Patient activity recognition using radar sensors and machine learning

Bhavanasi, Geethika; Werthen‐Brabants, Lorin; Dhaene, Tom; Couckuyt, Ivo

doi:10.1007/s00521-022-07229-x

Cited by 37 publications

(24 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An effect of stretching exercise on HRV was found in 23 , and recovery was also discussed; however, such study may be good for low-level exercises effect on HRV. ANS activity recognition, such as stress, was measured using radar by referring to HRV components 24 , 25 ; therefore, further activities such as rest, fatigue, drowsiness and emotion classification using novel radar technology are still under debate. In our study, we assessed whether radar can be a fatigue predictor in relation to body composition parameter (BF percentage) and LF/HF ratios.…”

Section: Discussionmentioning

confidence: 99%

Noncontact assessment for fatigue based on heart rate variability using IR-UWB radar

Ahmed

Lee

Lim

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Physical fatigue can be assessed using heart rate variability (HRV). We measured HRV at rest and in a fatigued state using impulse-radio ultra wideband (IR-UWB) radar in a noncontact fashion and compared the measurements with those obtained using electrocardiography (ECG) to assess the reliability and validity of the radar measurements. HRV was measured in 15 subjects using radar and ECG simultaneously before (rest for 10 min before exercise) and after a 20-min exercise session (fatigue level 1 for 0–9 min; fatigue level 2 for 10–19 min; recovery for ≥ 20 min after exercise). HRV was analysed in the frequency domain, including the low-frequency component (LF), high-frequency component (HF) and LF/HF ratio. The LF/HF ratio measured using radar highly agreed with that measured using ECG during rest (ICC = 0.807), fatigue-1 (ICC = 0.712), fatigue-2 (ICC = 0.741) and recovery (ICC = 0.764) in analyses using intraclass correlation coefficients (ICCs). The change pattern in the LH/HF ratios during the experiment was similar between radar and ECG. The subject’s body fat percentage was linearly associated with the time to recovery from physical fatigue (R2 = 0.96, p < 0.001). Our results demonstrated that fatigue and rest states can be distinguished accurately based on HRV measurements using IR-UWB radar in a noncontact fashion.

show abstract

Section: Discussionmentioning

confidence: 99%

Noncontact assessment for fatigue based on heart rate variability using IR-UWB radar

Ahmed

Lee

Lim

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…The Patient Activity Recognition with radar sensors (PARrad 2 ) data set from [2] is considered. The PARrad data set contains data of 14 different activities of adult and elderly people.…”

Section: A Data Setmentioning

confidence: 99%

“…We adapted the CNN-RD network from [2] which uses RD maps as features. The RD maps consist of 40 frames, representing 3.7 seconds of radar data.…”

Section: B Deep Discriminative Representation Network (Ddrn)mentioning

confidence: 99%

See 1 more Smart Citation

Open-Set Patient Activity Recognition With Radar Sensors and Deep Learning

Bhavanasi

Werthen‐Brabants

Dhaene

et al. 2023

IEEE Geosci. Remote Sensing Lett.

Self Cite

View full text Add to dashboard Cite

Open-set recognition has achieved significant importance in recent years. For a robust recognition system, we need to identify the right class from a myriad of knowns and unknowns. In this work, we build and compare open-set recognition systems for patient activity recognition using compact radar sensors in a hospital setting. Radar sensors are an important part of a privacypreserving monitoring system. Specifically, the proposed approach is based on a deep discriminative representation network trained using the large margin cosine loss and triplet loss. A probability of inclusion model in the embedding space based on the Weibull distribution is able to separate knowns from unknowns. This overall approach limits the risk of open space and enables us to easily identify any unknown activities. Our experiments show that the proposed approach is significantly better for open-set human activity recognition with radar when compared to the state-of-the-art open-set approaches.

show abstract

“…Elderly persons are often reluctant to use the existing monitoring techniques because they may infringe on the privacy of those persons, or require the constant wearing of some additional devices [ 9 , 10 ]. As a result, two relatively new non-invasive and non-intrusive monitoring techniques are attracting growing attention of the researchers, viz., techniques based on depths sensors [ 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 ] and radar sensors [ 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 ].…”

Section: Introductionmentioning

confidence: 99%

Application of Feedforward and Recurrent Neural Networks for Fusion of Data from Radar and Depth Sensors Applied for Healthcare-Oriented Characterisation of Persons’ Gait

Mazurek

2023

Sensors

View full text Add to dashboard Cite

In this paper, the useability of feedforward and recurrent neural networks for fusion of data from impulse-radar sensors and depth sensors, in the context of healthcare-oriented monitoring of elderly persons, is investigated. Two methods of data fusion are considered, viz., one based on a multilayer perceptron and one based on a nonlinear autoregressive network with exogenous inputs. These two methods are compared with a reference method with respect to their capacity for decreasing the uncertainty of estimation of a monitored person’s position and uncertainty of estimation of several parameters enabling medical personnel to make useful inferences on the health condition of that person, viz., the number of turns made during walking, the travelled distance, and the mean walking speed. Both artificial neural networks were trained on the synthetic data. The numerical experiments show the superiority of the method based on a nonlinear autoregressive network with exogenous inputs. This may be explained by the fact that for this type of network, the prediction of the person’s position at each time instant is based on the position of that person at the previous time instants.

show abstract

Patient activity recognition using radar sensors and machine learning

Cited by 37 publications

References 50 publications

Noncontact assessment for fatigue based on heart rate variability using IR-UWB radar

Noncontact assessment for fatigue based on heart rate variability using IR-UWB radar

Open-Set Patient Activity Recognition With Radar Sensors and Deep Learning

Application of Feedforward and Recurrent Neural Networks for Fusion of Data from Radar and Depth Sensors Applied for Healthcare-Oriented Characterisation of Persons’ Gait

Contact Info

Product

Resources

About