EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Learning Classifier for Robust Artifact Rejection in FMCW Radar Vital Sensing

Alessandra Fusco, Sviatoslav Sakharov, Kostiantyn Lavronenko, Souvik Hazra, Lorenzo Servadei, Robert Wille

IEEE Sensors Journal · 01.07.2025 · 25 (13) · 23304-23311

DOI: 10.1109/jsen.2024.3497797 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 01.07.2025. Verfasst von Alessandra Fusco und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate and continuous monitoring of vital signs like heart and breathing rate is essential for timely diagnosis and early detection of critical health conditions. While traditional wearable devices fulfill this purpose, they can be uncomfortable and impractical for continuous use. In this study, we propose a novel classifier for radar-based vital sensing that leverages deep learning to enhance the accuracy and reliability of noncontact vital sign detection. Our classifier, integrated as a body motion rejection block, effectively differentiates between high-quality and corrupted data. Experimental results demonstrate a significant performance improvement over conventional methods. Specifically, our approach achieves 99.1% accuracy, 98.9% precision, 99.5% recall, and a 99.2% ${F}1$ score. These metrics represent an improvement of 8.4% in accuracy, 7.9% in precision, 6.7% in recall, and 7.3% in ${F}1$ score compared to the reference algorithm, which records respective values of 90.7%, 91.0%, 92.8%, and 91.9%. Additionally, we explored several architectural variants, including the use of Range FFT, Doppler FFT, and their combination as inputs. Our findings indicate that using both Range FFT and Doppler FFT inputs yields optimal performance. The combination effectively captures both spatial and velocity information, leading to improved model accuracy and robustness. The enhanced performance of our classifier holds promise for its application in real-time, privacy-sensitive Internet of Things (IoT) environments, marking a significant advancement in the field of noncontact vital sign monitoring.

Zitieren

APA

Fusco, A., Sakharov, S., Lavronenko, K., Hazra, S., Servadei, L., & Wille, R. (2025). Deep Learning Classifier for Robust Artifact Rejection in FMCW Radar Vital Sensing. IEEE Sensors Journal, 25(13), 23304-23311. https://doi.org/10.1109/jsen.2024.3497797

Vancouver

Fusco A, Sakharov S, Lavronenko K, Hazra S, Servadei L, Wille R. Deep Learning Classifier for Robust Artifact Rejection in FMCW Radar Vital Sensing. IEEE Sensors Journal. 2025;25(13):23304-23311. doi:10.1109/jsen.2024.3497797

BibTeX
@article{Fusco2025,
  author = {Fusco, Alessandra and Sakharov, Sviatoslav and Lavronenko, Kostiantyn and Hazra, Souvik and Servadei, Lorenzo and Wille, Robert},
  title = {Deep Learning Classifier for Robust Artifact Rejection in FMCW Radar Vital Sensing},
  journal = {IEEE Sensors Journal},
  year = {2025},
  volume = {25},
  number = {13},
  pages = {23304--23311},
  doi = {10.1109/jsen.2024.3497797}
}
Kostenlos starten →