Threshold-based fall detection using a hybrid of tri-axial accelerometer and gyroscope

Wang, Fu-Tai; Chan, Hsiao‐Lung; Hsu, Meng‐Hsiang; Lin, C.-C.; Chao, Pei-Kuang; Chang, Ya-Ju

doi:10.1088/1361-6579/aae0eb

Cited by 36 publications

(23 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This review also found that automatic tracking by wearable devices is another common strategy to promote physical activity in older people. Falling and being at risk of falling can in fact be feasibly and accurately detected by wearable devices (e.g., accelerometers and gyroscopes) [76]. Early studies had already shown that fall detectors reduce a person's fear of falling [77].…”

Section: Discussionmentioning

confidence: 99%

The effect of e-health interventions promoting physical activity in older people: a systematic review and meta-analysis

Kwan

Salihu

Lee

et al. 2020

Eur Rev Aging Phys Act

View full text Add to dashboard Cite

Introduction: The objectives of this review paper were to synthesize the data from randomized controlled trials in the literature to come to a conclusion on the effects of e-health interventions on promoting physical activity in older people. Methods: The Medline, CINAHL, Embase, PsycINFO, and SportDiscus databases were searched for articles about studies that 1) recruited subjects with a mean age of > 50 years, 2) tested e-health interventions, 3) employed control groups with no or less advanced e-health strategies, 4) measured physical activity as an outcome, 5) were published between 1st January 2008 and 31st May 2019, and 6) employed randomized controlled trials. The risk of bias in individual studies was assessed using the Physiotherapy Evidence Database scale. To examine the effects of the interventions, variables quantifying the amount of physical activity were extracted. The within-group effects of individual studies were summarized using Hedges g and 95% confidence intervals. Between-group effects were summarized by meta-analyses using RevMan 5.0 with a random effect model. Results: Of the 2810 identified studies, 38 were eligible, 25 were included in the meta-analyses. The within-group effect sizes (Hedges g) of physical activity in the intervention group at T1 ranged from small to large: physical activity time (0.12 to 0.84), step counts (− 0.01 to 11.19), energy expenditure (− 0.05 to 0.86), walking time (0.13 to 3.33), and sedentary time (− 0.12 to − 0.28). The delayed effects as observed in T2 and T3 also ranged from small to large: physical activity time (0.24 to 1.24) and energy expenditure (0.15 to 1.32). In the meta-analysis, the betweengroup effect of the e-health intervention on physical activity time measured by questionnaires, physical activity time measured by objective wearable devices, energy expenditure, and step counts were all significant with minimal heterogeneity. Conclusion: E-health interventions are effective at increasing the time spent on physical activity, energy expenditure in physical activity, and the number of walking steps. It is recommended that e-health interventions be included in guidelines to enhance physical activity in older people. Further studies should be conducted to determine the most effective e-health strategies.

show abstract

Section: Discussionmentioning

confidence: 99%

The effect of e-health interventions promoting physical activity in older people: a systematic review and meta-analysis

Kwan

Salihu

Lee

et al. 2020

Eur Rev Aging Phys Act

View full text Add to dashboard Cite

show abstract

“…Wang et al, in [33], present a fall classification methodology based on two new inertial parameters: acceleration cubic-product-root magnitude (ACM) and angular velocity cubic-product-root magnitude (AVCM). These indexes have been introduced to improve the selectivity of threshold-based fall detection methods, and evaluate strategies to distinguish falls from other activities of daily life (ADLs).…”

Section: Customized Systemsmentioning

confidence: 99%

Advanced Solutions Aimed at the Monitoring of Falls and Human Activities for the Elderly Population

et al. 2019

View full text Add to dashboard Cite

Ageing is a global phenomenon which is pushing the scientific community forward the development of innovative solutions in the context of Active and Assisted Living (AAL). Among functionality to be implemented, a major role is covered by falls and human activities monitoring. In this paper, main technological solutions to cope with the aforementioned needs are briefly introduced. A specific focus is given on solutions for Falls recognition and classification. A case of study is presented, where a classification methodology based on an event-driven correlation paradigm and an advanced threshold-based classifier is addressed. The receiver operating characteristic (ROC) theory is used to properly define thresholds’ values while, in order to properly assess performances of the classification methodology proposed, dedicated metrics are suggested, such as sensitivity and specificity. The solution proposed shows an average Sensitivity of 0.97 and an average Specificity of 0.99.

show abstract

“…As alternatives, accelerometers combined with surface electromyography sensors [26], gyroscopes [22], [23], or various bio-signal sensors, including those used to record electrical activity of the heart, blood pressure, pulse oximetry, respiration rate, and body surface temperature [27]. Among these various options, we have chosen a heart rate sensor because higher accuracy levels have been achieved to an extent using a multi-dimensional combination of physiological and kinematic parameters [15].…”

Section: Introductionmentioning

confidence: 99%

Cluster-Analysis-Based User-Adaptive Fall Detection Using Fusion of Heart Rate Sensor and Accelerometer in a Wearable Device

2020

View full text Add to dashboard Cite

This paper proposes an automatic fall detector in a wearable device that can reduce risks by detecting falls and promptly alerting caregivers. For this purpose, we propose cluster-analysis-based useradaptive fall detection using a fusion of heart rate sensor and accelerometer. The objectives of the proposed fall detector are to have high accuracy with a low-complexity model regardless of diverse conditions. To meet the objectives, we propose the best 13-dimensional feature subset by using feature selection. In addition, we verify the performance increment of combining a heart rate sensor with an accelerometer and the effectiveness of the cluster-analysis-based anomaly detection. We also show the effectiveness of the useradaptive method when using both heart rate and acceleration signals that were hardly covered in other papers. Finally, we prove that the performance of the proposed fall detector achieves is better than that of recent useradaptive and user-independent approaches. This study is the first attempt to demonstrate the merits of the user-adaptive approach using a combination of heart rate and acceleration signals to detect falls. Moreover, this paper also contributes to fall detection area by providing the data we collected.

show abstract

Threshold-based fall detection using a hybrid of tri-axial accelerometer and gyroscope

Abstract: Using multiple inertial parameters improves the specificity of fall detection.

Cited by 36 publications

References 30 publications

The effect of e-health interventions promoting physical activity in older people: a systematic review and meta-analysis

The effect of e-health interventions promoting physical activity in older people: a systematic review and meta-analysis

Advanced Solutions Aimed at the Monitoring of Falls and Human Activities for the Elderly Population

Cluster-Analysis-Based User-Adaptive Fall Detection Using Fusion of Heart Rate Sensor and Accelerometer in a Wearable Device

Contact Info

Product

Resources

About