EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on a Lightweight Arrhythmia Classification Model Based on Knowledge Distillation for Wearable Single-Lead ECG Monitoring Systems

Xiang An, Shiwen Shi, Qian Wang, Yansuo Yu, Qiang Liu iD

Sensors · 10.12.2024 · 24 (24) · 7896

DOI: 10.3390/s24247896 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.12.2024. Verfasst von Xiang An und 4 weiteren Autor:innen. Beteiligte Einrichtung: Academy of Artificial Intelligence, Beijing Institute of Petrochemical Technology, Beijing 102617, China. Hauptthemen laut MEDLINE: Wearable Electronic Devices, Electrocardiography, Arrhythmias, Cardiac. Die Arbeit wurde bisher 49-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Municipal Education Commission, National College Students Innovation and Entrepreneurship Training Program, Zhiyuan Science Foundation of BIPT.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Arrhythmias are among the diseases with high mortality rates worldwide, causing millions of deaths each year. This underscores the importance of real-time electrocardiogram (ECG) monitoring for timely heart disease diagnosis and intervention. Deep learning models, trained on ECG signals across twelve or more leads, are the predominant approach for automated arrhythmia detection in the AI-assisted medical field. While these multi-lead ECG-based models perform well in automatic arrhythmia detection, their complexity often restricts their use on resource-constrained devices. In this paper, we propose an efficient, lightweight arrhythmia classification model using a knowledge distillation technique to train a student model from a teacher model, tailored for embedded intelligence in wearable devices. The results show that the student model achieves 96.32% accuracy, which is comparable to the teacher model, with a remarkable compression ratio that is 1242.58 times smaller, outperforming other lightweight models. Enabled by the proposed model, we developed a wearable ECG monitoring system based on the STM32F429 Discovery kit and ADS1292R chip, achieving real-time arrhythmia detection on small wearable devices.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Wearable Electronic DevicesElectrocardiographyArrhythmias, CardiacHumansSignal Processing, Computer-AssistedAlgorithmsDeep LearningMonitoring, Physiologic

Stichwörter der Autor:innen

arrhythmia classificationedge intelligenceelectrocardiogram (ECG)embedded systemknowledge distillation (KD)microcontroller

Autor:innen und Institutionen

  • Academy of Artificial Intelligence, Beijing Institute of Petrochemical Technology, Beijing 102617, China.

ORCID-Profile: Qiang Liu

Förderung

  • Beijing Municipal Education Commission
  • National College Students Innovation and Entrepreneurship Training Program
  • Zhiyuan Science Foundation of BIPT

Zitieren

APA

An, X., Shi, S., Wang, Q., Yu, Y., & Liu, Q. (2024). Research on a Lightweight Arrhythmia Classification Model Based on Knowledge Distillation for Wearable Single-Lead ECG Monitoring Systems. Sensors, 24(24), 7896. https://doi.org/10.3390/s24247896

Vancouver

An X, Shi S, Wang Q, Yu Y, Liu Q. Research on a Lightweight Arrhythmia Classification Model Based on Knowledge Distillation for Wearable Single-Lead ECG Monitoring Systems. Sensors. 2024;24(24):7896. doi:10.3390/s24247896

BibTeX
@article{An2024,
  author = {An, Xiang and Shi, Shiwen and Wang, Qian and Yu, Yansuo and Liu, Qiang},
  title = {Research on a Lightweight Arrhythmia Classification Model Based on Knowledge Distillation for Wearable Single-Lead ECG Monitoring Systems},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {24},
  pages = {7896},
  doi = {10.3390/s24247896}
}
Kostenlos starten →