Human Fall Detection

Funding agency: 
Palmetto Health / Alzheimer's association
08/23/2012 - 00:00 to 08/23/2015 - 00:00

Falls and fall injuries continue to be major safety challenges for older adults with dementia. In the long term care setting, falls and near falls often go unreported, leading to missed opportunities for interventions that might prevent future, more serious, and disabling falls. While the literature is replete with reports of fall detection systems that have been developed and tested in laboratory settings (using weight proportionate manikins or adults who have been trained to perform simulated falls), there are few studies that have been conducted in “real-world” settings. This project builds on our existing research, in which we have developed a falls detection system that is based on structural accelerations. The proposed monitoring system is fully passive, i.e., it is embedded entirely within the environment, and does not require the monitored person to wear any device. Moving beyond existing environmental systems that consist of sound, motion, direct video, the proposed system uses structural vibrations.