. 用于运动单元活动追踪的动作电位卷积神经网络分类方法仿真研究[J]. 西安交通大学学报, 2023,57(6):10-17. DOI： 10.7652/xjtuxb202306002.

LI Yixin, ZHENG Yang. Simulation Study on CNN-Based Motor Unit Action Potential Classification Method for Activity Tracking of Motor Unit[J]. 2023, 57(6): 10-17. DOI： 10.7652/xjtuxb202306002.

摘要

为了解决在真实条件下运动单元动作电位(MUAP)波形变异导致的MUAP分类识别准确率低

进而降低运动单元(MU)追踪性能的问题

提出了一种基于卷积神经网络(CNN)的MUAP分类方法

并利用仿真数据进行了效果验证。该方法以被称为MU指纹的MUAP波形作为模型输入

结合Keras深度学习框架设计的CNN网络结构简单

并采取Early-stop策略训练网络

可实现不同MU的准确分类和匹配

从而持续追踪给定MU放电活动。所提基于CNN的MU分类方法能够在样本量较小的情况下

即每个MU可获取(54.49±29.28)个MUAP波形样本

对平均(30.23±5.37)个MU进行准确分类

分类准确性达到(89.41%±3.72%)

显著高于现有的基于MUAP波形相似度的方法(49.66%±6.12%)。结果表明

所提方法对MUAP波形变异展现出了更好的鲁棒性

为开展真实条件下MU放电活动持续追踪研究提供重要的技术支撑

对运动控制的神经机制研究等具有重要意义。

Abstract

To solve the problem of low accuracy of motor unit action potential(MUAP)waveform similarity classification method caused by MUAP waveform variation under real conditions

which reduces the tracking performance of the motor unit(MU)

a MUAP classification method based on convolutional neural network(CNN)was proposed and tested using the simulated high-density electromyogram(EMG)recordings in this paper. The network was designed with the Keras deep-learning framework and had a simple structure with the MUAP waveform called MU “fingerprints” as the input. The network was trained using the early-stop strategy in order to realize the classification and matching of different MUs

and thus longitudinal tracking of the discharge activities of given MUs. The results showed that the proposed CNN-based method could reach a classification accuracy of(89.41% ± 3.72%)among(30.23 ± 5.37)MUs on average even when only(54.49 ± 29.28)MUAP waveform samples were available for individual MUs. The performance of the proposed method was significantly higher than the conventional MUAP waveform similarity classification method with an accuracy of(49.66%±6.12%). These results demonstrated that the proposed method was more robust to the variation of MUAP waveforms. The proposed method has the potential to promote the studies in which longitudinal tracking of MU discharge activities is needed

and it is of great significance for multiple studies such as the exploration of the neural mechanisms underlying motor control.

关键词

Keywords

references

SØGAARD K. Motor unit recruitment pattern during low-level static and dynamic contractions [J]. Muscle & Nerve, 1995, 18(3): 292-300.[2] MURPHY S A, NEGRO F, FARINA D, et al. Stroke increases ischemia-related decreases in motor unit discharge rates [J]. Journal of Neurophysiology, 2018, 120(6): 3246-3256.[3] ZHENG Yang, HU Xiaogang. Concurrent estimation of finger flexion and extension forces using motoneuron discharge information [J]. IEEE Transactions on Biomedical Engineering, 2021, 68(5): 1638-1645.[4] DE LUCA C J, ADAM A, WOTIZ R, et al. Decomposition of surface EMG signals [J]. Journal of Neurophysiology, 2006, 96(3): 1646-1657.[5] ZHENG Yang, HU Xiaogang. Adaptive real-time decomposition of electromyogram during sustained muscle activation: a simulation study [J]. IEEE Transactions on Biomedical Engineering, 2022, 69(2): 645-653.[6] HU Xiaogang, RYMER W Z, SURESH N L. Motor unit pool organization examined via spike-triggered averaging of the surface electromyogram [J]. Journal of Neurophysiology, 2013, 110(5): 1205-1220.[7] MARTINEZ-VALDES E, NEGRO F, LAINE C M, et al. Tracking motor units longitudinally across experimental sessions with high-density surface electromyography [J]. The Journal of Physiology, 2017, 595(5): 1479-1496.[8] 褚雪忠, 杨基海, 李强, 等. 电极配置对MUAP检测影响的仿真研究 [J]. 生物医学工程研究, 2006, 25(3): 137-140, 146.CHU Xuezhong, YANG Jihai, LI Qiang, et al. A simulation study on the influence of electrode's configuration on motor unit action potential detection [J]. Journal of Biomedical Engineering Research, 2006, 25(3): 137-140, 146.[9] STEGEMAN D F, BLOK J H, HERMENS H J, et al. Surface EMG models: properties and applications [J]. Journal of Electromyography and Kinesiology, 2000, 10(5): 313-326.[10] FARINA D, GAZZONI M, CAMELIA F. Low-threshold motor unit membrane properties vary with contraction intensity during sustained activation with surface EMG visual feedback [J]. Journal of Applied Physiology, 2004, 96(4): 1505-1515.[11] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks [J]. Science, 2006, 313(5786): 504-507.[12] LECUN Y, BENGIO Y, HINTON G. Deep learning [J]. Nature, 2015, 521(7553): 436-444.[13] LI Haoxiang, LIN Zhe, SHEN Xiaohui, et al. A convolutional neural network cascade for face detection [C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2015: 5325-5334.[14] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM, 2017, 60(6): 84-90.[15] HINTON G, DENG Li, YU Dong, et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups [J]. IEEE Signal Processing Magazine, 2012, 29(6): 82-97.[16] KIM Y. Convolutional neural networks for sentence classification [EB/OL]. [2022-10-10]. https://arxiv.org/abs/1408.5882.[17] 陈保家, 陈学力, 沈保明, 等. CNN-LSTM深度神经网络在滚动轴承故障诊断中的应用 [J]. 西安交通大学学报, 2021, 55(6): 28-36.CHEN Baojia, CHEN Xueli, SHEN Baoming, et al. An application of convolution neural network and long short-term memory in rolling bearing fault diagnosis [J]. Journal of Xi'an Jiaotong University, 2021, 55(6): 28-36.[18] 吕阳, 廖与禾, 王报祥, 等. 基于VMD和CNN的滚动轴承故障定量诊断方法 [J]. 中国科技论文, 2020, 15(7): 735-742.LÜ Yang, LIAO Yuhe, WANG Baoxiang, et al. Quantitative diagnosis method for rolling bearing faults based on VMD and CNN [J]. China Sciencepaper, 2020, 15(7): 735-742.[19] 姜洪开, 邵海东, 李兴球. 基于深度学习的飞行器智能故障诊断方法 [J]. 机械工程学报, 2019, 55(7): 27-34.JIANG Hongkai, SHAO Haidong, LI Xingqiu. Deep learning theory with application in intelligent fault diagnosis of aircraft [J]. Journal of Mechanical Engineering, 2019, 55(7): 27-34.[20] 段艳杰, 吕宜生, 张杰, 等. 深度学习在控制领域的研究现状与展望 [J]. 自动化学报, 2016, 42(5): 643-654.DUAN Yanjie, LÜ Yisheng, ZHANG Jie, et al. Deep learning for control: the state of the art and prospects [J]. Acta Automatica Sinica, 2016, 42(5): 643-654.[21] CHEN Maoqi, ZHOU Ping. A novel framework based on FastICA for high density surface EMG decomposition [J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2016, 24(1): 117-127.[22] ZHENG Yang, HU Xiaogang. Real-time isometric finger extension force estimation based on motor unit discharge information [J]. Journal of Neural Engineering, 2019, 16(6): 066006.[23] FUGLEVAND A J, WINTER D A, PATLA A E. Models of recruitment and rate coding organization in motor-unit pools [J]. Journal of Neurophysiology, 1993, 70(6): 2470-2488.[24] ZHENG Yang, XU Guanghua, LI Yixin, et al. Improved online decomposition of non-stationary electromyogram via signal enhancement using a neuron resonance model: a simulation study [J]. Journal of Neural Engineering, 2022, 19(2): 026030.[25] XU Feng, ZHENG Yang, HU Xiaogang. Real-time finger force prediction via parallel convolutional neural networks: a preliminary study [C]//42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society. Piscataway, NJ, USA: IEEE, 2020: 3126-3129.

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

脑-运动单元功能耦合估计方法

深立井井壁图像的卷积神经网络去噪方法

采用深度迁移学习与自适应加权的滚动轴承故障诊断

电动车辆间接热系统快速除湿响应迟滞机理及优化控制策略

电子级超纯氮深冷空分流程节能优化研究