EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hardware Aspects of Machine Learning-Based Cardiac Fibrillation Diagnosis

Ioannis Kouretas, Anastasios G. Skrivanos, Nikos C. Sagias, Kostas P. Peppas

Electronics · 17.08.2026 · 15 (16) · 3663

DOI: 10.3390/electronics15163663 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 17.08.2026. Verfasst von Ioannis Kouretas und 3 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents the hardware aspects of a Hjorth-parameter deep neural network (DNN)-based cardiac fibrillation diagnosis pipeline targeting low-power Internet of Medical Things (IoMT) devices and ASIC implementations. Building on earlier edge-to-cloud studies where Hjorth activity, mobility, and complexity were computed in software on microcontrollers and classified by a floating-point DNN, we introduce a fully synthesizable fixed-point hardware module that computes these parameters in real time, together with a quantized neural network (QNN) operating directly on the resulting fixed-point features. The Hjorth block includes derivative generation, accumulator banks, variance computation, and hardware divider and square-root units. Using the Shandong Provincial Hospital Database (SPHD) as in our previous work, we evaluate the impact of end-to-end fixed-point quantization on the AF-related arrhythmia detection performance for bit widths between 6 and 16 bits. For 10–12-bit configurations, the quantized pipeline achieves accuracy of approximately 93.7% and an area under the ROC curve (AUC) above 0.97, closely matching the floating-point baseline while significantly reducing the arithmetic complexity and memory footprint. ASIC synthesis in a 28 nm CMOS standard-cell library shows that the complete atrial detector core, integrating the Hjorth extractor and the hardware fully connected QNN, occupies on the order of 2×104μm2 and dissipates about 3 mW, with a critical-path delay of 7.08 ns. For the optimal 10–12-bit operating points, the synthesized core achieves per-inference energy in the range of 18.6–19.0 nJ (18,600–19,000 pJ) per classification, confirming its suitability for integration into wearable and IoMT ECG monitoring nodes. These results demonstrate that co-designed fixed-point Hjorth hardware and quantized DNNs can deliver a favorable trade-off between diagnostic performance, area, power, latency, and per-inference energy compared with existing MCU-, FPGA-, and ASIC-based ECG classifiers.

Zitieren

APA

Kouretas, I., Skrivanos, A. G., Sagias, N. C., & Peppas, K. P. (2026). Hardware Aspects of Machine Learning-Based Cardiac Fibrillation Diagnosis. Electronics, 15(16), 3663. https://doi.org/10.3390/electronics15163663

Vancouver

Kouretas I, Skrivanos AG, Sagias NC, Peppas KP. Hardware Aspects of Machine Learning-Based Cardiac Fibrillation Diagnosis. Electronics. 2026;15(16):3663. doi:10.3390/electronics15163663

BibTeX
@article{Kouretas2026,
  author = {Kouretas, Ioannis and Skrivanos, Anastasios G. and Sagias, Nikos C. and Peppas, Kostas P.},
  title = {Hardware Aspects of Machine Learning-Based Cardiac Fibrillation Diagnosis},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {16},
  pages = {3663},
  doi = {10.3390/electronics15163663}
}
Kostenlos starten →