From Continuous sEMG Signals to Discrete Muscle State Tokens: A Robust and Interpretable Representation Framework
School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications（北京邮电大学计算机学院（国家示范性软件工程学院））；Key Laboratory of Trustworthy Distributed Computing and Service (BUPT), Ministry of Education（教育部可信分布式计算与服务重点实验室（北京邮电大学））；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Institute for Precision Medicine, Tsinghua University（清华大学精准医学研究所）；College of AI, Tsinghua University（清华大学人工智能学院）；Research Academy of Grand Health, Ningbo University（宁波大学大健康研究院）；School of Information Technology and Artificial Intelligence, Zhejiang University of Finance and Economics（浙江财经大学信息技术与人工智能学院）
Yuepeng Chen, Kaili Zheng, Ji Wu, Zhuangzhuang Li, Ye Ma, Dongwei Liu, Chenyi Guo, Xiangling Fu
Surface electromyography (sEMG) signals exhibit substantial inter-subject variability and are highly susceptible to noise, posing challenges for robust and interpretable decoding. To address these limitations, we propose a discrete representation of sEMG signals based on a physiology-informed tokenization framework. The method employs a sliding window aligned with the minimal muscle contraction cycle to isolate individual muscle activation events. From each window, ten time-frequency features, including root mean square (RMS) and median frequency (MDF), are extracted, and K-means clustering is applied to group segments into representative muscle-state tokens. We also introduce a large-scale benchmark dataset, ActionEMG-43, comprising 43 diverse actions and sEMG recordings from 16 major muscle groups across the body. Based on this dataset, we conduct extensive evaluations to assess the inter-subject consistency, representation capacity, and interpretability of the proposed sEMG tokens. Our results show that the token representation exhibits high inter-subject consistency (Cohen's Kappa = 0.82+-0.09), indicating that the learned tokens capture consistent and subject-independent muscle activation patterns. In action recognition tasks, models using sEMG tokens achieve Top-1 accuracies of 75.5% with ViT and 67.9% with SVM, outperforming raw-signal baselines (72.8% and 64.4%, respectively), despite a 96% reduction in input dimensionality. In movement quality assessment, the tokens intuitively reveal patterns of muscle underactivation and compensatory activation, offering interpretable insights into neuromuscular control. Together, these findings highlight the effectiveness of tokenized sEMG representations as a compact, generalizable, and physiologically meaningful feature space for applications in rehabilitation, human-machine interaction, and motor function analysis.
Physics-informed Deep Learning for Muscle Force Prediction with Unlabeled sEMG Signals
School of Electronic and Electrical Engineering, University of Leeds（利兹大学电子与电气工程学院）；Centre for Wireless Innovation, Queen’s University Belfast（贝尔法斯特女王大学无线创新中心）；School of Mechanical Engineering, Tianjin University（天津大学机械工程学院）；International Institute for Innovative Design and Intelligent Manufacturing of Tianjin University in Zhejiang（天津大学浙江创新设计与智能制造国际研究院）；Rex Bionics Ltd（Rex Bionics有限公司）
针对肌肉力预测依赖标签且物理模型计算慢的问题，提出将 Hill 前向动力学作为损失嵌入 FNN 的物理信息深度学习方法，利用无标签 sEMG 实现准确的肌肉力预测与个性化肌肉-肌腱参数识别。
Improving the clinical utility of lower-limb surface electromyography (sEMG) by quantifying and correcting for location changes in inter-session recordings
School of Biomedical Engineering, University of British Columbia（不列颠哥伦比亚大学生物医学工程学院）；Centre for Aging SMART, University of British Columbia（不列颠哥伦比亚大学老龄化SMART中心）；Focal Lines Technologies（Focal Lines科技有限公司）
SDEMG: Score-based Diffusion Model for Surface Electromyographic Signal Denoising
National Yang Ming Chiao Tung University（国立阳明交通大学）；National Taiwan University（国立台湾大学）；National Taipei University of Technology（国立台北科技大学）；National Taiwan University of Science and Technology（国立台湾科技大学）；Academia Sinica（中央研究院）
TEMGNet: Deep Transformer-based Decoding of Upperlimb sEMG for Hand Gestures Recognition
Concordia University（康考迪亚大学）；Concordia Institute for Information System Engineering (CIISE)（康考迪亚大学信息系统工程研究所（CIISE））；Electrical and Computer Engineering (ECE), Concordia University（康考迪亚大学电气与计算机工程系（ECE））；Department of Bioengineering, Imperial College London（帝国理工学院生物工程系）；Electrical and Computer Engineering and Mechanical and Aerospace Engineering, New York University (NYU)（纽约大学（NYU）电气与计算机工程及机械与航空航天工程系）；New York University (NYU)（纽约大学（NYU））；Imperial College London（帝国理工学院）
TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancement
National Taiwan University（台湾大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；National Taiwan University of Science and Technology（台湾科技大学）；Academia Sinica（中央研究院）；Chung Yuan Christian University（中原大学）
MSEMG: Surface Electromyography Denoising with a Mamba-based Efficient Network
National Yang Ming Chiao Tung University（国立阳明交通大学）；National Taiwan University（国立台湾大学）；University of Palermo（巴勒莫大学）；Academic Sinica（中央研究院）；Research Center for Information Technology Innovation（资讯科技创新研究中心）
A Non-Intrusive Neural Quality Assessment Model for Surface Electromyography Signals
National Yang Ming Chiao Tung University（国立阳明交通大学）；National Taiwan University（国立台湾大学）；University of Massachusetts（马萨诸塞大学）；National Institute of Information and Communications Technology（信息通信研究机构）；Academia Sinica（中央研究院）
