Social-aware and context-aware multi-sensor fall detection system
01/01/2013 - 31/12/2014
Has been initialized


For elderly people fall incidents are often a life-changing event that might lead to degradation or even loss of autonomy. More than half of the elderly living in a nursing home and about one third of the elderly living at home fall at least once a year, denoting the high prevalence of falling. Of those who fall, 10 to 15% suffer severe injuries. The lack of timely aid can lead to further complications, e.g. dehydration, pressure ulcers and even death. Although not all fall incidents lead to physical injuries, psychological consequences are equally important (fear of falling, losing self-confidence and fear of losing independence). Due to the high impact of falling, both fall prevention and reliable fall detecting are necessities. To support this, technologies in ‘closing the loop’ from the elder at risk towards the (in)formal caregiver network need to be optimized in view of the changing demographics (more elderly people, less caregivers).

Innovation and leap of knowledge

The FallRisk project will design and develop non-stigmatizing, holistic services in view of the automated follow up of fall risk and the multi-sensor and contextual detection of fall incidents. The project will develop a multi-sensor approach in the home network environment, exploring the active inclusion of microphone arrays and the TV set. Optimum design of a multi-sensor system focuses on the assurance that every real fall incident can be detected (100% sensitivity), while at the same time capturing valuable context information.

Secondly a context-aware and social-aware selection algorithm will be developed to be able to support the dynamic and optimum forwarding of FallRisk events or alarms towards the (in)formal caregiver network. This back-end system will handle 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).It is envisaged that the FallRisk service design will lead to a decrease in the fear for falling, thus empowering the sustained mobility of the elderly person. Next to this the interdisciplinary approach with all relevant stakeholders will ensure optimum user buy-in of the FallRisk service in future valorization scenarios. Proof of Concept testing in real life settings and demonstrators collecting user feedback will lead to new service concepts that can feed into better examples of future products.

In Fallrisk, SMIT has focused on exploring older adults' and nurses' views on using sensors for fall detection and prevention. In addition, SMIT also designed a concept for a service to prevent and detect falls.

Partners: iMinds - EDM - UHASSELT; iMinds - IBCN - Ugent; Wit-Gele Kruis; TP Vision Belgium NV; Verhaert; COMmeto; Televic Healthcare