Nils C. Albrecht, Markus Heyder, Marvin Wenzel, Dominik Langer, Hui Lu, Alexander Koelpin
{"title":"Long-Distance Heart Sound Detection using 122 GHz CW Radar with 3D Printed High-Gain Antennas","authors":"Nils C. Albrecht, Markus Heyder, Marvin Wenzel, Dominik Langer, Hui Lu, Alexander Koelpin","doi":"10.1109/RWS55624.2023.10046319","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":110742,"journal":{"name":"2023 IEEE Radio and Wireless Symposium (RWS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE Radio and Wireless Symposium (RWS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/RWS55624.2023.10046319","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
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.