Classification of Human Postures Using Ultra-Wide Band Radar Based on Neural Networks

Kiasari, Mohammad Ahangar; Na, Seung You; Kim, Jin Young

doi:10.1109/icitcs.2014.7021751

Cited by 8 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To avoid such drawbacks, deep learning methods were adopted to extract the appropriate motion characters automatically [15][16][17][18][19][20][21]. Convolutional neural network (CNN) is one of the most utilized deep learning structures to improve the classification accuracy for multiple human motion types [22].…”

Section: Introductionmentioning

confidence: 99%

Human Motion Serialization Recognition With Through-the-Wall Radar

Yang

Chen

Wang³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Motivated by the intrinsic dynamics of physical motion as well as establishment of target motion model, this paper addresses the problem of human motion recognition with ultra wide band (UWB) through-the-wall radar (TWR) in a novel view of range profile serialization. Specifically, we first convert the original radar echoes into range profiles. Then, an auto-encoder network (AEN) with three dense layers is adopted to reduce the dimension and extract the features of each range profile. After that, a gated recurrent unit (GRU) network with two hidden layers is employed to deal with the features of each time-range slice and output the recognition results at each slice in real time. Finally, experimental data with respect to four different behind-wall human motions is collected by self-developed UWB TWR to validate the effectiveness of the proposed model. The results show that the proposed model can validly recognize the human motion serialization and achieve 93% recognition accuracy within the initial 20% duration of the activities (the average durations are 4s, 5.5s, 3s and 4.5s), which is of great significance for real-time human motion recognition. INDEX TERMS Human motion recognition, ultra wide band through-the-wall radar, auto-encoder network, gated recurrent unit.

show abstract

Section: Introductionmentioning

confidence: 99%

Human Motion Serialization Recognition With Through-the-Wall Radar

Yang

Chen

Wang³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Classification of postures and activities using a single CW or UWB radar as a precursor to vital sign estimation. The posture classification for UWB is novel and is an improvement in classification accuracy compared to the only existing algorithm in literature [8].…”

Section: Contributionsmentioning

confidence: 99%

“…A radar-video fusion system was presented which used radar for initial location of the subject, but video processing alone was used for posture classification [32]. Classification of posture using an IR-UWB radar was performed by Ahangar-Kiasari et al with 86% accuracy for standing, 83% accuracy for sitting and 80% accuracy for lying postures [8]. This work extracted statistical features from the first 10 principal components of the radar return signals and used them for training a neural network.…”

Section: Posture Classificationmentioning

confidence: 99%

“…Ahangar-Kiasari et al used PCA to classify human postures using a neural network classifier [8]. They computed the first 10 PCs from each sample.…”

Section: Occupancy Detectionmentioning

confidence: 99%

“…For posture classification using UWB radar, data in which the subject was moving and is recorded at greater distances from the radar [8].…”

Section: Posture Classificationmentioning

confidence: 99%

See 2 more Smart Citations

Human Activity and Posture Classification Using Single Non-Contact Radar Sensor

Baird¹

View full text Add to dashboard Cite

Radar has been proposed for monitoring the health of elderly patients in long term care because it is safe, non-contact and preserves the privacy of patients. Random body movements (RBM) obscure radar return signals making it difficult if not impossible to accurately estimate vitals. Activity classification is presented in this thesis as a preprocessing step for dealing with RBMs. Posture classification is presented in this thesis for assistance in preventing falls. Two popular radar architectures-continuous wave (CW) Doppler and ultra-wideband (UWB) are investigated in this thesis. Activity classification is performed with 92% average accuracy with CW and 86% with UWB.Posture Classification is performed with 64% average accuracy with CW and 85% with UWB. An occupancy detection algorithm was also developed for UWB and achieved 88% average accuracy. The contribution of this thesis is a proposed hierarchical processing approach for both radar types capable of dealing with moving subjects.iii

show abstract

Machine Learning for Healthcare Radars: Recent Progresses in Human Vital Sign Measurement and Activity Recognition

Ahmed,

Cho

2024

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

The unprecedented non-contact, non-invasive, and privacy-preserving nature of radar sensors has enabled various healthcare applications, including vital sign monitoring, fall detection, gait analysis, activity recognition, fitness evaluation, and sleep monitoring. Machine learning (ML) is revolutionizing every domain, with radar-based healthcare being no exception. Progress in the field of healthcare radars and ML is complementing the existing radar-based healthcare industry. This article provides an overview of ML usage for two major healthcare applications: vital sign monitoring and activity recognition. Vital sign monitoring is the most promising healthcare application of radar, as it can predict several chronic cardiac and respiratory diseases. Activity recognition is also a prominent application since the inability to perform activities may result in critical suffering. The article presents an overview of commercial radars, radar hardware, and historical progress of healthcare radars, followed by the usage of ML for healthcare radars. Subsequently, the paper discusses how ML can overcome the limitations of conventional radar data processing chains for healthcare radars. The article also touches upon recent generative ML concepts used in healthcare radars. Among several interesting findings, it was discovered that ML does not completely replace existing vital sign monitoring algorithms; rather, ML is deployed to overcome the limitations of traditional algorithms. On the other hand, activity recognition always relies on ML approaches. The most widely used algorithms for both applications are Convolutional Neural Network (CNN) followed by Support Vector Machine (SVM). Generative AI has the capability to augment data and is expected to have a significant impact soon. Recent trends, lessons learned from these trends, and future directions for both healthcare applications are presented in detail. Finally, the future work section discusses a wide range of healthcare topics for humans, ranging from neonates to elderly individuals.

show abstract

Classification of Human Postures Using Ultra-Wide Band Radar Based on Neural Networks

Cited by 8 publications

References 10 publications

Human Motion Serialization Recognition With Through-the-Wall Radar

Human Motion Serialization Recognition With Through-the-Wall Radar

Human Activity and Posture Classification Using Single Non-Contact Radar Sensor

Machine Learning for Healthcare Radars: Recent Progresses in Human Vital Sign Measurement and Activity Recognition

Contact Info

Product

Resources

About