Abstract
Monitoring the activity of elderly individuals in nursing homes is key, as it has been shown that physical activity leads to significant health improvement. In this work, we introduce NurseNet, a system that combines an unobtrusive, affordable, and robust piezoelectric floor sensor with a convolutional neural network algorithm, which aims at measuring elderly physical activity. Our algorithm is trained using signal embedding based on atoms of a pre-learned dictionary and focuses the network’s attention on step-related signals. We show that NurseNet is able to avoid the main limitation of floor sensors by recognizing relevant signals (i.e., signals produced by patients) and ignoring events related to the medical staff, offering a new tool to monitor elderly activity in nursing homes efficiently.
Highlights
We present the floor sensor that was used in N URSE N ET
The accuracy of N URSE N ET is studied over each subgroup of our database, and we take a closer look at misclassified signals
A complete ablation analysis is done to show the relative improvement added by each part of the algorithm, and our approach is compared to a another robust off-the-shelf classification algorithm
Summary
The notion of frailty has received increased attention from the medical community as an early sign of significant health deterioration in the elderly population [1,2]. People living in elderly care facilities are more likely to have disabilities than other elderly people They tend to be more isolated from the rest of the population and do less physical activity than the general elderly population [5]. The lack of exercise is damaging, as it has been shown that physical activity reduces muscle weakness, increases mobility, improves neuronal health, limits frailty, and reduces overall risk of death [6,7]. The monitoring physical activity of the elderly in nursing homes is key, as it allows focusing resources on people who are vulnerable to frailty
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
