{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:58:35Z","timestamp":1791395915593,"version":"4.3.3"},"reference-count":44,"publisher":"IOP Publishing","issue":"5","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Joint Funds for the Innovation of Science and Technology in Fujian Province","award":["2023Y9280"],"award-info":[{"award-number":["2023Y9280"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62471207"],"award-info":[{"award-number":["62471207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"crossref","award":["2024J02029"],"award-info":[{"award-number":["2024J02029"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"crossref","award":["202508350016"],"award-info":[{"award-number":["202508350016"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Open Project of Fujian Key Laboratory of Medical Big Data Engineering","award":["KLKF202301"],"award-info":[{"award-number":["KLKF202301"]}]},{"name":"Open Foundation of the Engineering Research Center of Big Data Application in Private Health Medicine of Fujian Province University","award":["MKF202202"],"award-info":[{"award-number":["MKF202202"]}]},{"name":"Talent Introduction Projects (Seedling Fund) of Putian University","award":["2019110"],"award-info":[{"award-number":["2019110"]}]},{"name":"Putian Science and Technology Plan Project","award":["2024GZ2001PTXY18"],"award-info":[{"award-number":["2024GZ2001PTXY18"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Physiol. Meas."],"published-print":{"date-parts":[[2026,5,29]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Miniature electrocardiogram (ECG) devices can rapidly and accurately acquire real-time cardiac signals, enabling timely warnings for patients with heart disease. To achieve accurate arrhythmia classification on resource-constrained ECG edge devices, we propose EdgeECG, an ultra-lightweight neural network designed for deployment on low-power microcontrollers.\n                    <jats:italic>Approach.<\/jats:italic>\n                    EdgeECG is first designed with a compact convolutional architecture to ensure compatibility with resource-limited embedded platforms. A dual criterion pruning (DCP) strategy is then introduced to evaluate weight importance using both magnitude and median deviation for more precise model compression. In addition, quantization is applied to reduce storage cost and improve deployment efficiency on an STM32F103 microcontroller.\n                    <jats:italic>Main results.<\/jats:italic>\n                    Experimental results on the benchmark MIT-BIH arrhythmia dataset show that EdgeECG achieves an overall classification accuracy of 98.07%, outperforming several representative methods. In patient-independent record-level evaluation, the accuracy reaches 80.73%. The model contains only 2680 parameters and is successfully deployed on an STM32F103 microcontroller with 64 KB SRAM, achieving an inference latency of 0.025\u2009s and an energy consumption of 0.156\u2009mJ per inference. In addition, DCP reduces the number of non-zero parameters by nearly 50% while maintaining promising classification performance.\n                    <jats:italic>Significance.<\/jats:italic>\n                    EdgeECG provides an effective solution for five-class ECG arrhythmia classification on severely resource-constrained edge devices. Its compact architecture, effective pruning strategy, and successful deployment on an STM32F103 demonstrate its potential for low-power edge-based ECG analysis and wearable cardiac monitoring applications. The source code of EdgeECG is publicly available at:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/jyanhuang\/EdgeECG-code\">https:\/\/github.com\/jyanhuang\/EdgeECG-code<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1088\/1361-6579\/ae696a","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T22:53:25Z","timestamp":1778108005000},"page":"055014","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["EdgeECG: a lightweight edge-oriented network with dual criterion pruning for real-time ECG arrhythmia classification"],"prefix":"10.1088","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0496-4646","authenticated-orcid":true,"given":"Jiayan","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Systems Engineering, Automation and Industrial Informatics"},{"name":"Putian University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuansheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering, Automation and Industrial Informatics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4112-3325","authenticated-orcid":false,"given":"Antoni","family":"Grau","sequence":"additional","affiliation":[{"name":"Department of Systems Engineering, Automation and Industrial Informatics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongyi","family":"Xiao","sequence":"additional","affiliation":[{"name":"Putian University"},{"name":"City University of Macau"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoye","family":"Luo","sequence":"additional","affiliation":[{"name":"Putian University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Che","sequence":"additional","affiliation":[{"name":"Fujian Province University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0952-9915","authenticated-orcid":false,"given":"Zuoyong","family":"Li","sequence":"additional","affiliation":[{"name":"Minjiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"pmeaae696abib1","doi-asserted-by":"publisher","first-page":"103","DOI":"10.21928\/uhdjst.v4n1y2020.pp103-117","type":"journal-article","article-title":"A review study for electrocardiogram signal classification","volume":"4","author":"Abdulla","year":"2020","journal-title":"UHD J. Sci. Technol."},{"key":"pmeaae696abib2","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.compbiomed.2017.08.022","type":"journal-article","article-title":"A deep convolutional neural network model to classify heartbeats","volume":"89","author":"Acharya","year":"2017","journal-title":"Comput. Biol. Med."},{"key":"pmeaae696abib3","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-26476-1","type":"journal-article","article-title":"Comparative evaluation of filtration techniques for ECG signal denoising with emphasis on stationary wavelet transform","volume":"15","author":"\u00c1d\u00e1m","year":"2025","journal-title":"Sci. Rep."},{"key":"pmeaae696abib4","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105884","type":"journal-article","article-title":"A lightweight hybrid CNN-LSTM explainable model for ECG-based arrhythmia detection","volume":"90","author":"Alamatsaz","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"pmeaae696abib5","doi-asserted-by":"publisher","first-page":"7896","DOI":"10.3390\/s24247896","type":"journal-article","article-title":"Research on a lightweight arrhythmia classification model based on knowledge distillation for wearable single-lead ECG monitoring systems","volume":"24","author":"An","year":"2024","journal-title":"Sensors (Basel, Switzerland)"},{"key":"pmeaae696abib6","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2023.1246746","type":"journal-article","article-title":"Deep learning for ECG Arrhythmia detection and classification: an overview of progress for period 2017\u20132023","volume":"14","author":"Ansari","year":"2023","journal-title":"Front. Physiol."},{"key":"pmeaae696abib7","doi-asserted-by":"publisher","DOI":"10.1177\/11779322221149600","type":"journal-article","article-title":"A literature review: ECG-based models for arrhythmia diagnosis using artificial intelligence techniques","volume":"17","author":"Boulif","year":"2023","journal-title":"Bioinform. Biol. Insights"},{"key":"pmeaae696abib8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.22489\/CinC.2020.085","type":"conference-proceedings","article-title":"SE-ECGNet: multi-scale SE-Net for multi-lead ECG data","author":"Chen","year":"2020"},{"key":"pmeaae696abib9","doi-asserted-by":"publisher","first-page":"5772","DOI":"10.1109\/JBHI.2022.3171918","type":"journal-article","article-title":"Edge2Analysis: a novel AIoT platform for atrial fibrillation recognition and detection","volume":"26","author":"Chen","year":"2022a","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"pmeaae696abib10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119230","type":"journal-article","article-title":"Cross-modal multiscale multi-instance learning for long-term ECG classification","volume":"643","author":"Chen","year":"2023","journal-title":"Inf. Sci."},{"key":"pmeaae696abib11","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.103493","type":"journal-article","article-title":"Review of ECG detection and classification based on deep learning: coherent taxonomy, motivation, open challenges and recommendations","volume":"74","author":"Chen","year":"2022b","journal-title":"Biomed. Signal Process. Control"},{"key":"pmeaae696abib12","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1109\/TBME.2004.827359","type":"journal-article","article-title":"Automatic classification of heartbeats using ECG morphology and heartbeat interval features","volume":"51","author":"De Chazal","year":"2004","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmeaae696abib13","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105714","type":"journal-article","article-title":"Ecgtransform: Empowering adaptive ECG Arrhythmia classification framework with bidirectional transformer","volume":"89","author":"El-Ghaish","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"pmeaae696abib14","doi-asserted-by":"publisher","first-page":"134041","DOI":"10.1109\/ACCESS.2025.3592729","type":"journal-article","article-title":"FPGA SoC implementation of adaptive deep neural network based multimodal edge intelligence for internet of medical things","volume":"13","author":"Gaikwad","year":"2025","journal-title":"IEEE Access"},{"key":"pmeaae696abib15","doi-asserted-by":"publisher","first-page":"5570","DOI":"10.1038\/s41598-024-55942-5","type":"journal-article","article-title":"Complex hybrid weighted pruning method for accelerating convolutional neural networks","volume":"14","author":"Geng","year":"2024","journal-title":"Sci. Rep."},{"key":"pmeaae696abib16","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1201\/9781003162810-13","type":"book","article-title":"A survey of quantization methods for efficient neural network inference","author":"Gholami","year":"2022"},{"key":"pmeaae696abib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113301","type":"journal-article","article-title":"Advanced deep learning framework for ECG arrhythmia classification using 1D\u2013CNN with attention mechanism","volume":"315","author":"Guhdar","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"pmeaae696abib18","first-page":"vol 28","type":"conference-proceedings","article-title":"Learning both weights and connections for efficient neural network","author":"Han","year":"2015"},{"key":"pmeaae696abib19","doi-asserted-by":"publisher","first-page":"e3710","DOI":"10.1002\/ett.3710","type":"journal-article","article-title":"Edge computing in smart health care systems: review, challenges and research directions","volume":"33","author":"Hartmann","year":"2022","journal-title":"Trans. Emerg. Telecommun. Technol."},{"key":"pmeaae696abib20","first-page":"4340","type":"conference-proceedings","article-title":"Filter pruning via geometric median for deep convolutional neural networks acceleration","author":"He","year":"2019"},{"key":"pmeaae696abib21","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1109\/ICHI.2018.00092","type":"conference-proceedings","article-title":"ECG heartbeat classification: a deep transferable representation","author":"Kachuee","year":"2018"},{"key":"pmeaae696abib22","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.22266\/ijies2025.0229.86","type":"journal-article","article-title":"Efficient ECG classification based on machine learning and feature selection algorithm for IoT-5G enabled health monitoring systems","volume":"18","author":"Kailan","year":"2025","journal-title":"Int. J. Intell. Eng. Syst."},{"key":"pmeaae696abib23","doi-asserted-by":"publisher","first-page":"3741","DOI":"10.1038\/s41467-023-39472-8","type":"journal-article","article-title":"Practical intelligent diagnostic algorithm for wearable 12-lead ECG via self-supervised learning on large-scale dataset","volume":"14","author":"Lai","year":"2023","journal-title":"Nat. Commun."},{"key":"pmeaae696abib24","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.104963","type":"journal-article","article-title":"Lightx3ecg: a lightweight and explainable deep learning system for 3-lead electrocardiogram classification","volume":"85","author":"Le","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"pmeaae696abib25","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1109\/JETCAS.2012.2187707","type":"journal-article","article-title":"An ultra-low power ECG acquisition and monitoring ASIC system for WBAN applications","volume":"2","author":"Liu","year":"2012","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"key":"pmeaae696abib26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpcardiol.2025.103082","type":"journal-article","article-title":"Machine learning algorithms for heart disease diagnosis: a systematic review","volume":"50","author":"Mao","year":"2025","journal-title":"Curr. Problems Cardiol."},{"key":"pmeaae696abib27","doi-asserted-by":"publisher","first-page":"11256","DOI":"10.1109\/CVPR.2019.01152","type":"conference-proceedings","article-title":"Importance estimation for neural network pruning","author":"Molchanov","year":"2019"},{"key":"pmeaae696abib28","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.bspc.2018.08.007","type":"journal-article","article-title":"Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers","volume":"47","author":"Mond\u00e9jar-Guerra","year":"2019","journal-title":"Biomed. Signal Process. Control"},{"key":"pmeaae696abib29","doi-asserted-by":"publisher","DOI":"10.13026\/C2F305","type":"dataset","article-title":"MIT-BIH Arrhythmia Database","author":"Moody","year":"2005","unstructured":"Moody G Mark R 2005 MIT-BIH Arrhythmia Database PhysioNet 10.13026\/C2F305"},{"key":"pmeaae696abib30","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1109\/51.932724","type":"journal-article","article-title":"The impact of the MIT-BIH arrhythmia database","volume":"20","author":"Moody","year":"2001","journal-title":"IEEE Eng. Med. Biol. Mag."},{"key":"pmeaae696abib31","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.1109\/JBHI.2019.2942938","type":"journal-article","article-title":"Inter-patient ecg classification with symbolic representations and multi-perspective convolutional neural networks","volume":"24","author":"Niu","year":"2020","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"pmeaae696abib32","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105780","type":"journal-article","article-title":"A lightweight SelfONN model for general ECG classification with pretraining","volume":"89","author":"Qin","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"pmeaae696abib33","doi-asserted-by":"publisher","first-page":"58","DOI":"10.3390\/bioengineering11010058","type":"journal-article","article-title":"Cardiovascular diseases diagnosis using an ECG multi-band non-linear machine learning framework analysis","volume":"11","author":"Ribeiro","year":"2024","journal-title":"Bioengineering"},{"key":"pmeaae696abib34","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1186\/s12911-020-01199-7","type":"journal-article","article-title":"Survey: smartphone-based assessment of cardiovascular diseases using ECG and PPG analysis","volume":"20","author":"Shabaan","year":"2020","journal-title":"BMC Med. Inf. Decis. Mak."},{"key":"pmeaae696abib35","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1093\/europace\/euaa377","type":"journal-article","article-title":"Deep learning and the electrocardiogram: review of the current state-of-the-art","volume":"23","author":"Somani","year":"2021","journal-title":"Ep Europace"},{"key":"pmeaae696abib36","first-page":"20390","type":"conference-proceedings","article-title":"Sanity-checking pruning methods: Random tickets can win the jackpot","volume":"vol 33","author":"Su","year":"2020"},{"key":"pmeaae696abib37","doi-asserted-by":"publisher","first-page":"e1564","DOI":"10.7717\/peerj-cs.1564","type":"journal-article","article-title":"Random pruning: channel sparsity by expectation scaling factor","volume":"9","author":"Sun","year":"2023","journal-title":"PeerJ Comput. Sci."},{"key":"pmeaae696abib38","article-title":"A lightweight CNN-attention-BiLSTM architecture for multi-class arrhythmia classification on standard and wearable ECGs","author":"Thota","year":"2025","type":"preprint"},{"key":"pmeaae696abib39","author":"World Health Organization","year":"2025","type":"other"},{"key":"pmeaae696abib40","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105017","type":"journal-article","article-title":"SRT: improved transformer-based model for classification of 2D heartbeat images","volume":"88","author":"Wu","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"pmeaae696abib41","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1109\/JBHI.2021.3090421","type":"journal-article","article-title":"ULECGNet: an ultra-lightweight end-to-end ECG classification neural network","volume":"26","author":"Xiao","year":"2021","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"pmeaae696abib42","doi-asserted-by":"publisher","first-page":"1965","DOI":"10.1109\/EMBC46164.2021.9630588","type":"conference-proceedings","article-title":"Multistage pruning of CNN based ECG classifiers for edge devices","author":"Xiaolin","year":"2021"},{"key":"pmeaae696abib43","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106377","type":"journal-article","article-title":"Conditional generative adversarial network driven variable-duration single-lead to 12-lead electrocardiogram reconstruction","volume":"95","author":"Zhan","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"pmeaae696abib44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0326079","type":"journal-article","article-title":"Arrhythmia classification based on multi-input convolutional neural network with attention mechanism","volume":"20","author":"Zheng","year":"2025","journal-title":"PLoS One"}],"container-title":["Physiological Measurement"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae696a","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae696a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae696a","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae696a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae696a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae696a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae696a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae696a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T10:06:43Z","timestamp":1779098803000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6579\/ae696a"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":44,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,18]]},"published-print":{"date-parts":[[2026,5,29]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6579\/ae696a","relation":{},"ISSN":["0967-3334","1361-6579"],"issn-type":[{"value":"0967-3334","type":"print"},{"value":"1361-6579","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]},"assertion":[{"value":"EdgeECG: a lightweight edge-oriented network with dual criterion pruning for real-time ECG arrhythmia classification","name":"article_title","label":"Article Title"},{"value":"Physiological Measurement","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-01-09","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-05-06","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-05-18","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}