EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Neural Architecture Search-Based ECG Classification for Low-Power Edge Deployment in IoT Healthcare Systems

Xiaolin Li iD, Long Nguyen iD, Sean Lim, Guoxin Wang iD, Rajesh Panicker, Declan Delaney iD, Ganesh Neelakanta Iyer iD, Deepu John iD

IEEE Journal of Translational Engineering in Health and Medicine · 2026

DOI: 10.1109/jtehm.2026.3701554 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Journal of Translational Engineering in Health and Medicine, 2026. Verfasst von Xiaolin Li und 7 weiteren Autor:innen. Beteiligte Einrichtung: Beijing University of Technology Beijing 100124 China. Hauptthemen laut MEDLINE: Signal Processing, Computer-Assisted, Electrocardiography, Neural Networks, Computer, Internet of Things. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Microelectronic Circuits Centre Ireland, Taighde Êireann, Fundamental Research Funds for Beijing Municipal Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To develop and validate a deployment-centric ECG arrhythmia classification framework for low-power wearable edge devices, with emphasis on efficient on-device screening and reduced communication burden in remote cardiac monitoring workflows, optimized for seamless integration into clinical remote monitoring workflows using resource-constrained wearable IoT edge devices.Methods and Procedures: We design a clinically-oriented wearable-to-phone workflow in which the edge device performs on-device ECG inference and transmits actionable anomaly summaries to a smartphone via Bluetooth Low Energy (BLE). This approach reduces latency, energy cost, and privacy risks compared to continuous raw-signal transmission. A NAS process tailored to arrhythmia detection automatically explores candidate architectures under diverse compute and memory constraints to identify feasible models for embedded platforms. Multiple deployment-ready variants are generated via quantization and pruning, and implemented on an ARM Cortex-M33-based system. System efficiency is quantified through end-to-end measurements of energy consumption and data throughput, ensuring its readiness for long-term ambulatory monitoring.

Results

The deployed models achieve real-time inference on an ARM Cortex-M33 with as little as 21.7 kB RAM and 265k MACs. After optimization, energy consumption is reduced to 5.51 mJ per inference. Compared with the original model, RAM usage is reduced by 53.6%, with only a 0.5% absolute decrease in accuracy (97.9% to 97.4%). Hardware-in-the-loop power profiling confirms significant efficiency gains, validating the clinical feasibility of the proposed selective offloading strategy.

Conclusion

A NAS-guided, deployment-centric pipeline-spanning architecture search, compression/mapping, and embedded power profiling enables accurate, real-time ECG classification within stringent wearable constraints. The selective-offloading strategy bridges the gap between laboratory algorithms and practical cardiac surveillance by providing a high-fidelity, low-power, and clinically-aware solution for continuous arrhythmia screening.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Signal Processing, Computer-AssistedElectrocardiographyNeural Networks, ComputerInternet of ThingsWearable Electronic DevicesHumansArrhythmias, CardiacDigital HealthAlgorithmsSmartphoneRemote Patient Monitoring

Stichwörter der Autor:innen

Edge AIbiomedical signal classification (BSC)deep neural networks (DNNs)resource constrained implementation

Autor:innen und Institutionen

  • Beijing University of Technology Beijing 100124 China.
  • National University of Singapore Cluny Road Singapore 119077.
  • Trinity College Dublin Dublin D02PN40 Ireland.
  • University College Dublin Dublin D04V1W8 Ireland.

ORCID-Profile: Xiaolin Li, Long Nguyen, Guoxin Wang, Declan Delaney, Ganesh Neelakanta Iyer, Deepu John

Förderung

  • Microelectronic Circuits Centre Ireland
  • Taighde Êireann
  • Fundamental Research Funds for Beijing Municipal Universities
  • Introducing Talents for Cultivation project of Beijing University of Technology

Zitieren

APA

Li, X., Nguyen, L., Lim, S., Wang, G., Panicker, R., Delaney, D., Iyer, G. N., & John, D. (2026). Neural Architecture Search-Based ECG Classification for Low-Power Edge Deployment in IoT Healthcare Systems. IEEE Journal of Translational Engineering in Health and Medicine. https://doi.org/10.1109/jtehm.2026.3701554

Vancouver

Li X, Nguyen L, Lim S, Wang G, Panicker R, Delaney D, et al. Neural Architecture Search-Based ECG Classification for Low-Power Edge Deployment in IoT Healthcare Systems. IEEE Journal of Translational Engineering in Health and Medicine. 2026. doi:10.1109/jtehm.2026.3701554

BibTeX
@article{Li2026,
  author = {Li, Xiaolin and Nguyen, Long and Lim, Sean and Wang, Guoxin and Panicker, Rajesh and Delaney, Declan and Iyer, Ganesh Neelakanta and John, Deepu},
  title = {Neural Architecture Search-Based ECG Classification for Low-Power Edge Deployment in IoT Healthcare Systems},
  journal = {IEEE Journal of Translational Engineering in Health and Medicine},
  year = {2026},
  doi = {10.1109/jtehm.2026.3701554}
}
Kostenlos starten →