EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Cardiac Arrhythmia Classification Using TinyML on Ultra-Low-Cost Microcontrollers: A Feasibility Study for Resource-Constrained Environments

Misael Zambrano-de la Torre iD, Sebastian Guzman-Alfaro iD, Andrea Acuña-Correa iD, Manuel A Soto-Murillo iD, Maximiliano Guzmán-Fernández iD, Ricardo Robles-Ortiz iD, Karen E Villagrana-Bañuelos iD, Jose G Arceo-Olague iD, Carlos H Espino-Salinas iD, Ana G Sánchez-Reyna iD, Erik O Cuevas-Rodriguez iD

Bioengineering · 01.05.2026 · 13 (5) · 532

DOI: 10.3390/bioengineering13050532 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 01.05.2026. Verfasst von Misael Zambrano-de la Torre und 10 weiteren Autor:innen. Beteiligte Einrichtung: Unidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas, Zacatecas 98160, Mexico. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in edge computing and Tiny Machine Learning (TinyML) have enabled the deployment of artificial intelligence models directly on microcontrollers with extremely limited computational and memory resources. In this context, this work presents the design, implementation, and validation of a real-time cardiac arrhythmia classification system based on a quantized one-dimensional convolutional neural network (1D-CNN), deployed on an 8-bit Arduino UNO microcontroller. The proposed system integrates end-to-end processing, including ECG signal acquisition using a low-cost AD8232 analog front-end, signal preprocessing, heartbeat segmentation, classification, and real-time visualization on an OLED display. The model was trained and evaluated using the MIT-BIH Arrhythmia Database, considering a reduced three-class problem (Normal, Ventricular, and Supraventricular) to meet the constraints of ultra-low-cost hardware deployment. Under benchmark conditions, the quantized model achieved an accuracy of 97.6%, with a memory footprint below 24 KB and an average inference time of 200 ms per heartbeat, enabling real-time operation on a resource-constrained microcontroller. Real-time experiments were conducted using signals acquired from healthy volunteers to validate system functionality, although no annotated ground truth was available for these recordings, and therefore no diagnostic performance was derived from them. The results demonstrate the feasibility of deploying lightweight deep learning models on ultra-constrained embedded systems using the TinyML paradigm, implemented using TensorFlow 2.15 and TensorFlow Lite. This work should be interpreted as a proof-of-concept platform that highlights the trade-off between classification performance and hardware limitations, providing a foundation for future development of low-cost cardiac monitoring technologies in resource-limited environments.

Schlagwörter

Stichwörter der Autor:innen

ECGTinyMLarrhythmia classificationedge AIembedded systemslow-cost healthcare

Autor:innen und Institutionen

  • Unidad Académica de Ingeniería Eléctrica, Universidad Autónoma de Zacatecas, Zacatecas 98160, Mexico.
  • Unidad Académica de Medicina Humana, Universidad Autónoma de Zacatecas, Jardín Juárez 147, Centro, Zacatecas 98000, Mexico.

ORCID-Profile: Misael Zambrano-de la Torre, Sebastian Guzman-Alfaro, Andrea Acuña-Correa, Manuel A Soto-Murillo, Maximiliano Guzmán-Fernández, Ricardo Robles-Ortiz, Karen E Villagrana-Bañuelos, Jose G Arceo-Olague, Carlos H Espino-Salinas, Ana G Sánchez-Reyna, Erik O Cuevas-Rodriguez

Zitieren

APA

Zambrano-de la Torre, M., Guzman-Alfaro, S., Acuña-Correa, A., Soto-Murillo, M. A., Guzmán-Fernández, M., Robles-Ortiz, R., Villagrana-Bañuelos, K. E., Arceo-Olague, J. G., Espino-Salinas, C. H., Sánchez-Reyna, A. G., & Cuevas-Rodriguez, E. O. (2026). Real-Time Cardiac Arrhythmia Classification Using TinyML on Ultra-Low-Cost Microcontrollers: A Feasibility Study for Resource-Constrained Environments. Bioengineering, 13(5), 532. https://doi.org/10.3390/bioengineering13050532

Vancouver

Zambrano-de la Torre M, Guzman-Alfaro S, Acuña-Correa A, Soto-Murillo MA, Guzmán-Fernández M, Robles-Ortiz R, et al. Real-Time Cardiac Arrhythmia Classification Using TinyML on Ultra-Low-Cost Microcontrollers: A Feasibility Study for Resource-Constrained Environments. Bioengineering. 2026;13(5):532. doi:10.3390/bioengineering13050532

BibTeX
@article{ZambranodelaTorre2026,
  author = {Zambrano-de la Torre, Misael and Guzman-Alfaro, Sebastian and Acuña-Correa, Andrea and Soto-Murillo, Manuel A and Guzmán-Fernández, Maximiliano and Robles-Ortiz, Ricardo and Villagrana-Bañuelos, Karen E and Arceo-Olague, Jose G and Espino-Salinas, Carlos H and Sánchez-Reyna, Ana G and Cuevas-Rodriguez, Erik O},
  title = {Real-Time Cardiac Arrhythmia Classification Using TinyML on Ultra-Low-Cost Microcontrollers: A Feasibility Study for Resource-Constrained Environments},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {5},
  pages = {532},
  doi = {10.3390/bioengineering13050532}
}
Kostenlos starten →