| CPC A61B 5/1117 (2013.01) [A61B 5/1118 (2013.01); A61B 5/681 (2013.01)] | 20 Claims |
|
1. A method comprising:
receiving, at a wearable device worn by a user, motion data based on the user's activities over a period of time, wherein the wearable device includes a motion sensor, wherein the motion sensor includes a first motion sensor worn on a first wrist of the user, and a second motion sensor worn on a second wrist of the user, wherein the motion sensor collects acceleration data, the acceleration data including data indicating a first wrist acceleration and a second wrist acceleration, wherein the acceleration data relates to the motion data, wherein the wearable device communicates with a server;
calculating one or more properties of the motion data, comprising:
calculating a two-dimensional data transform of the motion data;
determining, using the two-dimensional data transform, an area where the transform's values exceed a threshold; and
calculating one or more properties of the area;
determining that the user fell using a machine learning model executed on a processor of a cloud service and based on the one or more properties of the motion data, wherein the machine learning model was previously trained on historical motion data; and
transmitting the determination to the server, a caretaker of the user, and an emergency system.
|