EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things Applications

Moez Hizem iD, Leila Bousbia, Yassmine Ben Dhiab iD, Mohamed Ould-Elhassen Aoueileyine iD, Ridha Bouallegue

Sensors · 15.04.2025 · 25 (8) · 2496

DOI: 10.3390/s25082496 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.04.2025. Verfasst von Moez Hizem und 4 weiteren Autor:innen. Beteiligte Einrichtung: Innov'COM Laboratory, Higher School of Communication of Tunis, University of Carthage, Tunis 1054, Tunisia. Hauptthemen laut MEDLINE: Electrocardiography, Internet of Things, Arrhythmias, Cardiac. Die Arbeit wurde bisher 67-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Young Researchers Encouragement Program (PEJC).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The advent of Tiny Machine Learning (TinyML) has unlocked the potential to deploy machine learning models on resource-constrained edge devices, revolutionizing real-time monitoring in Internet of Medical Things (IoMT) applications. This study introduces a novel approach to real-time electrocardiogram (ECG) anomaly detection by integrating TinyML with edge Artificial Intelligence (AI) on low-power embedded systems. We demonstrate the feasibility and effectiveness of deploying optimized models on edge devices, such as the Raspberry Pi and Arduino, to detect ECG anomalies, including arrhythmias. The proposed workflow encompasses data preprocessing, feature extraction, and model inference, all executed directly on the edge device, eliminating the need for cloud resources. To address the constraints of memory and power consumption in wearable devices, we applied advanced optimization techniques, including model pruning and quantization, achieving an optimal balance between accuracy and resource utilization. The optimized model achieved an accuracy of 92.3% while reducing the power consumption to 0.024 mW, enabling continuous, long-term health monitoring with minimal energy requirements. This work highlights the potential of TinyML to advance edge AI for real-time medical applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectrocardiographyInternet of ThingsArrhythmias, CardiacHumansMachine LearningWearable Electronic DevicesArtificial IntelligenceAlgorithmsSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

ECGIoMTTinyMLanomaly detectionedge AIembedded systemslow-power

Autor:innen und Institutionen

  • Innov'COM Laboratory, Higher School of Communication of Tunis, University of Carthage, Tunis 1054, Tunisia.
  • Faculty of Sciences of Tunis, University of Tunis El Manar, Tunis 2092, Tunisia.

ORCID-Profile: Moez Hizem, Yassmine Ben Dhiab, Mohamed Ould-Elhassen Aoueileyine

Förderung

  • Young Researchers Encouragement Program (PEJC)

Zitieren

APA

Hizem, M., Bousbia, L., Ben Dhiab, Y., Aoueileyine, M. O., & Bouallegue, R. (2025). Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things Applications. Sensors, 25(8), 2496. https://doi.org/10.3390/s25082496

Vancouver

Hizem M, Bousbia L, Ben Dhiab Y, Aoueileyine MO, Bouallegue R. Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things Applications. Sensors. 2025;25(8):2496. doi:10.3390/s25082496

BibTeX
@article{Hizem2025,
  author = {Hizem, Moez and Bousbia, Leila and Ben Dhiab, Yassmine and Aoueileyine, Mohamed Ould-Elhassen and Bouallegue, Ridha},
  title = {Reliable ECG Anomaly Detection on Edge Devices for Internet of Medical Things Applications},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {8},
  pages = {2496},
  doi = {10.3390/s25082496}
}
Kostenlos starten →