Affordable falls detection equipment / hardware for the home
I’m interested to know what affordable technologies exist for the home environment that can assist with falls detection. I’m looking for something not too expensive that operates in multiple rooms in an elderly person’s home and what level of functionality is offered
I’m not able to answer your question but according to our experience, although using sensors around the home that can register any movement of the older person at home can be very interesting from a research point of view, older people can feel it very invasive.
There is a group at the University of Manchester developing a “Magic Carpet” system to detect falls which can be retrofitted to older people’s homes. It is a carpet using fibre optic technologies which when commercialised should prove to be fairly cheap. see their website for more information http://www.mub.eps.manchester.ac.uk/imagimat/
The University of Manchester team feature in a Reuters video in the link below.
we have a stand at the current EU Falls festival in Stuttgart.
It is also relevant here that the ENOFALLS project is building a repository of ICT solutions for prevention and monitoring of Falls http://www.e-nofalls.eu/ictrepository/. This mainly contains solutions that are already on the market – categorised by whether they are for prevention or detection and within that, categorised as Home systems, smartphone apps and wearable systems. So it should be possible to search for Home systems for falls detection and see what is available.
University of Manchester
Manchester M13 9PL
This report from the European Commission’s Joint Research Centre, delivered as part of the Long-Term Care Strategies for Independent Living of Older People (ICT-AGE) project, contains some interesting lessons on implementing long-term care policy strategies using technology-enabled services to help older adults
to live at home independently. Examples of technologies used, and the classification of these services are outlined, and includes details of the Home Automation and Telecare Programme (ESOPPE Project, Limousin Region, Department de la Corrèze, France), one of the Profound reference sites.
We would like to refer to the following projects:
iMinds ICON FallRisk project
During the FallRisk project non-stigmatizing, holistic services in view of the automated follow up of fallrisk and the multi-sensor and contextual detection of fall incidents were developed. Secondly a context-aware and social-aware selection algorithm was developed to support the dynamic and optimum forwarding of FallRisk events or alarms towards the (in)formal caregiver network. This back-end system handled the event forwarding in view of the context of the event (e.g. day or night / bathroom or kitchen, classification of events) and in view of the social-network of the elderly (proximity and availability of (in)formal caregiver, circles of trust, etc).
During the FallRisk project 4 sensor systems were installed with 3 older adults living alone and one couple. The measurements from these sensors were used to develop a system that can automatically assess the fall risk of a person and detect fall incidents.
A proof of concept of the FallRisk system was demonstrated at the closing event in a lab environment.
More information concerning the FallRisk project and its outcomes can be found here:
Assessing the fall risk of a person using the Nintendo Wii Balance Board
Currently a fall risk assessment tool using the Wii Balance Board is validated with approximately 100 older adults in a cooperation between the researchers from the KU Leuven research group AdvISe and the Center of Expertise for Fall and Fracture Prevention Flanders. For this fall risk assessment the older person has to stand on the board and remain rigid for 40 seconds after which the algorithm determines whether or not that person has an increased fall risk.
Prior to this validation the algorithm was already validated with a smaller group of 51 participants, of which 39 were used as training data and 12 for validation. The training dataset contains 16 ‘healthy’ college students acting as a control group, 8 elderly people who had fallen at least once in the past year and 15 elderly who had not. Initial validation of the classifiers was done using 10-fold cross validation. A maximum average accuracy of 96.49% ± 4.02 was achieved.
More information concerning this algorithm can be found in this paper:
The FallCam research project was set up to build a prototype camera system, designed to detect falls in older persons. Obtaining information from real-life images is critical for developing a fall detection system. Therefore, an observational study was conducted from July 2009 to April 2010 in two settings (assisted living and residential care, respectively) in Belgium. The FallCam camera system was installed in the room of three participating older residents, using a centralized PC platform in combination with standard IP cameras. Image recordings (resolution 640 by 480 pixels, frame rate of 12 frames per second) were made 24 hours a day, seven days a week. After notification of a fall, video data of reported falls were saved starting from two hours before until two hours after the fall. Real-life images, with additional information from the fall calendar, nursing notes and medical charts, were used to analyze fall incidents. During the study period a total of 26 were recorded on camera. More information about the results of the FallCam project can be found in the following papers:
– Vlaeyen, E., Deschodt, M., Debard, G., Dejaeger, E., Boonen, S., Goedemé, T., Vanrumste, B., Milisen, K. (2013). Fall incidents unraveled: A series of 26 video-based real-life fall events in three frail older persons. BMC Geriatrics, 13 (103), 1-10.
– Debard, G., Mertens, M., Deschodt, M., Vlaeyen, E., Devriendt, E., Dejaeger, E., Milisen, K., Tournoy, J., Croonenborghs, T., Goedemé, T., Tuytelaars, T., Vanrumste, B. (2015). Camera-based fall detection using real-world versus simulated data: how far are we from the solution? Journal of Ambient Intelligence and Smart Environments.
Bart Vanrumste & Greet Baldewijns, ESAT – STADIUS, Stadius Centre for Dynamical Systems, Signal Processing and Data Analytics, KULeuven, Belgium
Koen Milisen & Ellen Vlaeyen, Center of Expertise for Fall and Fracture Prevention Flanders & Department of Public Health and Primary Care, KULeuven, Belgium
Fall cam project
I am interested in the cost element of installing falls cam within patient’s rooms + the privacy and dignity issues (how did you over come the angst/legalities of patient/family and organisation)?
Was the project or have falls cam’s been installed in any hospital acute situations
Please can you provide contact details for the project leads/team so I can correspond
Susan McHugh – New Zealand
You must be logged in to reply to this topic.