Temporal and kinematic variables for real-world falls harvested from lumbar sensors in the elderly population.

Automatic fall detection will reduce the consequences of falls in the elderly and promote independent living, ensuring people can confidently live safely at home. Inertial sensor technology can distinguish falls from normal activities. However, <;7% of studies have used fall data recorded from elderly people in real life. The FARSEEING project has compiled a database of real life falls from elderly people, to gain new knowledge about fall events. We have extracted temporal and kinematic parameters to further improve the development of fall detection algorithms. A total of 100 real-world falls were analysed. Subjects with a known fall history were recruited, inertial sensors were attached to L5 and a fall report, following a fall, was used to extract the fall signal. This data-set was examined, and variables were extracted that include upper and lower impact peak values, posture angle change during the fall and time of occurrence. These extracted parameters, can be used to inform the design of fall-detection algorithms for real-world falls detection in the elderly.