EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Estimation of Compression Depth During CPR Using FMCW Radar with Deep Convolutional Neural Network

Insoo Choi iD, Stephen Gyung Won Lee, Hyoun-Joong Kong iD, Ki Jeong Hong iD, Youngwook Kim iD

Sensors · 24.09.2025 · 25 (19) · 5947

DOI: 10.3390/s25195947 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 24.09.2025. Verfasst von Insoo Choi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Engineering, Sogang University, Seoul 04107, Republic of Korea. Hauptthemen laut MEDLINE: Cardiopulmonary Resuscitation, Neural Networks, Computer, Radar. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Seoul National University Hospital Research Fund, Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Effective Cardiopulmonary Resuscitation (CPR) requires precise chest compression depth, but current out-of-hospital monitoring technologies face limitations. This study introduces a method using frequency-modulated continuous-wave (FMCW) radar to remotely and accurately monitor chest compressions. FMCW radar captures range, Doppler, and angular data, and we utilize micro-Doppler signatures for detailed motion analysis. By integrating Doppler shifts over time, chest displacement is estimated. We compare a regression model based on maximum Doppler frequency with deep convolutional neural networks (DCNNs) trained on spectrograms generated via short-time Fourier transform (STFT) and the Wigner–Ville distribution (WVD). The regression model achieved a root mean square error (RMSE) of 0.535 cm. The STFT-based DCNN improved accuracy with an RMSE of 0.505 cm, while the WVD-based DCNN achieved the best performance with an RMSE of 0.447 cm, representing an 11.5% improvement over the STFT-based DCNN. These findings highlight the potential of combining FMCW radar and deep learning to provide accurate, real-time chest compression depth measurement during CPR, supporting the development of advanced, non-contact monitoring systems for emergency medical response.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cardiopulmonary ResuscitationNeural Networks, ComputerRadarHumansDeep LearningFourier AnalysisAlgorithmsConvolutional Neural Networks

Stichwörter der Autor:innen

Doppler frequencyWigner–Ville distribution (WVD)cardiopulmonary resuscitation (CPR)deep convolutional neural network (DCNN)frequency-modulated continuous-wave (FMCW) radarmicro-doppler signatureregression

Autor:innen und Institutionen

  • Department of Electronic Engineering, Sogang University, Seoul 04107, Republic of Korea.
  • College of Medicine, Seoul National University, Seoul 03080, Republic of Korea.

ORCID-Profile: Insoo Choi, Hyoun-Joong Kong, Ki Jeong Hong, Youngwook Kim

Förderung

  • Seoul National University Hospital Research Fund
  • Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT)

Zitieren

APA

Choi, I., Lee, S. G. W., Kong, H. J., Hong, K. J., & Kim, Y. (2025). Estimation of Compression Depth During CPR Using FMCW Radar with Deep Convolutional Neural Network. Sensors, 25(19), 5947. https://doi.org/10.3390/s25195947

Vancouver

Choi I, Lee SGW, Kong HJ, Hong KJ, Kim Y. Estimation of Compression Depth During CPR Using FMCW Radar with Deep Convolutional Neural Network. Sensors. 2025;25(19):5947. doi:10.3390/s25195947

BibTeX
@article{Choi2025,
  author = {Choi, Insoo and Lee, Stephen Gyung Won and Kong, Hyoun-Joong and Hong, Ki Jeong and Kim, Youngwook},
  title = {Estimation of Compression Depth During CPR Using FMCW Radar with Deep Convolutional Neural Network},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {19},
  pages = {5947},
  doi = {10.3390/s25195947}
}
Kostenlos starten →