Long-distance heart sound detection using 122 GHz CW radar with 3D printed high-gain antennas

Publikationstyp
Conference Paper
Publikationsdatum
2023-01
Sprache
English
Author
Albrecht, Nils Christian orcid-logo
Heyer, Markus 
Wenzel, Marvin orcid-logo
Langer, Dominik 
Lu, Hui 
Kölpin, Alexander orcid-logo
Institut
Hochfrequenztechnik E-3 
TORE-URI
http://hdl.handle.net/11420/15017
Start Page
34
End Page
36
Citation
IEEE Radio and Wireless Symposium (RWS 2023)
Contribution to Conference
IEEE Radio and Wireless Symposium, RWS 2023 
Publisher DOI
10.1109/RWS55624.2023.10046319
Scopus ID
2-s2.0-85149343259
Publisher
IEEE
This contribution presents a 122 GHz continuous wave (CW) radar system capable of detecting human heart sounds over a distance of at least five meters. A bidirectional long short-term memory (LSTM) neural network is used to extract precise inter-beat-intervals (IBIs) from the radar data. A small-scale human trial with two persons is carried out, and the resulting accuracy of the system is compared to a gold-standard electrocardiogram (ECG). The proposed system shows a mean absolute error of 5 ms and a standard deviation (SD) of 63 ms compared to the ECG IBIs.
Schlagworte
continuous wave radar
machine learning
vital sign detection
MLE@TUHH
DDC Class
004: Informatik
600: Technik
610: Medizin
620: Ingenieurwissenschaften