Fall detection bracelet with an accelerometer and cellular connectivity

Sammanfattning: This thesis aims at developing a prototype for a fall detection bracelet that can connect to the cellular network. The bracelet consists of a processing unit, three sensors, a LTE USB modem and a powerbank. The prototype is aimed at elderly people since up to one out of three over the age of 65-years-old fall each year. Besides elderly people this system can be used in activities which involves substantial height, e.g. climbing and roofing. Statistics has shown that most serious consequences are not a direct result of falling, but from the lack of fast assistance and treatment. If a fall is detected a distress signal, in the form of an SMS message, is sent to a predefined emergency contact. The contents of the SMS messages includes time and date of fall, ambient temperature, fall location coordinates as well as an URL that redirects to the location as seen in Google Maps. The fall detection algorithm is threshold based and was created by first analyzing falls in different direction. It can successfully identify 74,4% of all falls, but as good as up to 91% of falls that are either backwards, forwards or to the left given that the bracelet is attached to the left wrist. The algorithm can further filter out 100% of studied activities that are not falls. Such activities include walking, running and sitting down. This gives an overall Accuracy of 93% for the system. The Accuracy takes into account how well a fall is detected and how well other activities are filtered out. Furthermore, the bracelet was worn for 40 hours, spread out over 11 days, in order to capture data during this persons every day life. During this time no false distress signal was sent to the emergency contact. Limitations of the system has been found to be the GPS module and the fact that the algorithm is threshold based. The location tracking can be improved by utilizing AGPS, which is the same technique that cellphones use. The threshold based system can't be circumvent in a wearable device solution. From this thesis it is indicated that a wearable bracelet can be a reliable fall detection unit. With more extensive falls and field testing even better results can be achieved and it can eventually be pushed as a real product.