Elderly care: activities of daily living classification with an
            <i>S</i>
            band radar

Shrestha, Ashish; Kernec, Julien Le; Fioranelli, Francesco; Lin, Yier; He, Qian; Lorandel, Jordane; Romain, Olivier

doi:10.1049/joe.2019.0561

Cited by 7 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…scale were used to identify the possibility of a fall; second, the WT coefficients at several scales across many successive frames were employed to form the feature vectors for the classification of fall and nonfall activities. Shrestha et al introduced another S-band radar system for classifying the elderly's activities in daily life [22]. The authors used the traditional fast Fourier transform (FFT) to generate spectrograms from raw data, by which a series of time-frequency features can be extracted (and selected) for training an SVM model.…”

Section: Sensorsmentioning

confidence: 99%

“…[18] Sensors Correlation LDA WAR: 95% The correlation is a simple but effective feature for gait analysis; the curvature radius of Parkinson's subjects is smaller than that of healthy subjects. [22] Sensors FFT SVM WAR: 90% Matching frequency bands to human movements during feature extraction is important for classifying specific events, e.g., falls.…”

Section: Health-care Managementmentioning

confidence: 99%

“…Their frequently used features, i.e., MFCCs [3], and more sophisticated large-scale feature sets (COMPARE [4], [5]), are based on the STFT approach. Moreover, for radar signal analysis, the STFT is a powerful tool [22]. The assumption of the STFT is that a longer-duration nonstationary signal can be divided into a series of stationary signals with shorter lengths (segments), which can be suitable for separately conducting FT in each segment to reveal frequency domain information.…”

Section: Classic MLmentioning

confidence: 99%

See 2 more Smart Citations

Artificial Intelligence Internet of Things for the Elderly: From Assisted Living to Health-Care Monitoring

Qian

Yamamoto

Schuller

2021

IEEE Signal Process. Mag.

View full text Add to dashboard Cite

Section: Sensorsmentioning

confidence: 99%

Section: Health-care Managementmentioning

confidence: 99%

Section: Classic MLmentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence Internet of Things for the Elderly: From Assisted Living to Health-Care Monitoring

Qian

Yamamoto

Schuller

2021

IEEE Signal Process. Mag.

View full text Add to dashboard Cite

“…Therefore, how to ensure the quality of life of the elderly and establish a complete medical and elderly care system will be a great challenge in China and in the world. In the daily life of the elderly, there are often unexpected falls or abnormal behaviours caused by diseases, which can be life-threatening in the case of unattended [11]. Thus, it is necessary to monitor Activities of Daily Living (ADL) of the elderly through equipment.…”

Section: Introductionmentioning

confidence: 99%

Bespoke Simulator for Human Activity Classification with Bistatic Radar

Yang

Abbasi

Fioranelli

et al. 2022

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

Self Cite

View full text Add to dashboard Cite

Radar is now widely used in human activity classification because of its contactless sensing capabilities, robustness to light conditions and privacy preservation compared to plain optical images. It has great value in elderly care, monitoring accidental falls and abnormal behaviours. Monostatic radar suffers from degradation in performance with varying aspect angles with respect to the target. Bistatic radar may offer a solution to this problem but finding the right geometry can be quite resource-intensive. We propose a bespoke simulation framework to test the radar geometry for human activity recognition. First, the analysis focuses on the monostatic radar model based on the Doppler effect in radar. We analyse the spectrogram of different motions by Short-time Fourier analysis (STFT), and then the classification data set was built for feature extraction and classification. The results show that the monostatic radar system has the highest accuracy, up to 98.17%. So, a bistatic radar model with separate transmitter and receiver was established in the experiment, and results show that bistatic radar with specific geometry configuration (CB2.5) not only has higher classification accuracy than monostatic radar in each aspect angle but also can recognise the object in a wider angle range. After training and fusing the data of all angles, it is found that the accuracy, sensitivity, and specificities of CB2.5 have 2.2%, 7.7% and 1.5% improvement compared with monostatic radar.

show abstract

“…There are few technologies used in HAR like cameras, various wearable sensors, ambient sensors, and radar. Compared with the camera and some other types of sensors, radar systems are versatile, contactless, and are perceived as non-intrusive [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

Complex field-based fusion network for human activities classification with radar

Guo¹,

Shu²,

Zhou³

et al. 2021

IET Conf. Proc.

View full text Add to dashboard Cite

In the context of assisted living, human activity recognition (HAR) is of increased importance to maintain people at home living independently longer. Compared with directly using spectrograms (µD) or range profiles (RP) as inputs for classification discarding either range or explicit Doppler information, range-Doppler-surface (RDS) can more fully represent the information contained in the observed activities. However, because the data are collected from di↵erent activities, people, and locations, the RDS has a requires non-trivial adjustments for pre-processing as discussed in this paper to maintain the number of points in the RDS to fixed integer. Although it has improved performance ( 92%) compared to CNN ( 90%), this algorithm also discards phase information as most algorithms do in HAR with radar. In contrast, the phase information of the range-Doppler domain, although its performance was not the best ( 88%), it had no obvious weakness in the recognition of all the movements. Our proposed complex field-based fusion network (CFFN) combines the amplitude and phase which improves both the accuracy of classification ( 94%) as well as accelerating training time by 12.5%.

show abstract

Elderly care: activities of daily living classification with an S band radar

Cited by 7 publications

References 34 publications

Artificial Intelligence Internet of Things for the Elderly: From Assisted Living to Health-Care Monitoring

Artificial Intelligence Internet of Things for the Elderly: From Assisted Living to Health-Care Monitoring

Bespoke Simulator for Human Activity Classification with Bistatic Radar

Complex field-based fusion network for human activities classification with radar

Contact Info

Product

Resources

About