Method for detecting falls and a fall detection system

Abstract

There is provided a fall detection system comprising a user device configured to be worn or carried by a user, the user device comprising a proximity sensor for measuring the proximity of the user device to the ground or a floor; and a movement sensor for measuring the movements of the user; the fall detection system further comprising a processing unit configured to process the measurements from the movement sensor to detect a potential fall; activate the proximity sensor if a potential fall is detected; and process the measurements from the proximity sensor to determine if the user has fallen.

Description

Technical field [0001] The present invention relates to a method for detecting a user's fall and a fall detection system implementing the method, and more particularly to a method and a fall detection system for detecting a fall that provide increased fall detection reliability. Background technique [0002] Falls affect millions of people every year and cause significant injuries, especially among the elderly. In fact, it is estimated that falls are one of the top three causes of death among older people. A fall is defined as a sudden, uncontrolled and unintentional downward displacement of the body to the ground, followed by an impact, after which the body remains on the ground. [0003] PERS is a system in which help can be guaranteed. With the help of the personal help button (PHB), the user can press the button for help in an emergency. Most calls are due to the user having fallen. Moreover, if the user suffers a severe fall (for example, they become unconscious due to the...

AI Technical Summary

Problems solved by technology

However, the wrist is capable of complex movement patterns and has a large range of movement shapes / forms / types, and is also susceptible to non-fall related impacts, where the hand, wrist or arm collides during the normal movement of the user to a target, e.g., a piece of furniture or a door frame, which means that existing fall detection methods based on analyzing measurements from accelerometers cannot provide a sufficiently high detection rate while minimizing the number of false alarms for this type of fall detection system change

Images