EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Data-driven Energy-efficient Adaptive Sampling Using Deep Reinforcement Learning

Berken Utku Demirel, Luke Chen, Mohammad Abdullah Al Faruque

ACM Transactions on Computing for Healthcare · 31.07.2023 · 4 (3) · 1-19

DOI: 10.1145/3598301 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Computing for Healthcare, online erschienen am 08.09.2023. Verfasst von Berken Utku Demirel und 2 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article presents a resource-efficient adaptive sampling methodology for classifying electrocardiogram (ECG) signals into different heart rhythms. We present our methodology in two folds: ( i ) the design of a novel real-time adaptive neural network architecture capable of classifying ECG signals with different sampling rates and ( ii ) a runtime implementation of sampling rate control using deep reinforcement learning (DRL). By using essential morphological details contained in the heartbeat waveform, the DRL agent can control the sampling rate and effectively reduce energy consumption at runtime. To evaluate our adaptive classifier, we use the MIT-BIH database and the recommendation of the AAMI to train the classifiers. The classifier is designed to recognize three major types of arrhythmias, which are supraventricular ectopic beats (SVEB), ventricular ectopic beats (VEB), and normal beats (N). The performance of the arrhythmia classification reaches an accuracy of 97.2% for SVEB and 97.6% for VEB beats. Moreover, the designed system is 7.3× more energy-efficient compared to the baseline architecture, where the adaptive sampling rate is not utilized. The proposed methodology can provide reliable and accurate real-time ECG signal analysis with performances comparable to state-of-the-art methods. Given its time-efficient, low-complexity, and low-memory-usage characteristics, the proposed methodology is also suitable for practical ECG applications, in our case for arrhythmia classification, using resource-constrained devices, especially wearable healthcare devices and implanted medical devices.

Zitieren

APA

Demirel, B. U., Chen, L., & Faruque, M. A. A. (2023). Data-driven Energy-efficient Adaptive Sampling Using Deep Reinforcement Learning. ACM Transactions on Computing for Healthcare, 4(3), 1-19. https://doi.org/10.1145/3598301

Vancouver

Demirel BU, Chen L, Faruque MAA. Data-driven Energy-efficient Adaptive Sampling Using Deep Reinforcement Learning. ACM Transactions on Computing for Healthcare. 2023;4(3):1-19. doi:10.1145/3598301

BibTeX
@article{Demirel2023,
  author = {Demirel, Berken Utku and Chen, Luke and Faruque, Mohammad Abdullah Al},
  title = {Data-driven Energy-efficient Adaptive Sampling Using Deep Reinforcement Learning},
  journal = {ACM Transactions on Computing for Healthcare},
  year = {2023},
  volume = {4},
  number = {3},
  pages = {1--19},
  doi = {10.1145/3598301}
}
Kostenlos starten →