Research Progress in Surface Electromyography Joint Continuous Motion Estimation

doi:10.3778/j.issn.1002-8331.2312-0288

Abstract

Abstract: Surface electromyography (sEMG) is a non-invasive bioelectrical signal used to capture changes in muscle activity during exercise. Because it is closely related to sports, it is widely used in the research and development process of intelligent assisted rehabilitation equipment to provide support and assistance for rehabilitation patients. Rehabilitation training involves complex three-dimensional motion, and sEMG-based joint continuous motion estimation is a method to estimate joint angle or moment by analyzing sEMG during exercise, which can effectively alleviate the problem of insufficient adaptability between rehabilitation machine and human body, providing safer assistance and significantly improving the rehabilitation effect. This paper firstly introduces the current status of joint continuous motion estimation, and then classifies the existing sEMG joint continuous motion estimation models into biomechanics-based musculoskeletal model and machine learning-based regression model according to different research methods, and summarizes and analyzes the relevant models respectively. In addition, the paper also analyzes the current challenges and looks forward to the future research trends.

Key words: surface electromyography signaling (sEMG), continuous movement of joints, musculoskeletal models, regression models

摘要： 表面肌电信号（surface electromyography, sEMG）是一种非侵入式的生物电信号，用于捕捉运动过程中肌肉活动的变化。因其与运动密切相关，所以广泛应用于智能辅助康复设备的研发过程中，为康复者提供支持和帮助。康复训练涉及到复杂的立体运动，而基于sEMG的关节连续运动估计是一种通过分析运动期间的sEMG来估计关节角度或力矩的方法，它能够有效缓解康复机器与人体之间的适应性不足的问题，并提供更安全的辅助，从而显著改善康复效果。介绍了关节连续运动估计的现状，然后根据不同的研究方法将现有的sEMG关节连续运动估计模型分为基于生物力学的肌肉骨骼模型和基于机器学习的回归模型，分别对相关模型进行总结分析；分析了当前所面临的挑战，并展望了未来的研究趋势。

关键词: 表面肌电信号（sEMG）, 关节连续运动, 肌肉骨骼模型, 回归模型

MA Yifan, WEI Dejian, FENG Yanyan, YU fengfan, LI Zhenjiang. Research Progress in Surface Electromyography Joint Continuous Motion Estimation[J]. Computer Engineering and Applications, 2024, 60(14): 26-36.

马一凡, 魏德健, 冯妍妍, 于丰帆, 李振江. 表面肌电关节连续运动估计的研究进展[J]. 计算机工程与应用, 2024, 60(14): 26-36.

References

[1] AI Q, LIU Z, MENG W, et al. Machine learning in robot assisted upper limb rehabilitation: a focused review[J]. IEEE Transactions on Cognitive and Developmental Systems, 2021, 15(4): 2053-2063.
[2] SHEN S, GU K, CHEN X R, et al. Movements classification of multi-channel sEMG based on CNN and stacking ensemble learning[J]. IEEE Access, 2019, 7: 137489-137500.
[3] MENG Z, KANG J. Continuous joint velocity estimation using CNN-based deep learning for multi-DoF prosthetic wrist for activities of daily living[J]. Frontiers in Neurorobotics, 2023, 17.
[4] LI H B, GUAN X R, Li Z, et al. Estimation of knee joint angle from surface EMG using multiple kernels relevance vector regression[J]. Sensors, 2023, 23(10): 4934.
[5] HAKONEN M, PIITULAINEN H, VISALA A. Current state of digital signal processing in myoelectric interfaces and related applications[J]. Biomedical Signal Processing and Control, 2015, 18: 334-359.
[6] BI L, FAN X A, LIU Y. EEG-based brain-controlled mobile robots: a survey[J]. IEEE Transactions on Human-Machine Systems, 2013, 43(2): 161-176.
[7] USAKLI A B, GURKAN S, ALOISE F, et al. On the use of electrooculogram for efficient human computer interfaces[J]. Computational Intelligence and Neuroscience, 2010, 135629: 1-5.
[8] ZHENG K, LIU S, YANG J, et al. sEMG-based continuous hand action prediction by using key state transition and model pruning[J]. Sensors, 2022, 22(24): 9949.
[9] SCHULTE R V, ZONDAG M, BUURKE J H, et al. Multi-day emg-based knee joint torque estimation using hybrid neuromusculoskeletal modelling and convolutional neural networks[J]. Frontiers in Robotics and AI, 2022, 9: 869476.
[10] BAO T, ZAIDI S A R, XIE S, et al. Inter-subject domain adaptation for CNN-based wrist kinematics estimation using sEMG[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021, 29: 1068-1078.
[11] LI J, LI K, ZHANG J, et al. Continuous motion estimation of knee joint based on a parameter self-updating mechanism model[J]. Bioengineering, 2023, 10(9): 1028.
[12] MOKRI C, BAMDAD M, ABOLGHASEMI V. Muscle force estimation from lower limb EMG signals using novel optimised machine learning techniques[J]. Medical & Biological Engineering & Computing, 2022, 60(3): 683-699.
[13] BI L, GUAN C. A review on EMG-based motor intention prediction of continuous human upper limb motion for human-robot collaboration[J]. Biomedical Signal Processing and Control, 2019, 51: 113-127.
[14] 曹梦琳, 陈宇豪, 王珏, 等. 基于表面肌电图的人体运动意图识别研究进展[J]. 中国康复理论与实践, 2021, 27(5): 595-603.
CAO M L, CHEN Y H, WANG J, et al. Advance in human motion intention recognition based on surface electromyography (review)[J]. Chinese Journal of Rehabilitation Theory and Practice, 2021, 27(5): 595-603.
[15] 陆思源, 陆志海, 王水花, 等. 极限学习机综述[J]. 测控技术, 2018, 37(10): 3-9.
LU S Y, LU Z H, WANG S H, et al. Review of extreme learning machine[J]. Measurement and Control Technology, 2018, 37(10): 3-9.
[16] ZOU J, HAN Y, SO S S. Overview of artificial neural networks[J]. Artificial Neural Networks: Methods and Applications, 2008, 458: 15-23.
[17] HECHT-NIELSEN R. Theory of the backpropagation neural network[M]//Neural networks for perception. [S.l.]: Academic Press, 1992: 65-93.
[18] SAKAMOTO S, HUTABARAT Y, OWAKI D, et al. Ground reaction force and moment estimation through EMG sensing using long short-term memory network during posture coordination[J]. Cyborg and Bionic Systems, 2023, 4: 0016.
[19] MEDSKER L R, JAIN L. Recurrent neural networks[J]. Design and Applications, 2001, 5(64/67): 2.
[20] LEA C, FLYNN M D, VIDAL R, et al. Temporal convolutional networks for action segmentation and detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 156-165.
[21] MUNDT M, JOHNSON W R, POTTHAST W, et al. A comparison of three neural network approaches for estimating joint angles and moments from inertial measurement units[J]. Sensors, 2021, 21(13): 4535.
[22] 王志红. 基于视觉手势识别的机械手操控系统的研究[D]. 天津: 天津工业大学, 2017.
WANG Z H. Research on robot manipulation system based on visual gesture recognition[D]. Tianjin: Tianjin University of Technology, 2017.
[23] 宋鹰翔. 基于sEMG的人体下肢关节角度连续运动估计[D]. 杭州: 杭州电子科技大学, 2020.
SONG Y X. Continuous motion estimation of lower limb joint angle based on sEMG[D]. Hangzhou: Hangzhou University of Electronic Science and Technology, 2020.
[24] ZHANG S, LU J, HUO W, et al. Estimation of knee joint movement using single-channel sEMG signals with a feature-guided convolutional neural network[J]. Frontiers in Neurorobotics, 2022, 16: 978014.
[25] 陈江城, 张小栋, 李睿, 等. 利用sEMG的下肢动态关节力矩预测模型[J]. 西安交通大学学报, 2015, 49(12): 26-33.
CHEN J C, ZHANG X D, LI R, et al. Prediction model for dynamic joint torque of lower limb with surface EMG[J]. Journal of Xi’an Jiaotong University, 2015, 49(12): 26-33.
[26] 杜妍辰, 孙洁, 汪晓铭, 等. 基于肌电信号的人体下肢运动意图映射研究进展[J]. 上海理工大学学报, 2023, 45(2): 128-136.
DU Y C, SUN J, WANG X M, et al. Advances in human lower limb motion intention mapping based on electromyography[J]. Journal of University of Shanghai for Science and Technology, 2023, 45(2): 128-136.
[27] DING Q C, XIONG A B, ZHAO X G, et al. A novel EMG-driven state space model for the estimation of continuous joint movements[C]//Proceedings of the 2011 IEEE International Conference on Systems, Man, and Cybernetics, 2011: 2891-2897.
[28] CHEN J, ZHANG X, GU L, et al. Estimating muscle forces and knee joint torque using surface electromyography: a musculoskeletal biomechanical model[J]. Journal of Mechanics in Medicine and Biology, 2017, 17(4): 1750069.
[29] HAN J, DING Q, XIONG A, et al. A state-space EMG model for the estimation of continuous joint movements[J]. IEEE Transactions on Industrial Electronics, 2015, 62(7): 4267-4275.
[30] XI X, JIANG W, HUA X, et al. Simultaneous and continuous estimation of joint angles based on surface electromyography state-space model[J]. IEEE Sensors Journal, 2021, 21(6): 8089-8099.
[31] ZHAO Y, LI Z, ZHANG Z, et al. An EMG-driven musculoskeletal model for estimation of wrist kinematics using mirrored bilateral movement[J]. Biomedical Signal Processing and Control, 2023, 81: 104480.
[32] BUONGIORNO D, BARSOTTI M, BARONE F, et al. A linear approach to optimize an EMG-driven neuromusculoskeletal model for movement intention detection in myo-control: a case study on shoulder and elbow joints[J]. Frontiers in Neurorobotics, 2018, 12: 74.
[33] KIM Y, STAPORNCHAISIT S, KAMBARA H, et al. Muscle synergy and musculoskeletal model-based continuous multi-dimensional estimation of wrist and hand motions[J]. Journal of Healthcare Engineering, 2020(1): 5451219.
[34] LIANG F Y, GAO F, LIAO W H. Synergy-based knee angle estimation using kinematics of thigh[J]. Gait & Posture, 2021, 89: 25-30.
[35] 张亚男. 基于肌肉协同分析的上肢多关节同步连续运动估计研究[D]. 武汉: 武汉理工大学, 2018.
ZHANG Y N. Research on simultaneous and continuous motion estimation for multiple joints of upper limb based on muscle synergy analysis[D]. Wuhan: Wuhan University of Technology, 2018.
[36] HE Z, QIN Z, KOIKE Y. Continuous estimation of finger and wrist joint angles using a muscle synergy based musculoskeletal model[J]. Applied Sciences, 2022, 12(8): 3772.
[37] PENG L, HOU Z G, KASABOV N, et al. sEMG-based torque estimation for robot-assisted lower limb rehabilitation[C]//Proceedings of the 2015 International Joint Conference on Neural Networks (IJCNN), 2015: 1-5.
[38] ATOUFI B, KAMAVUAKO E N, HUDGINS B, et al. Toward proportional control of myoelectric prostheses with muscle synergies[J]. Journal of Medical and Biological Engineering, 2014, 34(5): 475-481.
[39] LOCONSOLE C, DETTORI S, FRISOLI A, et al. An EMG-based approach for on-line predicted torque control in robotic-assisted rehabilitation[C]//Proceedings of the 2014 IEEE Haptics Symposium (HAPTICS), 2014: 181-186.
[40] DENG Y, GAO F, CHEN H. Angle estimation for knee joint movement based on PCA-RELM algorithm[J]. Symmetry, 2020, 12(1): 130.
[41] ZHANG Q, LIU R, CHEN W, et al. Simultaneous and continuous estimation of shoulder and elbow kinematics from surface EMG signals[J]. Frontiers in Neuroscience, 2017, 11: 253504.
[42] ZHANG Q, ZHENG C, XIONG C. EMG-based estimation of shoulder and elbow joint angles for intuitive myoelectric control[C]//Proceedings of the 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), 2015: 1912-1916.
[43] SONG Q, MA X, LIU Y. Continuous online prediction of lower limb joints angles based on sEMG signals by deep learning approach[J]. Computers in Biology and Medicine, 2023, 163: 107124.
[44] HUANG Y, CHEN K, ZHANG X, et al. Motion estimation of elbow joint from sEMG using continuous wavelet transform and back propagation neural networks[J]. Biomedical Signal Processing and Control, 2021, 68: 102657..
[45] 王豪. 基于表面肌电信号的人体下肢运动估计及识别研究[D]. 天津: 河北工业大学, 2022.
WANG H. Estimation and recognition of human lower limb motion based on surface EMG[D]. Tianjin: Hebei University of Technology, 2022.
[46] YOKOYAMA M, KOYAMA R, YANAGISAWA M. An evaluation of hand-force prediction using artificial neural-network regression models of surface EMG signals for handwear devices[J]. Journal of Sensors, 2017, 3980906: 1-12.
[47] 杨纳川. 基于sEMG的关节力矩估计方法与肘关节康复外骨骼系统研究[D]. 广州: 华南理工大学, 2021.
YANG N C. Research on joint torque estimation method and elbow rehabilitation exoskeleton system based on surface electromyography[D]. Guangzhou: South China University of Technology, 2021.
[48] 李素姣, 朱越, 吴坤, 等. 基于多模态信息融合的肘关节连续运动估计[J]. 医用生物力学, 2023, 38(2): 324-330.
LI S J, ZHU Y, WU K, et al. Continuous motion estimation of elbow joint based on multi-modal information fusion[J]. Journal of Medical Biomechanics, 2023, 38(2): 324-330.
[49] WANG J, WANG L, XI X, et al. Estimation and correlation analysis of lower limb joint angles based on surface electromyography[J]. Electronics, 2020, 9(4): 556.
[50] SHI Y J, GAO X S, LUO D G, et al. Prediction of lower limb joint motion based on surface EMG signal and extreme learning machine[J]. Ordnance Industry Automation, 2021, 11(40): 11.
[51] HUANG G B, ZHOU H, DING X, et al. Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2011, 42(2): 513-529.
[52] 陈洋, 王士同. 多样性正则化极限学习机的集成方法 [J]. 计算机科学与探索, 2022, 16(8): 1819-1828.
CHEN Y, WANG S T. Ensemble method of diverse regularized extreme learning machines[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16 (8): 1819-1828.
[53] XIE H, LI G, ZHAO X, et al. Prediction of limb joint angles based on multi-source signals by GS-GRNN for exoskeleton wearer[J]. Sensors, 2020, 20(4): 1104.
[54] ZHAO H, QIU Z, PENG D, et al. Prediction of joint angles based on human lower limb surface electromyography[J]. Sensors, 2023, 23(12): 5404.
[55] WU H, HUANG Q, WANG D, et al. A CNN-SVM combined model for pattern recognition of knee motion using mechanomyography signals[J]. Journal of Electromyography and Kinesiology, 2018, 42: 136-142.
[56] 张瑞轩, 郭媛, 王瑞雪, 等. 表面肌电信号驱动手部运动的机器学习表征与识别[J]. 医用生物力学, 2021, 36(S1): 353.
ZHANG R X, GUO Y, WANG R X, et al. Machine learning representation and recognition of surface EMG signal-driven hand motions[J]. Medical Biomechanics, 2021, 36(S1): 353.
[57]SHERSTINSKY A. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network[J]. Physica D: Nonlinear Phenomena, 2020, 404: 132306.
[58]HUANG Y, HE Z, LIU Y, et al. Real-time intended knee joint motion prediction by deep-recurrent neural networks[J]. IEEE Sensors Journal, 2019, 19(23): 11503-11509.
[59]黄吕超, 杨黄屯, 崔明涛, 等. 基于自学习的LSTM网络短路电流零点预测方法[J]. 电工电能新技术, 2024, 43(2): 78-86.
HUANG L C, YANG H T, CUI M T, et al. A method for predicting short circuit current zeros in LSTM networks based on self-learning[J]. Advanced Technology of Electrical Engineering and Energy, 2024, 43(2): 78-86.
[60] TANG G, SHENG J, WANG D, et al. Continuous estimation of human upper limb joint angles by using PSO-LSTM model[J]. IEEE Access, 2020, 9: 17986-17997.
[61] ZHAO D, MA Y, MENG J, et al. MCR-ALS-based muscle synergy extraction method combined with LSTM neural network for motion intention detection[J]. Frontiers in Neurorobotics, 2023, 17: 1174710.
[62] AVIAN C, PRAKOSA S W, FAISAL M, et al. Estimating finger joint angles on surface EMG using manifold learning and long short-term memory with attention mechanism[J]. Biomedical Signal Processing and Control, 2022, 71: 103099.
[63] HAJIAN G, MORIN E. Deep multi-scale fusion of convolutional neural networks for EMG-based movement estimation[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 486-495.
[64] SUN N, CAO M, CHEN Y, et al. Continuous estimation of human knee joint angles by fusing kinematic and myoelectric signals[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2022, 30: 2446-2455.
[65] CHEN Z, WANG H, CHEN H, et al. Continuous motion finger joint angle estimation utilizing hybrid sEMG-FMG modality driven transformer-based deep learning model[J]. Biomedical Signal Processing and Control, 2023, 85: 105030.
[66] CHAI Y, LIU K, LI C, et al. A novel method based on long short term memory network and discrete-time zeroing neural algorithm for upper-limb continuous estimation using sEMG signals[J]. Biomedical Signal Processing and Control, 2021, 67: 102416.
[67] LIU X, WANG J, LIANG T, et al. SE-TCN network for continuous estimation of upper limb joint angles[J]. Mathematical Biosciences and Engineering, 2022, 20(2): 3237-3260.