Recognizing activities of daily living from UWB radars and deep learning

Maître, Julien; Bouchard, Kévin; Bertuglia, Camille; Gaboury, Sébastien

doi:10.1016/j.eswa.2020.113994

Cited by 49 publications

(26 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The collected data were run using 10-fold cross validation and it was found that KNN performed the best with a result of 94.90% accuracy. The authors of [ 27 ] used UWB radars to collect data for binary classification of falling and non-falling events. Data were collected using 10 volunteers in three different locations within a proposed apartment.…”

Section: Related Workmentioning

confidence: 99%

Radar Sensing for Activity Classification in Elderly People Exploiting Micro-Doppler Signatures Using Machine Learning

Taylor

Dashtipour

Shah

et al. 2021

Sensors

View full text Add to dashboard Cite

The health status of an elderly person can be identified by examining the additive effects of aging along with disease linked to it and can lead to ‘unstable incapacity’. This health status is determined by the apparent decline of independence in activities of daily living (ADLs). Detecting ADLs provides possibilities of improving the home life of elderly people as it can be applied to fall detection systems. This paper presents fall detection in elderly people based on radar image classification by examining their daily routine activities, using radar data that were previously collected for 99 volunteers. Machine learning techniques are used classify six human activities, namely walking, sitting, standing, picking up objects, drinking water and fall events. Different machine learning algorithms, such as random forest, K-nearest neighbours, support vector machine, long short-term memory, bi-directional long short-term memory and convolutional neural networks, were used for data classification. To obtain optimum results, we applied data processing techniques, such as principal component analysis and data augmentation, to the available radar images. The aim of this paper is to improve upon the results achieved using a publicly available dataset to further improve upon research of fall detection systems. It was found out that the best results were obtained using the CNN algorithm with principal component analysis and data augmentation together to obtain a result of 95.30% accuracy. The results also demonstrated that principal component analysis was most beneficial when the training data were expanded by augmentation of the available data. The results of our proposed approach, in comparison to the state of the art, have shown the highest accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Radar Sensing for Activity Classification in Elderly People Exploiting Micro-Doppler Signatures Using Machine Learning

Taylor

Dashtipour

Shah

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…With a result of 94 percent accuracy, the obtained data were processed through 10-fold cross-validation technique and it was discovered that KNN performed better. In [44], authors acquired data for binary classification of non-falling and falling incidents using UWB RADAR. Ten volunteers were used to collect data in three distinct areas within the proposed residence.…”

Section: Related Workmentioning

confidence: 99%

Portable UWB RADAR Sensing System for Transforming Subtle Chest Movement Into Actionable Micro-Doppler Signatures to Extract Respiratory Rate Exploiting ResNet Algorithm

et al. 2021

View full text Add to dashboard Cite

Contactless or non-invasive technology for the monitoring of anomalies in an inconspicuous and distant environment has immense significance in health-related applications, in particular COVID-19 symptoms detection, diagnosis, and monitoring. Contactless methods are crucial specifically during the COVID-19 epidemic as they require the least amount of involvement from infected individuals as well as healthcare personnel. According to recent medical research studies regarding coronavirus, individuals infected with novel COVID-19-Delta variant undergo elevated respiratory rates due to extensive infection in the lungs. This appalling situation demands constant real-time monitoring of respiratory patterns, which can help in avoiding any pernicious circumstances. In this paper, an Ultra-Wideband RADAR sensor "XeThru X4M200" is exploited to capture vital respiratory patterns. In the low and high frequency band, X4M200 operates within the 6.0-8.5 GHz and 7.25-10.20 GHz band, respectively. The experimentation is conducted on six distinct individuals to replicate a realistic scenario of irregular respiratory rates. The data is obtained in the form of spectrograms by carrying out normal (eupnea) and abnormal (tachypnea) respiratory. The collected spectrogram data is trained, validated, and tested using a cutting-edge deep learning technique called Residual Neural Network or ResNet. The trained ResNet model's performance is assessed using the confusion matrix, precision, recall, F1-score, and classification accuracy. The unordinary skip connection process of the deep ResNet algorithm significantly reduces the underfitting and overfitting problem, resulting in a classification accuracy rate of up to 90%.

show abstract

“…The antenna has been used for the application of monitoring perforations in an oil well wall. In [46] authors have examined the feasibility of living in smart homes integrating UWB technology with deep learning for the elderly. Recognition of activities performed by seniors is done using three UWB radars along with a deep learning model and a voting system.…”

Section: Uwb Antenna Technologymentioning

confidence: 99%

Ultrawideband Antennas: Growth and Evolution

Kumar

Ali

et al. 2021

Micromachines

View full text Add to dashboard Cite

Narrowband antennas fail to radiate short pulses of nano- or picosecond length over the broader band of frequencies. Therefore, Ultrawideband (UWB) technology has gained momentum over the past couple of years as it utilizes a wide range of frequencies, typically between 3.1–10.6 GHz. UWB antennas have been utilized for various applications such as ground-penetrating radars, disaster management through detection of unexploded mines, medical diagnostics, and commercial applications ranging from USB dongles to detection of cracks in highways and bridges. In the first section of the manuscript, UWB technology is detailed with its importance for future wireless communications systems. In the next section various types of UWB antennas and their design methodology are reviewed, and their important characteristics are highlighted. In section four the concept of a UWB notch antenna is presented. Here various methods to obtain the notch, such as slots, parasitic resonators, metamaterials, and filters are discussed in detail. In addition, various types of important notch antenna design with their technical specifications, advantages, and disadvantages are presented. Finally, the need of reconfigurable UWB notch antennas is discussed in the next section. Here various insight to the design of frequency reconfigurable notch antennas is discussed and presented. Overall, this article aims to showcase the beginnings of UWB technology, the reason for the emergence of notching in specific frequency bands, and ultimately the need for reconfiguring UWB antennas along with their usage.

show abstract

Recognizing activities of daily living from UWB radars and deep learning

Cited by 49 publications

References 39 publications

Radar Sensing for Activity Classification in Elderly People Exploiting Micro-Doppler Signatures Using Machine Learning

Radar Sensing for Activity Classification in Elderly People Exploiting Micro-Doppler Signatures Using Machine Learning

Portable UWB RADAR Sensing System for Transforming Subtle Chest Movement Into Actionable Micro-Doppler Signatures to Extract Respiratory Rate Exploiting ResNet Algorithm

Ultrawideband Antennas: Growth and Evolution

Contact Info

Product

Resources

About