Elderly Fall Detection Using Wearable Sensors: A Low Cost Highly Accurate Algorithm

Saleh, Majd; Jeannès, Régine Le Bouquin

doi:10.1109/jsen.2019.2891128

Cited by 103 publications

(56 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Otherwise, an acceleration's peak signal is trained by supervised learning [11], [12]. Several approaches using binary classifiers of support vector machine (SVM) [12], [13], [17], [25], k-nearest neighbors [25], [30], and feed forward neural network (NN) [10], [11] have been proposed for detecting fall signals.…”

Section: B Cluster-analysis-based Anomaly Detectionmentioning

confidence: 99%

“…We gathered 8280 non-fall and 2458 fall segmented windows from all subjects. In the case of the user-independent approach for the comparison group [10], [11], [17], [25], [42], the 8280 non-fall and 2458 fall windows are divided into 10-equal sized groups. For example, one group consisting of 828 non-fall and 246 fall segmented windows is taken as a test dataset.…”

Section: Evaluation Criteriamentioning

confidence: 99%

“…In addition, wearable devices are essential because many elderly people want to live autonomously at home without locational restrictions [16]. Wearable-based fall detection systems typically use accelerometers [6]- [13], [17]- [19], gyroscopes [20], heart rate sensors [21], or a combination of these [22]- [25]. Recently, several smartwatches have started to provide fall detection services.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Section: B Cluster-analysis-based Anomaly Detectionmentioning

confidence: 99%

Section: Evaluation Criteriamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

show abstract

“…Though this system provides better results, the computation complexity will increase accordingly, when the sampling interval between two consecutive clips increases and even some frames of fall event may get missed. Maid Saleh [2] et al proposes a low cost, highly accurate and wearable system for fall detection. This system mounts a wearable device over the waist where the activity of the elderly is captured using 3-axial accelerometer.…”

Section: Literature Surveymentioning

confidence: 99%

Survey on Fall Detection System CNN based Fall Detection and Health Monitoring System using IOT

Geetha¹

2020

IJRASET

View full text Add to dashboard Cite

Falls are the common problem faced by elderly population. Fall may happen due to fainting. The reason for faint involves sudden changes in the heart rate. Falls are the common cause of traumatic brain injuries in elderly people and also cause severe injuries such as fracture of the hip. This kind of injuries can create negative impact on their quality of life. In most of the cases the elderly who lay on the floors for more than an hour after falls usually results in serious trauma, also leads to death of the individuals. There are some systems exist for detecting the falls of the elderly people. These ambient sensors involve video-based methods for fall detection using rule based and machine learning based methods. The wearable sensor mainly include accelerometer, gyroscope, barometric pressure sensor, infrared sensor and kinetic RGBD camera. The existing systems are based upon the ambient sensors faces some risks such as storage and processing of video is a complex task and it also affects the privacy of the people. It is necessary to propose a system that can overcome the above drawbacks. The system proposed involves capturing the motion of the elderly people using accelerometer sensors. Those captured data via sensors are processed using CNN, which involve steps such as convolution, it results in feature map then it has to be down sampled using the max pooling methods and based on the resultant layers, the captured motion can be determined whether it is a day to day activities or a fall. Once the fall is detected the information will be sent to the family members and neighbours. Additionally, it is provided with sensor to monitor the health conditions of the elderly people, when heart rate deteriorates, an alert message will be sent to neighbours and family members to provide medical assistance.

show abstract

“…Many models have been proposed by researchers to detect human fall, but the researchers always determine/ limit the position of smartphone that has been carried by people who use fall detection. This situation is not in accordance with real life condition because people will usually put their smartphone freely in any position they want [10].…”

Section: Introductionmentioning

confidence: 96%

Ans-Assist: Robust Human Fall Detection for Unconstraint Smartphone Positions using Modified Long Short-Term Memory Cell

Astriani*,

Heryadi,

Kusuma

et al. 2019

IJRTE

View full text Add to dashboard Cite

In many aging countries, where the population distribution has shifted to old ages, the need for automatic monitoring devices to help an elderly person when they fall is very crucial. Smartphone is one of the best candidate devices for detecting fall because accelerometer and gyroscope sensors embedded in it respond based on human movements. People usually carry their smartphone in any position and can make fall detection method difficult to detect when fall occurs. This research explored the model for unconstraint human fall detection by using the sensors embedded in smartphone for carried/wearable- sensor-based method. We proposed robust model called Ans-Assist using modified cell of Long Short-Term Memory based model as fall recognition model which can detect human fall from any smartphone position (unconstraint). Some experimental results showed that Ans-Assist achieved 0.95 (± 0.028) average accuracy value using unconstraint smartphone positions. This model can adapt the input from accelerometer and gyroscope sensors which are responsive when human fall.

show abstract

Elderly Fall Detection Using Wearable Sensors: A Low Cost Highly Accurate Algorithm

Cited by 103 publications

References 24 publications

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

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

Survey on Fall Detection System CNN based Fall Detection and Health Monitoring System using IOT

Ans-Assist: Robust Human Fall Detection for Unconstraint Smartphone Positions using Modified Long Short-Term Memory Cell

Contact Info

Product

Resources

About