[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86123-en":3,"doc-seo-86123-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86123,962075114765,"Quinn","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Efficient and Robust Spiking Neural Networks for sEMG-Based Muscle Fatigue Detection","Surface electromyography (sEMG) enables essential muscle fatigue monitoring for sports, rehabilitation, and wearable health systems, where accurate and timely detection helps prevent injuries, improve performance, and protect user safety. Existing deep models often remain impractical due to high computation and data demands. An energy-efficient spiking neural network framework is proposed using sparse event-driven temporal modeling, plus a quantization-compatible training scheme (SDH) to enhance robustness under noise. Experiments on two public sEMG datasets show quantized SNNs match or exceed strong baselines and reduce estimated energy consumption by up to 201.77×.","Efficient and Robust Spiking Neural Networks for sEMG-Based Muscle Fatigue Detection  \nKaiwen Tang* , Jiaqi Dong* , Zhanglu Yan†, and Weng-Fai Wong  \nUniversity of Singapore  \nSingapore, Singapore  \narXiv :2607 . 1 1065v 1 [ cs .NE] 13 Jul 2026  \nAbstract—Detecting muscle fatigue via surface electromyography (sEMG) is essential for applications in sports, rehabilitation, and wearable health monitoring. Accurate and timely detection of fatigue is crucial for preventing injuries, optimizing physical performance, and ensuring user safety during prolonged activity. However, existing deep learning models are often unsuitable for this task due to their high computational cost and dependence on large-scale data. In this work, we propose an energy-efficient framework for muscle fatigue detection based on Spiking Neural Networks (SNNs), which exploit sparse, event-driven computation and temporal modeling. We further introduce a quantizationcompatible training scheme (SDH) that combines multiple regularization terms to improve robustness under noisy conditions. Evaluated on two public sEMG datasets against a broad set of baselines and under seven noise conditions including physically motivated perturbations, our quantized SNNs match or exceed strong baselines while remaining more stable under diverse noise and reducing estimated energy consumption by up to 201.77×. These results demonstrate the framework’s strong potential for real-time deployment in low-power wearable systems.  \nIndex Terms—Spiking Neural Networks, Muscle Fatigue Detection, Edge Computing, Surface Electromyography  \nI. INTRODUCTION  \nMuscle fatigue detection is essential across domains such as sports, rehabilitation, and occupational safety [1]–[3] . In competitive sports, timely identification of fatigue allows coaches to optimize training loads and prevent injuries; in laborintensive industries, it helps managers mitigate safety risks by monitoring workers’ physical conditions. Surface electromyography (sEMG), a non-invasive technique for recording muscle electrical activity [4], provides a promising signal source for fatigue assessment. However, sEMG signals are often noisy, subject-dependent, and exhibit complex temporal dynamics, posing challenges for reliable real-time analysis in practical environments, particularly when the system is expected to run continuously on power-constrained, wearable devices.  \nIn real-world applications such as sports training or workplace monitoring, muscle fatigue detection must operate reliably on lightweight wearable devices under unconstrained, noisy conditions [5], [6] . To preserve user privacy and enable low-latency feedback, models must process data locally rather than relying on cloud-based computation [7] . This imposes three core requirements on practical models: (1)  \nhigh predictive accuracy under limited training data; (2) low * Kaiwen Tang and Jiaqi Dong contributed equally to this work.  \n†Corresponding author: Zhanglu Yan ([zhangluyan@comp.nus.edu.sg](zhangluyan@comp.nus.edu.sg)) .  \ncomputational overhead suitable for edge devices; and (3) strong robustness to signal noise induced by motion artifacts or environmental factors.  \nPrior work in fatigue detection primarily leverages either conventional machine learning (ML) models or deep neural networks. Conventional ML methods such as SVM, k-NN, or ensemble methods [8]–[10] often have limited ability to capture the temporal dynamics inherent in fatigue progression. While deep models such as LSTM [11] and attentionbased methods [12] can improve predictive performance, they usually come with higher latency and energy cost, which limits their use on resource-constrained wearable platforms. Moreover, due to the non-invasive nature of sEMG acquisition, the signals remain highly susceptible to noise [13], and few existing methods explicitly address robustness to motioninduced artifacts [14], [15] . As a result, reliable real-time ondevice deployment remains challenging.  \nS","cbCaicaku3gJU1zo","https://ap.wps.com/l/cbCaicaku3gJU1zo","pdf",1355715,5,1,9,"English","en",105,"# Introduction\n## Muscle fatigue detection requirements\n## Prior approaches and limitations\n## Why spiking neural networks\n# Proposed method\n## Structure-preserving conversion from ANN to SNN\n## SDH robust quantization-compatible training\n## Weight quantization for deployment\n# Experiments and results\n## Datasets and baselines\n## Accuracy metrics\n## Noise robustness evaluation","[{\"question\":\"Why is muscle fatigue detection important for real-world systems?\",\"answer\":\"It supports injury prevention, training load optimization, and safer monitoring during prolonged or labor-intensive activities.\"},{\"question\":\"What makes standard deep learning approaches difficult to use for sEMG fatigue detection?\",\"answer\":\"High computational cost and reliance on large-scale training data, combined with latency and energy constraints on wearable edge devices.\"},{\"question\":\"How does the proposed framework improve efficiency and robustness?\",\"answer\":\"It uses spiking neural networks with sparse event-driven temporal modeling for energy efficiency, and introduces the SDH training scheme with multiple quantization-related regularization terms to handle noisy, variability-prone sEMG signals.\"}]",1784208661,23,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"efficient-and-robust-spiking-neural-networks-for-semg-based-muscle-fatigue-detection","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/efficient-and-robust-spiking-neural-networks-for-semg-based-muscle-fatigue-detection/86123/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-27","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is muscle fatigue detection important for real-world systems?","Question",{"text":76,"@type":77},"It supports injury prevention, training load optimization, and safer monitoring during prolonged or labor-intensive activities.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What makes standard deep learning approaches difficult to use for sEMG fatigue detection?",{"text":81,"@type":77},"High computational cost and reliance on large-scale training data, combined with latency and energy constraints on wearable edge devices.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the proposed framework improve efficiency and robustness?",{"text":85,"@type":77},"It uses spiking neural networks with sparse event-driven temporal modeling for energy efficiency, and introduces the SDH training scheme with multiple quantization-related regularization terms to handle noisy, variability-prone sEMG signals.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":20,"slug":137},19,"General","general"]