Detecting falls using a mobile device

1. A method comprising:

receiving, by a computing device, motion data obtained by one or more sensors over a time period, wherein the one or more sensors are worn by a user;

determining, by the computing device, an impact experienced by the user based on the motion data, the impact occurring during a time interval of the time period;

determining, by the computing device based on the motion data, motion characteristics of the user prior to the time interval, during the time interval, and after the time interval;

determining, by the computing device, that the user has fallen based on the impact the motion characteristics of the user, and a statistical model,

wherein the statistical model is generated based on one or more sampled impacts and one or more sampled motion characteristics, and

wherein the one or more sampled impacts and the one or more sampled motion characteristics are determined based on additional motion data obtained by one or more additional sensors worn by one or more additional users over one or more additional time periods; and

responsive to determining that the user has fallen, generating, by the computing device, a notification indicating that the user has fallen.

2. The method of claim 1 , wherein determining the motion characteristics of the user comprises determining, based on the motion data, that the user was walking prior to the time interval.

3. The method of claim 1 , wherein determining the motion characteristics comprises determining, based on the motion data, that the user was traversing stairs prior to the time interval.

4. The method of claim 1 , wherein determining the motion characteristics comprises determining, based on the motion data, that the user was moving a body part according to a flailing motion or a bracing motion prior to the time interval.

5. The method of claim 1 , wherein determining the motion characteristics comprises determining, based on the motion data, that the user was walking after the time interval.

6. The method of claim 1 , wherein determining the motion characteristics comprises determining, based on the motion data, that the user was standing after the time interval.

7. The method of claim 1 , wherein determining the motion characteristics comprises determining, based on the motion data, that an orientation of a body part of the user changed one or more times after the time interval.

8. The method of claim 1 , wherein generating the notification comprises presenting an indication that the user has fallen on at least one of a display device or an audio device of the computing device.

9. The method of claim 1 , wherein generating the notification comprises transmitting data to a communications device remote from the computing device, the data comprising an indication that the user has fallen.

10. The method of claim 9 , wherein the communications device is associated with an emergency response system.

11. The method of claim 1 , wherein the statistical model is a Bayesian statistical model.

12. The method of claim 1 , wherein the one or more sampled motion characteristics comprise an indication of a type of activity being performed by a particular additional user.

13. The method of claim 1 , wherein the one or more sampled motion characteristics comprises an indication of an activity level of a particular additional user.

14. The method of claim 1 , wherein the one or more sampled motion characteristics comprises an indication of a walking speed of a particular additional user.

15. The method of claim 1 , wherein the method is performed by a co-processor of the computing device, and wherein the co-processor is configured to receive the motion data from the one or more sensors, process the motion data, and provide the processed motion data to one or more processors of the computing device.

16. The method of claim 1 , wherein the computing device comprises at least some of the one or more sensors.

17. The method of claim 1 , wherein the computing device is worn on an arm or a wrist of the user while the motion data is obtained by the one or more sensors.

18. The method of claim 1 , wherein the computing device is a wearable mobile device.

19. The method of claim 18 , wherein the computing device is a smart watch.

20. A system comprising:

one or more processors;

one or more sensors; and

one or more non-transitory computer readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

receiving motion data obtained by the one or more sensors over a time period, wherein the one or more sensors are worn by a user;

determining an impact experienced by the user based on the motion data, the impact occurring during a time interval of the time period;

determining, based on the motion data, motion characteristics of the user prior to the time interval, during the time interval, and after the time interval;

determining that the user has fallen based on the impact the motion characteristics of the user, and a statistical model,

wherein the statistical model is generated based on one or more sampled impacts and one or more sampled motion characteristics, and

wherein the one or more sampled impacts and the one or more sampled motion characteristics are determined based on additional motion data obtained by one or more additional sensors worn by one or more additional users over one or more additional time periods; and

responsive to determining that the user has fallen, generating a notification indicating that the user has fallen.

21. The system of claim 20 , wherein determining the motion characteristics of the user comprises determining, based on the motion data, that the user was walking prior to the time interval.

22. The system of claim 20 , wherein determining the motion characteristics comprises determining, based on the motion data, that the user was traversing stairs prior to the time interval.

23. The system of claim 20 , wherein determining the motion characteristics comprises determining, based on the motion data, that the user was moving a body part according to a flailing motion or a bracing motion prior to the time interval.

24. The system of claim 20 , wherein determining the motion characteristics comprises determining, based on the motion data, that the user was walking after the time interval.

25. The system of claim 20 , wherein determining the motion characteristics comprises determining, based on the motion data, that the user was standing after the time interval.

26. The system of claim 20 , wherein determining the motion characteristics comprises determining, based on the motion data, that an orientation of a body part of the user changed one or more times after the time interval.

27. The system of claim 20 , further comprising at least one of a display device or an audio device, and

wherein generating the notification comprises presenting an indication that the user has fallen on at least one of the display device or the audio device.

28. The system of claim 20 , wherein generating the notification comprises transmitting data to a communications device remote from the system, the data comprising an indication that the user has fallen.

29. The system of claim 28 , wherein the communications device is associated with an emergency response system.

30. The system of claim 20 , wherein the statistical model is a Bayesian statistical model.

31. The system of claim 20 , wherein the one or more sampled motion characteristics comprise an indication of a type of activity being performed by a particular additional user.

32. The system of claim 20 , wherein the one or more sampled motion characteristics comprises an indication of an activity level of a particular additional user.

33. The system of claim 20 , wherein the one or more sampled motion characteristics comprises an indication of a walking speed of a particular additional user.

34. The system of claim 20 , wherein the one or more processors comprise a co-processor, wherein the operations are performed, at least in part, by the co-processor.

35. The system of claim 20 , wherein the system is configured to be worn on an arm or a wrist of the user while the motion data is obtained by the one or more sensors.

36. The system of claim 20 , wherein the system is a wearable mobile device.

37. The system of claim 36 , wherein the system is a smart watch.

38. One or more non-transitory computer readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving motion data obtained by one or more sensors over a time period, wherein the one or more sensors are worn by a user;

determining an impact experienced by the user based on the motion data, the impact occurring during a time interval of the time period;

determining, based on the motion data, motion characteristics of the user prior to the time interval, during the time interval, and after the time interval; determining that the user has fallen based on the impact, the motion characteristics of the user, and a statistical model,

wherein the statistical model is generated based on one or more sampled impacts and one or more sampled motion characteristics, and

wherein the one or more sampled impacts and the one or more sampled motion characteristics are determined based on additional motion data obtained by one or more additional sensors worn by one or more additional users over one or more additional time periods; and

responsive to determining that the user has fallen, generating a notification indicating that the user has fallen.