Fall Detection Using Multiple Bioradars and Convolutional Neural Networks

Anishchenko, Lesya; Zhuravlev, Andrey; Chizh, Margarita

doi:10.3390/s19245569

“…To select a learning framework to evaluate the recognition performance of the proposed method, comparative experiments were performed on five different learning models including PCA based SVM, because PCA based SVM method is widely used in the motion classification. In this paper, the learning frameworks considered are GoogleNet, ResNet, VGG, AlexNet, and PCA based SVM [ 34 , 39 , 40 , 51 , 52 , 53 ]. Comparative recognition performance is summarized in Table 2 .…”

Section: Recognition Resultsmentioning

confidence: 99%

“…On the other hand, deep learning approaches based on multi-layer networks such as the convolutional neural network (CNN) are promising for overcoming such feature selection problems without advance need for feature sets. GoogleNet, AlexNet, VGGNet, ResNet, and DenseNet are good examples of deep learning models [ 34 , 35 , 36 , 37 , 38 , 39 , 40 ].…”

Section: Introductionmentioning

confidence: 99%

Foot Gesture Recognition Using High-Compression Radar Signature Image and Deep Learning

Song

¹

,

Kim

²

,

Kim

³

et al. 2021

Sensors

1

0

View full text Add to dashboard Cite

Recently, Doppler radar-based foot gesture recognition has attracted attention as a hands-free tool. Doppler radar-based recognition for various foot gestures is still very challenging. So far, no studies have yet dealt deeply with recognition of various foot gestures based on Doppler radar and a deep learning model. In this paper, we propose a method of foot gesture recognition using a new high-compression radar signature image and deep learning. By means of a deep learning AlexNet model, a new high-compression radar signature is created by extracting dominant features via Singular Value Decomposition (SVD) processing; four different foot gestures including kicking, swinging, sliding, and tapping are recognized. Instead of using an original radar signature, the proposed method improves the memory efficiency required for deep learning training by using a high-compression radar signature. Original and reconstructed radar images with high compression values of 90%, 95%, and 99% were applied for the deep learning AlexNet model. As experimental results, movements of all four different foot gestures and of a rolling baseball were recognized with an accuracy of approximately 98.64%. In the future, due to the radar’s inherent robustness to the surrounding environment, this foot gesture recognition sensor using Doppler radar and deep learning will be widely useful in future automotive and smart home industry fields.

show abstract

“…Among other applications of MW, it is also worth mentioning a proposal to use radar to monitor the living areas for old people in order to detect falls [57].…”

Section: Monitoring Of Human Vital Signsmentioning

confidence: 99%

Design and Applications of Multi-Frequency Holographic Subsurface Radar: Review and Case Histories

Ivashov¹,

Capineri²,

Bechtel³

et al. 2021

Preprint

1

0

View full text Add to dashboard Cite

Holographic subsurface radar (HSR) is currently not in widespread usage. This is due to an historical perspective in the ground penetrating radar (GPR) community that the high attenuation of electromagnetic waves in most media of interest, and the inability to apply time-varying gain to the continuous wave (CW) HSR signal precludes sufficient effective penetration depth. While it is true that the fundamental physics of HSR, with its use of a CW signal, does not allow amplification of later (i.e. deeper) arrivals in lossy media (as is possible with impulse subsurface radar — ISR), HSR has distinct some distinctive advantages. The most important of these is the ability to do shallow subsurface imaging with a resolution that is not possible with ISR. In addition, the design of an HSR system is simpler than for ISR due to the relatively low-tech transmitting and receiving antennae. This paper provides a review of the main principles of HSR through an optical analogy and describes possible algorithms for radar hologram reconstruction. We also present a review of the history of development of systems and applications for HSR of the “RASCAN” type which is possibly the only holographic subsurface radar that is produced in lots. Among the subsurface imaging and remote sensing applications considered are humanitarian demining, construction inspection, surveys of historic architecture and artworks, nondestructive testing of dielectric aerospace materials, security applications, paleontology, detection of wood-boring insect damage, and others. Each application is illustrated with relevant data acquired in laboratory and/or field experiments.

show abstract

“…❖ Diagnostics of composite materials in aerospace and other industries [26], [27], [28], [29], [30], [31], [32], [33], [34] ❖ Diagnostics of building details and constructions including cultural heritage monuments [35], [36], [37], [38], [39] ❖ Archaeological and paleontological imaging [40], [41], [42] ❖ Landmine detection and discrimination [9], [10], [11], [43], [44], [45], [46] ❖ Security systems [47], [48], [49], [50], [51], [52], [53] ❖ Detection of wood-boring insect damage [54] ❖ Medical imaging [55], [56], [57], [58], [59].…”

Section: Hsr Hologramsmentioning

confidence: 99%

Design and Applications of Multi-Frequency Holographic Subsurface Radar: Review and Case Histories

Ivashov¹,

Capineri²,

Bechtel³

et al. 2021

Preprint

0

View full text Add to dashboard Cite

Holographic subsurface radar (HSR) is currently not in widespread usage. This is due to an historical perspective in the ground penetrating radar (GPR) community that the high attenuation of electromagnetic waves in most media of interest, and the inability to apply time-varying gain to the continuous wave (CW) HSR signal precludes sufficient effective penetration depth. While it is true that the fundamental physics of HSR, with its use of a CW signal, does not allow amplification of later (i.e. deeper) arrivals in lossy media (as is possible with impulse subsurface radar — ISR), HSR has distinct some distinctive advantages. The most important of these is the ability to do shallow subsurface imaging with a resolution that is not possible with ISR. In addition, the design of an HSR system is simpler than for ISR due to the relatively low-tech transmitting and receiving antennae. This paper provides a review of the main principles of HSR through an optical analogy and describes possible algorithms for radar hologram reconstruction. We also present a review of the history of development of systems and applications for HSR of the “RASCAN” type which is possibly the only holographic subsurface radar that is produced in lots. Among the subsurface imaging and remote sensing applications considered are humanitarian demining, construction inspection, surveys of historic architecture and artworks, nondestructive testing of dielectric aerospace materials, security applications, paleontology, detection of wood-boring insect damage, and others. Each application is illustrated with relevant data acquired in laboratory and/or field experiments.

show abstract

Fall Detection Using Multiple Bioradars and Convolutional Neural Networks

Cited by 31 publications

References 30 publications

Foot Gesture Recognition Using High-Compression Radar Signature Image and Deep Learning

Foot Gesture Recognition Using High-Compression Radar Signature Image and Deep Learning

Design and Applications of Multi-Frequency Holographic Subsurface Radar: Review and Case Histories

Design and Applications of Multi-Frequency Holographic Subsurface Radar: Review and Case Histories

Contact Info

Product

Resources

About