基于深度学习的手腕多运动模式分类模型
Classification Model for Hand and Wrist Multiple-Mode Pattern Based on Deep Learning
DOI: 10.12677/MOS.2023.123271, PDF,    国家自然科学基金支持
作者: 张 越, 唐源敏：上海理工大学康复工程与技术研究所，上海；上海康复器械工程技术研究中心，上海；李素姣*：上海理工大学康复工程与技术研究所，上海；上海康复器械工程技术研究中心，上海；民政部神经功能信息与康复工程重点实验室，上海
关键词: 分类模型；一维卷积神经网络；循环神经网络；表面肌电信号；Classification Model； 1D-CNN； RNN； Surface EMG
摘要: 基于sEMG信号模式识别的假肢控制方法是目前重要的假肢控制方法，为了解决分类识别率和时间延迟无法兼顾的问题，本文结合CNN与RNN的优势，提出一种适用于sEMG的基于一维卷积循环网络(1D-CNN-RNN)的手腕动作分类模型，并对其实时识别性能进行分析。本文提出的1D-CNN-RNN分类模型对设定的多种手和腕部动作模式有较好的分类效果，并且平均时延在人体无明显延迟感的时间范围内，有望为肌电假肢手提供一种有效的控制方法。
Abstract: The prosthesis control method based on sEMG signal pattern recognition is an important prosthesis control method at present. A classification model of hand and wrist movements based on one- di-mensional convolutional neural network and recurrent neural network (1D-CNN-RNN) was pro-posed, in order to solve the problem that classification recognition rate and time delay cannot be taken into account. This model combined the advantages of CNN and RNN. Its real time recognition performance was analyzed. The proposed 1D-CNN-RNN classification model has a good classification effect on various hand and wrist motion patterns. The average delay is within the time range that the human body has no obvious sense of delay. It is expected to provide an effective control method for myoelectric prosthetic hand.
文章引用：张越, 唐源敏, 李素姣. 基于深度学习的手腕多运动模式分类模型[J]. 建模与仿真, 2023, 12(3): 2940-2949. https://doi.org/10.12677/MOS.2023.123271

参考文献

[1] Scheme, E. and Eenglehart, K. (2011) Electromyogram Pattern Recognition for Control of Powered Upper-Limb Prostheses: State of the Art and Challenges for Clinical Use. Journal of Rehabilitation Research & Development, 48, 643-659. [Google Scholar] [CrossRef] 
[2] Manfredo, A., Matteo, C. and Henning, M. (2016) Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Pros-thetic Hands. Frontiers in Neurorobotics, 10, Article 9. [Google Scholar] [CrossRef] [PubMed]
[3] Geng, W., Du, Y., Jin, W., et al. (2016) Gesture Recognition by Instantaneous Surface EMG Images. Scientific Reports, 6, Article No. 36571. [Google Scholar] [CrossRef] [PubMed]
[4] Zhai, X., Beth, J., Chan, R.H.M. and Tin, C. (2017) Self-Recalibrating Surface EMG Pattern Recognition for Neuroprosthesis Control Based on Convolutional Neural Network. Frontiers in Neuroscience, 11, Article 379. [Google Scholar] [CrossRef] [PubMed]
[5] Wei, W., Wong, Y., Du, Y., et al. (2017) A Multi-Stream Convolutional Neural Network for sEMG-Based Gesture Recognition in Muscle-Computer Interface. Pattern Recognition Letters, 119, 131-138. [Google Scholar] [CrossRef] 
[6] Chen, H., Zhang, Y., Li, G., Fang, Y. and Liu, H. (2020) Surface Elec-tromyography Feature Extraction via Convolutional Neural Network. International Journal of Machine Learning and Cybernet-ics, 11, 185-196. [Google Scholar] [CrossRef] 
[7] Hüsken, M. and Stagge, P. (2003) Recurrent Neural Networks for Time Series Classification. Neurocomputing, 50, 223-235. [Google Scholar] [CrossRef] 
[8] Barron, O., Raison, M., Gaudet, G. and Achiche, S. (2020) Recurrent Neural Network for Electromyographic Gesture Recognition in Transhumeral Amputees. Applied Soft Computing, 96, Article ID: 106616. [Google Scholar] [CrossRef] 
[9] Teban, T.-A., Precup, R.-E., Voisan, E.-I., de Oliveira, T.E.A. and Petriu, E.M. (2016) Recurrent Dynamic Neural Network Model for Myoelectric-Based Control of a Prosthetic Hand. 2016 Annual IEEE Systems Conference (SysCon), Orlando, 18-21 April 2016, 1-6. [Google Scholar] [CrossRef] 
[10] Koch, P., Phan, H., Maass, M., Katzberg, F. and Mertins, A. (2018) Recurrent Neural Network Based Early Prediction of Future Hand Movements. 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Honolulu, 18-21 July 2018, 4710-4713. [Google Scholar] [CrossRef] 
[11] Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780. [Google Scholar] [CrossRef] [PubMed]
[12] Quivira, F., Koike-Akino, T., Wang, Y. and Erdogmus, D. (2018) Translating sEMG Signals to Continuous Hand Poses using Recurrent Neural Networks. 2018 IEEE EMBS International Con-ference on Biomedical & Health Informatics (BHI), Las Vegas, 4-7 March 2018, 166-169. [Google Scholar] [CrossRef] 
[13] Hu, Y., Wong, Y., Wei, W., et al. (2018) A Novel Attention-Based Hy-brid CNN-RNN Architecture for sEMG-Based Gesture Recognition. PLOS ONE, 13, e0206049. [Google Scholar] [CrossRef] [PubMed]
[14] Xia, P., Hu, J. and Peng, Y. (2018) EMG-Based Estimation of Limb Movement Using Deep Learning with Recurrent Convolutional Neural Networks. Artificial Organs, 42, E67-E77. [Google Scholar] [CrossRef] [PubMed]
[15] Jiang, Y.J., Song, L., Zhang, J.M., et al. (2022) Multi-Category Gesture Recogni-tion Modeling Based on sEMG and IMU Signals. Sensors, 22, Article No. 5855. [Google Scholar] [CrossRef] [PubMed]
[16] Chen, Y., Dai, C. and Chen, W. (2020) Cross-Comparison of EMG-to-Force Methods for Multi-DoF Finger Force Prediction Using One-DoF Training. IEEE Access, 8, 13958-13968. [Google Scholar] [CrossRef] 
[17] Hakkani-Tür, D., Tur, G., et al. (2016) Multi-Domain Joint Semantic Frame Parsing Using Bi-directional RNN-LSTM. The 17th Annual Meeting of the International Speech Commu-nication Association (INTERSPEECH 2016), San Francisco, 8-12 September 2016, 715-719. [Google Scholar] [CrossRef] 
[18] Greff, K., Srivastava, R.K., Koutník, J., Steunebrink, B.R. and Schmidhuber, J. (2016) LSTM: A Search Space Odyssey. IEEE Transactions on Neural Networks & Learning Systems, 28, 2222-2232. [Google Scholar] [CrossRef] 
[19] Smith, L.H., Hargrove, L.J., Lock, B.A. and Kuiken, T.A. (2011) Determining the Optimal Window Length for Pattern Recognition-Based Myoelectric Control: Balancing the Competing Effects of Classification Error and Controller Delay. IEEE Transactions on Neural Systems & Rehabilitation Engineering, 19, 186-192. [Google Scholar] [CrossRef] 

为你推荐