Healthcare System for Non-invasive Fall Detection in Indoor Environment

Mercuri, Mario; Garripoli, Carmine; Karsmakers, Peter; Soh, Ping Jack; Vandenbosch, Guy A. E.; Pace, Calogero; Leroux, Paul; Schreurs, Dominique

doi:10.1007/978-3-319-20227-3_19

Cited by 7 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The elderly population is on the rise, leading to a substantial decline in nursing home capacity. [5,6]. The elderly population is set to be 2.1 billion in the year 2050 according to statistics from the United Nations [7,8].…”

Section: Introductionmentioning

confidence: 99%

An Intelligent Non-Invasive Real-Time Human Activity Recognition System for Next-Generation Healthcare

Taylor

Shah

Dashtipour

et al. 2020

Sensors

132

View full text Add to dashboard Cite

Human motion detection is getting considerable attention in the field of Artificial Intelligence (AI) driven healthcare systems. Human motion can be used to provide remote healthcare solutions for vulnerable people by identifying particular movements such as falls, gait and breathing disorders. This can allow people to live more independent lifestyles and still have the safety of being monitored if more direct care is needed. At present wearable devices can provide real-time monitoring by deploying equipment on a person’s body. However, putting devices on a person’s body all the time makes it uncomfortable and the elderly tend to forget to wear them, in addition to the insecurity of being tracked all the time. This paper demonstrates how human motions can be detected in a quasi-real-time scenario using a non-invasive method. Patterns in the wireless signals present particular human body motions as each movement induces a unique change in the wireless medium. These changes can be used to identify particular body motions. This work produces a dataset that contains patterns of radio wave signals obtained using software-defined radios (SDRs) to establish if a subject is standing up or sitting down as a test case. The dataset was used to create a machine learning model, which was used in a developed application to provide a quasi-real-time classification of standing or sitting state. The machine-learning model was able to achieve 96.70% accuracy using the Random Forest algorithm using 10 fold cross-validation. A benchmark dataset of wearable devices was compared to the proposed dataset and results showed the proposed dataset to have similar accuracy of nearly 90%. The machine-learning models developed in this paper are tested for two activities but the developed system is designed and applicable for detecting and differentiating x number of activities.

show abstract

Section: Introductionmentioning

confidence: 99%

An Intelligent Non-Invasive Real-Time Human Activity Recognition System for Next-Generation Healthcare

Taylor

Shah

Dashtipour

et al. 2020

Sensors

132

View full text Add to dashboard Cite

show abstract

“…Given this lack of training data, there may be no or little training data for falls, and it will hard to employ supervised classification techniques. There are also concerns that the sensing devices for the task of fall detection may be invasive and breach the privacy of the person [19,32]. Some non-invasive sensing devices, such as a thermal or depth camera, may not fully reveal the identity of a person, but it is difficult to extract discriminative features to identify unseen falls, especially in a highly skewed data scenario [27].…”

Section: Introductionmentioning

confidence: 99%

DeepFall: Non-Invasive Fall Detection with Deep Spatio-Temporal Convolutional Autoencoders

Nogas

Khan

Mihailidis

2019

J Healthc Inform Res

View full text Add to dashboard Cite

Human falls rarely occur; however, detecting falls is very important from the health and safety perspective. Due to the rarity of falls, it is difficult to employ supervised classification techniques to detect them. Moreover, in these highly skewed situations it is also difficult to extract domain specific features to identify falls. In this paper, we present a novel framework, DeepFall, which formulates the fall detection problem as an anomaly detection problem. The DeepFall framework presents the novel use of deep spatio-temporal convolutional autoencoders to learn spatial and temporal features from normal activities using non-invasive sensing modalities. We also present a new anomaly scoring method that combines the reconstruction score of frames across a video sequences to detect unseen falls. We tested the DeepFall framework on three publicly available datasets collected through non-invasive sensing modalities, thermal camera and depth cameras and show superior results in comparison to traditional autoencoder and convolutional autoencoder methods to identify unseen falls.

show abstract

“…In answering RQ2, the searches and screening process resulted in thirteen articles to be critically appraised. Twelve [46][47][48][49][50][51][52][53][54][55][56][57] of the thirteen studies demonstrated medium to high quality, as the twelve studies had information to answer all criteria in the MMAT, with the thirteenth [56] study falling short of answering S2 and the rest of the criteria. The research hypothesis of these twelve studies was clear and relevant, focusing on vibration and/or acoustic sensing technologies in monitoring human activities.…”

Section: Critical Appraisal and Overview Of Studies Includedmentioning

confidence: 99%

Acceptability of Remote Monitoring in Assisted Living/Smart Homes in the United Kingdom and Associated Use of Sounds and Vibrations—A Systematic Review

Tong,

Attenborough,

Sharp

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The ageing of populations is increasing pressure on health and social care systems. Potentially, assistive technologies are a way to support the independence of older adults in their daily activities. Among existing assistive technologies, ambient sensing technologies have received less attention than wearable systems. Moreover, there has been little research into cheaper technologies capable of using multiple modalities. A systematic review of the acceptability of assisted living or smart homes in the United Kingdom and the simultaneous use of sounds and vibrations in remote monitoring of assisted living or smart homes will inform and encourage the use of digital monitoring technologies. The acceptability of sensing technologies depends on whether there is any social stigma about their use, for example, the extent to which they invade privacy. The United Kingdom studies reviewed suggest a lack of measurements of the perceived efficacy or effectiveness of the monitoring devices. The primary use of vibration or acoustic technologies has been for detecting falls rather than monitoring health. The review findings suggest the need for further exploration of the acceptability and applicability of remote monitoring technologies, as well as a need for more research into the simultaneous use of sounds and vibrations in health monitoring.

show abstract

Healthcare System for Non-invasive Fall Detection in Indoor Environment

Cited by 7 publications

References 8 publications

An Intelligent Non-Invasive Real-Time Human Activity Recognition System for Next-Generation Healthcare

An Intelligent Non-Invasive Real-Time Human Activity Recognition System for Next-Generation Healthcare

DeepFall: Non-Invasive Fall Detection with Deep Spatio-Temporal Convolutional Autoencoders

Acceptability of Remote Monitoring in Assisted Living/Smart Homes in the United Kingdom and Associated Use of Sounds and Vibrations—A Systematic Review

Contact Info

Product

Resources

About