Radar sensing for human healthcare: challenges and results

Fioranelli, Francesco; Kernec, Julien Le

doi:10.1109/sensors47087.2021.9639702

Cited by 18 publications

(11 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The self-established dataset selected relatively simple activity acquisition patterns, and we will supplement more diverse and larger-scale activity patterns in our future work. Meanwhile, we conducted a comparative experiment to verify the superiority and adaptability of the proposed algorithm through a self-established dataset and a public dataset [ 30 ].…”

Section: Resultsmentioning

confidence: 99%

Radar Human Activity Recognition with an Attention-Based Deep Learning Network

Huan

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Radar-based human activity recognition (HAR) provides a non-contact method for many scenarios, such as human–computer interaction, smart security, and advanced surveillance with privacy protection. Feeding radar-preprocessed micro-Doppler signals into a deep learning (DL) network is a promising approach for HAR. Conventional DL algorithms can achieve high performance in terms of accuracy, but the complex network structure causes difficulty for their real-time embedded application. In this study, an efficient network with an attention mechanism is proposed. This network decouples the Doppler and temporal features of radar preprocessed signals according to the feature representation of human activity in the time–frequency domain. The Doppler feature representation is obtained in sequence using the one-dimensional convolutional neural network (1D CNN) following the sliding window. Then, HAR is realized by inputting the Doppler features into the attention-mechanism-based long short-term memory (LSTM) as a time sequence. Moreover, the activity features are effectively enhanced using the averaged cancellation method, which improves the clutter suppression effect under the micro-motion conditions. Compared with the traditional moving target indicator (MTI), the recognition accuracy is improved by about 3.7%. Experiments based on two human activity datasets confirm the superiority of our method compared to traditional methods in terms of expressiveness and computational efficiency. Specifically, our method achieves an accuracy close to 96.9% on both datasets and has a more lightweight network structure compared to algorithms with similar recognition accuracy. The method proposed in this article has great potential for real-time embedded applications of HAR.

show abstract

Section: Resultsmentioning

confidence: 99%

Radar Human Activity Recognition with an Attention-Based Deep Learning Network

Huan

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…This section describes the proposed approaches for feature extraction, which was not yet implemented but gives some context of the global processing chain, applied to both scenarios of monitoring human activities and gait analysis of specific individuals. For monitoring human activities we extract some features all along the pre-processing chain (from the data matrices) such as: the entropy, the energy curve (mean and variance), the centroid (mean and variance), the bandwidth [15]- [17]. For gait analysis of specific individuals some futher processing from the micro-doppler spectrogram is needed to extract the velocity-time and acceleration-time graph.…”

Section: Extraction Features and Further Processingmentioning

confidence: 99%

Towards Real-Time Implementation for the Pre-Processing of Radar-Based Human Activity Recognition

Bordat

Dobiáš

Kernec

et al. 2022

2022 IEEE 31st International Symposium on Industrial Electronics (ISIE)

View full text Add to dashboard Cite

The rapid aging of the population combined with the correlation between age and the increase in falls pushes us to create new ways to monitor the elderly. The privacy of radar data can respond to one of the weaknesses of existing technologies, but the huge amount of radar data to process becomes a challenge to process. We therefore introduce a first architecture allowing the processing of its data in real time. The radar technology used is an off-the-shelf Frequency Modulated Continuous Wave radar Ancortek (SDR 980AD2). It is followed by a pre-processing chain composed of Fast Fourier Transform, Filter and Short Time Fourier Transform to obtain time-velocity maps or spectrograms allowing the extraction of features from gait and human activities. An encouraging implementation (using SIMD logic) on Jetson Xavier allows us to move to data stream processing. Continuous monitoring of the subject will save lives, minimize injuries, reduce anxiety and prevent post-fall syndrome (PDS).

show abstract

“…Compared to passive sensing using Wi-Fi emissions or their channel state information (CSI), modern radar technology provides an additional degree of freedom in choosing the waveform and beam-forming used in assisted living applications. For all these reasons, radar has gained popularity as a sensing technology to support innovative/personalized healthcare services, including monitoring of daily activity patterns, analysis of gait parameters and imbalances, and prompt detection of critical events such as falls [2]- [8].…”

Section: Introductionmentioning

confidence: 99%

The Human Activity Radar Challenge: Benchmarking Based on the ‘Radar Signatures of Human Activities’ Dataset From Glasgow University

Yang

Kernec

Romain

et al. 2023

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Radar is an extremely valuable sensing technology for detecting moving targets and measuring their range, velocity, and angular positions. When people are monitored at home, radar is more likely to be accepted by end-users, as they already use WiFi, is perceived as privacy-preserving compared to cameras, and does not require user compliance as wearable sensors do. Furthermore, it is not affected by lighting conditions nor requires artificial lights that could cause discomfort in the home environment. So, radar-based human activities classification in the context of assisted living can empower an aging society to live at home independently longer. However, challenges remain as to the formulation of the most effective algorithms for radar-based human activities classification and their validation. To promote the exploration and cross-evaluation of different algorithms, our dataset released in 2019 was used to benchmark various classification approaches. The challenge was open from February 2020 to December 2020. A total of 23 organizations worldwide, forming 12 teams from academia and industry, participated in the inaugural Radar Challenge, and submitted 188 valid entries to the challenge. This paper presents an overview and evaluation of the approaches used for all primary contributions in this inaugural challenge. The proposed algorithms are summarized, and the main parameters affecting their performances are analyzed.

show abstract

Radar sensing for human healthcare: challenges and results

Cited by 18 publications

References 29 publications

Radar Human Activity Recognition with an Attention-Based Deep Learning Network

Radar Human Activity Recognition with an Attention-Based Deep Learning Network

Towards Real-Time Implementation for the Pre-Processing of Radar-Based Human Activity Recognition

The Human Activity Radar Challenge: Benchmarking Based on the ‘Radar Signatures of Human Activities’ Dataset From Glasgow University

Contact Info

Product

Resources

About