A dataset of radar-recorded heart sounds and vital signs including synchronised reference sensor signals

Abstract

Radar systems allow for contactless measurements of vital signs such as heart sounds, the pulse signal, and respiration. This approach is able to tackle crucial disadvantages of state-of-the-art monitoring devices such as the need for permanent wiring and skin contact. Potential applications include the employment in a hospital environment but also in home care or passenger vehicles. This dataset consists of synchronised data which are acquired using a Six-Port-based radar system operating at 24 GHz, a digital stethoscope, an ECG, and a respiration sensor. 11 test subjects were measured in different defined scenarios and at several measurement positions such as at the carotid, the back, and several frontal positions on the thorax. Overall, around 223 minutes of data were acquired at scenarios such as breath-holding, post-exercise measurements, and while speaking. The presented dataset contains reference-labeled ECG signals and can therefore easily be used to either test algorithms for monitoring the heart rate, but also to gain insights about characteristic effects of radar-based vital sign monitoring.

A dataset of clinically recorded radar vital signs with synchronised reference sensor signals

“…As previously mentioned in 13 , the amount of public data regarding the evaluation of radar-recorded vital signs is very small and so a contribution of data from 11 people has already been made. In this previous work the feasibility of monitoring vital signs using radar in different scenarios was examined.…”

“…In this previous work the feasibility of monitoring vital signs using radar in different scenarios was examined. A detailed description of the preclinical study is published in 13 and the gathered dataset is available at figshare 14 . With the recent completion of our clinical evaluation, a further contribution to a public database shall be made.…”

Interference Motion Removal for Doppler Radar Vital Sign Detection Using Variational Encoder-Decoder Neural Network

“…The real vital signs samples are from an open dataset of "GUARDIAN Vital Sign Data" [22]. The dataset contains a number of reference signals, such as Phonocardiogram (PCG), Electrocardiogram (ECG) and respiration sensor in addition to the recording of radar signals [23]. The radar dataset is not balanced as it contains samples from varying scenarios, sampling rates and sensor placement configurations at different proportions.…”

Radar Recorded Child Vital Sign Public Dataset and Deep Learning-Based Age Group Classification Framework for Vehicular Application

“…Similarly SisFall and AnkFall datasets of fall detection was proposed in [16,17] respectively. Nevertheless, for radars, few public datasets also exits and amongst them are, the two vital sign datasets presented by Shi et al [18,19], the synthetic aperture radar (SAR) dataset provided by Wang et al [20], and the oxford's car robot dataset [21]. Although several studies have been conducted for vital sign detection and monitoring, public data sets are lacking.…”

“…Although several studies have been conducted for vital sign detection and monitoring, public data sets are lacking. Shi and coworkers [19] provided synchronized radar-recorded human vital signs; however, all the participants were above 20 years of age, and the radar used was a single-frequency continuous-wave radar. No such vital sign dataset exists for the FMCW radar.…”