Compressed Deep Learning to Classify Arrhythmia in an Embedded Wearable Device
Open accessAbstract
The importance of an embedded wearable device with automatic detection and alarming cannot be overstated, given that 15–30% of patients with atrial fibrillation are reported to be asymptomatic. These asymptomatic patients do not seek medical care, hence traditional diagnostic tools including Holter are not effective for the further prevention of associated stroke or heart failure. This is likely to be more so in the era of COVID-19, in which patients become more reluctant on hospitalization and checkups. However, little literature is available on this important topic. For this reason, this study developed efficient deep learning with model compression, which is designed to use ECG data and classify arrhythmia in an embedded wearable device. ECG-signal data came from Korea University Anam Hospital in Seoul, Korea, with 28,308 unique patients (15,412 normal and 12,896 arrhythmia). Resnets and Mobilenets with model compression (TensorFlow Lite) were applied and compared for the diagnosis of arrhythmia in an embedded wearable device. The weight size of the compressed model registered a remarkable decrease from 743 MB to 76 KB (1/10000), whereas its performance was almost the same as its original counterpart. Resnet and Mobilenet were similar in terms of accuracy, i.e., Resnet-50 Hz (97.3) vs. Mo-bilenet-50 Hz (97.2), Resnet-100 Hz (98.2) vs. Mobilenet-100 Hz (97.9). Here, 50 Hz/100 Hz denotes the down-sampling rate. However, Resnets took more flash memory and longer inference time than did Mobilenets. In conclusion, Mobilenet would be a more efficient model than Resnet to classify arrhythmia in an embedded wearable device.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Lee et al. compressed an ECG arrhythmia-classification model from 743 MB to 76 KB, an approximately 10,000-fold reduction, for embedded wearable deployment.
“Lee et al. compressed an ECG arrhythmia-classification model from 743 MB to 76 KB, an approximately 10,000-fold reduction, for embedded wearable deployment”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [66]
The compressed ECG arrhythmia-classification model variants achieved accuracies of 97.2% to 98.2%.
“reporting accuracies of 97.2% to 98.2%”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [66]
The compressed ECG arrhythmia-classification model variants had inference times of approximately 150 to 600 ms.
“inference times of approximately 150 to 600 ms across the model variants evaluated”
From Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease (2026) · cites this paper as [66]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · see citing works
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015 · see citing works
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · see citing works
Han, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662 · see citing works
Worldwide Epidemiology of Atrial Fibrillation: A Global Burden of Disease 2010 Study
Chugh, S. S., Havmoeller, R., Narayanan, K., Singh, D., Rienstra, M., Benjamin, E. J., Gillum, R. F., Kim, Y.-H., McAnulty, J. H., Zheng, Z.-J., et al. (2014) · Circulation · doi:10.1161/circulationaha.113.005119 · Cited by 4,506 · see citing works
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_32 · Cited by 4,408 · see citing works
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196 · see citing works
Delay or avoidance of medical care because of COVID-19–related concerns—United States, June 2020.
Czeisler, M. É., Marynak, K., Clarke, K. E. N., Salah, Z., Shakya, I., Thierry, J. M., Ali, N., McMillan, H., Wiley, J. F., Weaver, M. D., et al. (2020) · MMWR. Morbidity and Mortality Weekly Report · doi:10.15585/mmwr.mm6936a4 · Cited by 1,516 · see citing works
A Survey of Model Compression and Acceleration for Deep Neural Networks
Cheng, Y., Wang, D., Zhou, P., & Zhang, T. (2017) · arXiv · doi:10.48550/arxiv.1710.09282 · Cited by 857 · see citing works
Cardiologist-Level Arrhythmia Detection with Convolutional Neural NetworksPreprint
Rajpurkar, P., Hannun, A., Haghpanahi, M., Bourn, C., & Ng, A. Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.01836 · Cited by 611 · see citing works
Characterization of Different Subsets of Atrial Fibrillation in General Practice in France
Lévy, S., Maarek, M., Coumel, P., Guize, L., Lekieffre, J., Medvedowsky, J. L., & Sebaoun, A. (1999) · Circulation · doi:10.1161/01.cir.99.23.3028 · Cited by 580 · see citing works
A deep learning approach for ECG-based heartbeat classification for arrhythmia detection
Sannino, G., & Pietro, G. D. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2018.03.057 · Cited by 452 · see citing works
LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices
Saadatnejad, S., Oveisi, M., & Hashemi, M. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2911367 · Cited by 452 · see citing works
Flaker, G. C., Belew, K., Beckman, K., Vidaillet, H., Kron, J., Safford, R., Mickel, M., & Barrell, P. (2005) · American Heart Journal · doi:10.1016/j.ahj.2004.06.032 · Cited by 341 · see citing works
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural NetworksPreprint
Rastegari, M., Ordóñez, V., Redmon, J., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.05279 · Cited by 279 · see citing works
Cardiac arrhythmia detection using deep learning
Işın, A., & Özdalili, S. (2017) · Procedia Computer Science · doi:10.1016/j.procs.2017.11.238 · Cited by 267 · see citing works
Rienstra, M., Lubitz, S. A., Mahida, S., Magnani, J. W., Fontes, J. D., Sinner, M. F., Van Gelder, I. C., Ellinor, P. T., & Benjamin, E. J. (2012) · Circulation · doi:10.1161/circulationaha.111.069450 · Cited by 237 · see citing works
Classification of ECG signals based on 1D convolution neural network
Li, D. X., Zhang, J., Zhang, Q., & Wei, X. (2017) · IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) · doi:10.1109/healthcom.2017.8210784 · Cited by 236 · see citing works
ECG arrhythmia classification using a 2-D convolutional neural networkPreprint
Jun, T. J., Nguyen, H. M., Kang, D., Kim, D., Kim, D.-Y., & Kim, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.06812 · Cited by 195 · see citing works
Increasing trends in hospital care burden of atrial fibrillation in Korea, 2006 through 2015
Kim, D., Yang, P., Jang, E., Yu, H. T., Kim, T., Uhm, J., Kim, J., Pak, H., Lee, M., Joung, B., et al. (2018) · Heart · doi:10.1136/heartjnl-2017-312930 · Cited by 133 · see citing works
Self-citationKerr, C. R., Boone, J. A., Connolly, S. J., Greene, M., Klein, G. J., Sheldon, R. S., & Talajic, M. R. (1996) · European Heart Journal · doi:10.1093/eurheartj/17.suppl_c.48 · Cited by 108 · see citing works
Patient-Specific ECG Classification Based on Recurrent Neural Networks and Clustering Technique
Zhang, C., Wang, G., Zhao, J., Gao, P., Lin, J., & Yang, H. (2017) · Biomedical Engineering · doi:10.2316/p.2017.852-029 · Cited by 99 · see citing works
Soft Weight-Sharing for Neural Network CompressionPreprint
Ullrich, K., Meeds, E., & Welling, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.04008 · Cited by 79 · see citing works
Trends and Patterns of Burden of Disease and Injuries in Korea Using Disability-Adjusted Life Years
Kim, Y., Park, H., Jo, M., Oh, I., Go, D., Jung, J., & Yoon, S. (2019) · Journal of Korean Medical Science · doi:10.3346/jkms.2019.34.e75 · Cited by 78 · see citing works
Self-citationLiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices
He, Z., Zhang, X., Cao, Y., Liu, Z., Zhang, B., & Wang, X. (2018) · Sensors · doi:10.3390/s18041229 · Cited by 56 · see citing works
ECG-Signal Multi-Classification Model Based on Squeeze-and-Excitation Residual Neural Networks
Park, J., Kim, J.-K., Jung, S., Gil, Y., Choi, J., & Son, H. S. (2020) · Applied Sciences · doi:10.3390/app10186495 · Cited by 39 · see citing works
Self-citationSun, C. L. F., Dyer, S., Salvia, J., Segal, L., & Levi, R. (2021) · Health Affairs · doi:10.1377/hlthaff.2021.00250 · Cited by 37 · see citing works
Jeon, E., Oh, K., Kwon, S., Son, H., Yun, Y., Jung, E.-S., & Kim, M. S. (2020) · JMIR Medical Informatics · doi:10.2196/17037 · Cited by 32 · see citing works
Self-citationLee, K., & Park, K. W. (2019) · Geriatrics and gerontology international/Geriatrics & gerontology international · doi:10.1111/ggi.13716 · Cited by 25 · see citing works
Self-citationOECD (2021) · OECD Quarterly International Trade Statistics · doi:10.1787/bd274241-en · Cited by 22 · see citing works
Atrial fibrillation classification based on convolutional neural networks
Lee, K., Jung, S., Gil, Y., & Son, H. S. (2019) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-019-0946-1 · Cited by 22 · see citing works
Self-citationRecent R&D Trends for Lightweight Deep Learning
Lee, Y., Hyuk, M. Y., Park, J., & Min, O. G. (2019) · doi:10.22648/etri.2019.j.340205 · Cited by 12 · see citing works
Arrhythmia Classification in Multi-Channel ECG Signals Using Deep Neural Networks
Kim, K. (2018) · UC Berkeley · Cited by 4 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Neri, L., Oberdier, M. T., van Abeelen, K. C. J., Menghini, L., Tumarkin, E., Tripathi, H., Jaipalli, S., Orro, A., Paolocci, N., Gallelli, I., et al. (2023) · Sensors · doi:10.3390/s23104805 · Cited by 137 · see citing works
Shumba, A.-T., Montanaro, T., Sergi, I., Bramanti, A., Ciccarelli, M., Rispoli, A., Carrizzo, A., De Vittorio, M., & Patrono, L. (2023) · Sensors · doi:10.3390/s23156896 · Cited by 74 · see citing works
Gupta, U., Paluru, N., Nankani, D., Kulkarni, K., & Awasthi, N. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e26787 · Cited by 51 · see citing works
Employing of machine learning and wearable devices in healthcare system: tasks and challenges
Saad, H. S., Zaki, J. F. W., & Abdelsalam, M. M. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10197-z · Cited by 51 · see citing works
A Systematic Review on the Use of Consumer-Based ECG Wearables on Cardiac Health Monitoring
Wang, R., Veera, S. C. M., Asan, O., & Liao, T. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3456028 · Cited by 42 · see citing works
Emara, H. M., El‐Shafai, W., Algarni, A. D., Soliman, N. F., & El‐Samie, F. E. A. (2023) · IEEE Access · doi:10.1109/access.2023.3317241 · Cited by 24 · see citing works
Machine Learning for Detecting Atrial Fibrillation from ECGs: Systematic Review and Meta-Analysis
Xie, C., Wang, Z., Yang, C., Liu, J., & Liang, H. (2024) · Reviews in Cardiovascular Medicine · doi:10.31083/j.rcm2501008 · Cited by 21 · see citing works
Jafari, M., Tao, X., Barua, P. D., Tan, R., & Acharya, U. R. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.102982 · Cited by 22 · see citing works
Mäkynen, M., Ng, G. A., Li, X., & Schlindwein, F. S. (2022) · Sensors · doi:10.3390/s22228588 · Cited by 23 · see citing works
Real-time Classification of Fetal Status Based on Deep Learning and Cardiotocography Data
Lee, K.-S., Choi, E. S., Nam, Y. J., Liu, N. W., Yang, Y. S., Kim, H. Y., Ahn, K. H., & Hong, S. (2023) · Journal of Medical Systems · doi:10.1007/s10916-023-01960-1 · Cited by 15 · see citing works
Self-citationRominger, C., & Schwerdtfeger, A. R. (2022) · Sensors · doi:10.3390/s22082925 · Cited by 14 · see citing works
Żyliński, M., Nassibi, A., & Mandic, D. P. (2023) · Sensors · doi:10.3390/s23177521 · Cited by 14 · see citing works
Karako, K. (2024) · BioScience Trends · doi:10.5582/bst.2024.01170 · Cited by 12 · see citing works
Prajitha, C., Sridhar, K. P., & Baskar, S. (2022) · Frontiers in Sustainable Cities · doi:10.3389/frsc.2022.1073486 · Cited by 11 · see citing works
A lightweight GRU-based gesture recognition model for skeleton dynamic graphs
Ni, J., Wang, Y., Tang, G., Cao, W., & Yang, S. X. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18313-w · Cited by 10 · see citing works
Kim, S., Lim, J., Shin, M., & Jung, S. (2023) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc40787.2023.10340882 · Cited by 8 · see citing works
Self-citationAkbari, Y., Lei, N., Patel, N., Peng, Y., & Faust, O. (2025) · Sensors · doi:10.3390/s25216601 · Cited by 7 · see citing works
Deep learning for ECG-based cardiovascular disease diagnosis: a systematic review and meta-analysis
Bulbul, A. A.-M., Awal, M. A., Mahendran, N., Islam, S. M. S., Pogrebna, G., Ross, A. G., & Moni, M. A. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-025-11479-1 · Cited by 7 · see citing works
Intelligent algorithms powered smart devices for atrial fibrillation discrimination
Xie, L., Wang, L., Mo, D., Zhang, Z., & Liang, M. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.107480 · Cited by 7 · see citing works
A Conceptual Framework for User Trust in AI Biosensors: Integrating Cognition, Context, and Contrast
Prahl, A. (2025) · Sensors · doi:10.3390/s25154766 · Cited by 6 · see citing works
Kumar, S. S., & Ramachandran, P. (2025) · IEEE Access · doi:10.1109/access.2025.3560544 · Cited by 3 · see citing works
Cavero, J. A. Z., Pérez, M. D., Mendoza, J., Bravo, R. J., & Huané, L. Y. C. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11251775 · Cited by 2 · see citing works
Lee, S., Lee, K.-S., Park, H.-J., Han, K. S., Song, J., Lee, S. W., & Kim, S. J. (2025) · Applied Sciences · doi:10.3390/app15084148 · Cited by 2 · see citing works
Self-citationMallikarjunamallu, K., & Syed, K. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10723877 · Cited by 1 · see citing works
Wei, C., Li, Q., Zhang, A., & Wang, T. (2026) · Brain Sciences · doi:10.3390/brainsci16010083 · Cited by 1 · see citing works
Bickmann, L., Plagwitz, L., Büscher, A., Eckardt, L., & Varghese, J. (2026) · Journal of Medical Internet Research · doi:10.2196/81116 · Cited by 1 · see citing works
Hołda, P., Wasielewska-Michniewska, K., Ganzha, M., & Paprzycki, M. (2026) · Informatica · doi:10.15388/26-infor620 · Cited by 1 · see citing works
$$\Phi $$-OTDR event detection using image-based data transformation and deep learning
Yeke, M. C., Sirin, S., Yüksel, K., & Gümüş, A. (2026) · Pattern Analysis and Applications · doi:10.1007/s10044-026-01694-z · Cited by 1 · see citing works
Image Recognition of Wild Birds in Yunnan Based on Improved Mobile Deep Learning
Li, Y., Zhou, H., Zhao, Y., & Yang, H. (2022) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai55851.2022.9904054 · Cited by 1 · see citing works
Singh, Y., Bhatt, S., Gupta, D., Verma, S., & Deep, P. (2025) · Journal of Drug Discovery and Health Sciences · doi:10.21590/jddhs.02.01.05 · Cited by 1 · see citing works
Wearable Smart Solution for Accurate Machine Learning-Based AF Detection Using ECG SignalsPreprint
Soudani, A. (2023) · Preprints.org · doi:10.20944/preprints202312.1534.v1 · Cited by 1 · see citing works
Deep Learning Applied to 12-Lead ECGs for Detection of Structural, Metabolic and Systemic Disease
Shaulian, S., Zeltser, R., & Makaryus, A. N. (2026) · Diagnostics · doi:10.3390/diagnostics16172834
Lee, S., Lee, K., Park, H., Han, K. S., Song, J., Lee, S. W., & Kim, S. J. (2024) · Research Square · doi:10.21203/rs.3.rs-4941076/v1
Self-citationIoMT-Based Compressive Sensing with Threshold Filtering for Healthcare Monitoring in POCT Device
Chakraborty, T., Mitra, D., & Nesa, N. (2026) · Sensing and Imaging · doi:10.1007/s11220-025-00711-5
Feng, W., Meng, L., Yang, T., Jin, H., Liu, X., & Pei, P. (2026) · Applied Sciences · doi:10.3390/app16062640
Liu, C. (2026) · Journal of Thermal Analysis and Calorimetry · doi:10.1007/s10973-026-16523-y
- Authors
- Lee, K.-S., Park, H.-J., Kim, J. E., Kim, H. J., Chon, S., Kim, S., Jang, J., Kim, J.-K., Jang, S., Gil, Y., & Son, H. S.
- Affiliations
- Korea University Anam Hospital (KR)
- Korea University (KR)
- Department of Thoracic and Cardiovascular Surgery, Korea University College of Medicine, Korea University Anam Hospital, Seoul 02841, Korea
- HUINNO Co., Ltd., Seoul 06011, Korea
- Corresponding author
- Son, Ho Sung
- ORCID
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2022-02-24
- Volume
- 22
- Issue
- 5
- Pages
- 1776
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC8914813
- OpenAlex
- W4214691458
- Cited by
- 36
- References
- 24
- Citations by year
- 2026: 9 · 2025: 7 · 2024: 9 · 2023: 7 · 2022: 4
- FWCI
- 4.70
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Korea government (No. 1711138362, KMDF_PR_20200901_0174-02)
- Topics
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › ECG Monitoring and Analysis
- Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Cardiac electrophysiology and arrhythmias
- Keywords
- arrhythmia classification, wearable devices, model compression, TensorFlow Lite, ResNet, MobileNet, ECG signals, embedded systems, atrial fibrillation, flash memory, inference latency
- MeSH terms
- Wearable Electronic Devices, Deep Learning, COVID-19, SARS-CoV-2, Atrial Fibrillation, Electrocardiography, Humans, Signal Processing, Computer-Assisted
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
