Falls among older people remain a very important public healthcare issue. Every year over 11 million falls are registered in the U.S. alone. This paper presents a practical real time fall detection system running on a smartwatch (F2D). A decision module takes into account the rebound after the fall and the residual movement of the user, matching a detected fall pattern to an actual fall. The final decision of a fall event is taken based on the location of the user. To the best of our knowledge, this is the first fall detection system which works on an independent smartwatch, being less stigmatizing for the end user. The fall detection algorithm has been tested by Fondation Suisse pour les Téléthèses (FST), the project partner who is responsible for the commercialization of our system. By analyzing real data of activities of daily life of elderly people, we are confident that F2D meets the demands of a reliable and easily extensible system. This paper highlights the innovative algorithm which takes into account the residual movement and the location of the user to increase the fall detection accuracy. By testing with real data we have a fall detection system ready to be deployed on the market.

Wearable watches provide very useful linear acceleration information that can be use to detect falls. However falls not from a standing position are difficult to spot among other normal activities. This paper describes methods, based on pattern recognition using machine learning, to improve the detection of "soft falls". The values of the linear accelerometers are combined in a robust vector that will be presented as input to the algorithms. The performance of these different machine learning algorithms is discussed and then, based on the best scoring method, the size of the time window fed to the system is studied. The best experiments lead to results showing more than 0.9 AUC on a real dataset. In a second part, a prototype implementation on an Android platform using the best results obtained during the experiments is described.

No abstract