Human activity monitoring device

1. A method comprising:

detecting motion by an inertial sensor included in a mobile device;

determining, by the mobile device, whether the motion has a motion signature indicative of a user activity that the mobile device is configured to monitor;

when the motion does not have a motion signature of a user activity that the mobile device is configured to monitor, entering a sleep mode.

2. The method of claim 1 , further comprising:

when the motion does have a motion signature of a user activity that the mobile device is configured to monitor, monitoring for future motions having the motion signature.

3. The method of claim 1 , further comprising, while the mobile device is in the sleep mode:

periodically sampling acceleration data at a predetermined sampling rate, wherein each sample includes acceleration data measured by the inertial sensor over a predetermined time period; and

when acceleration data having a motion signature indicative of a user activity that the mobile device configured to monitor is detected within the predetermined time period, exiting the sleep mode.

4. The method of claim 1 , wherein the inertial sensor has an inertial wakeup functionality, the method further comprising, while the mobile device is in the sleep mode:

detecting a motion sufficient to trigger the inertial wakeup;

sampling acceleration data for a predetermined time period;

determining whether the acceleration data includes a motion signature indicative of a user activity that the mobile device is configured to monitor; and

when the acceleration data includes a motion signature indicative of a user activity that the mobile device is configured to monitor, exiting the sleep mode.

5. A method for a mobile device comprising:

receiving acceleration data that meets stepping criteria from an accelerometer included in the mobile device;

incrementing a step count in a step count buffer;

when at least one of a) the step count is below a step count threshold, or b) a current user cadence fails to match a step cadence of a user profile, using a default step cadence window to identify a time frame within which to monitor for a next step; and

when the step count is at or above the step count threshold, determining a dynamic step cadence window and using the dynamic step cadence window to identify the time frame within which to monitor for the next step.

6. The method of claim 5 , wherein the step count buffer represents probable steps, the method further comprising:

emptying the step count buffer and acknowledging the step counts from the step count buffer as actual steps when the step count buffer reaches the step count threshold; and

entering a stepping mode upon emptying the step count buffer.

7. The method of claim 5 , further comprising, upon determining the dynamic step cadence window:

examining previous acceleration data to determine whether any additional steps would have been counted if the dynamic step cadence window had been used when the previous acceleration data was received; and

counting those additional steps.

8. The method of claim 5 , wherein determining the dynamic step cadence window comprises:

computing a rolling average of stepping periods of previously counted steps; and

setting the dynamic step cadence window based on the rolling average of stepping periods.

9. The method of claim 5 , wherein the stepping criteria comprise:

a first criterion that is satisfied when a current acceleration measurement has a greater magnitude than a previous acceleration measurement;

a second criterion that is satisfied when the current acceleration measurement has a greater magnitude than a lower threshold; and

a third criterion that is satisfied when the current acceleration measurement has a lesser magnitude than an upper threshold.

10. The method of claim 5 , further comprising:

determining an orientation of the mobile device with respect to gravity;

assigning a dominant axis based on the orientation; and

comparing only acceleration data for the dominant axis to the to the stepping criteria to make a determination that the acceleration data meets the stepping criteria.

11. The method of claim 5 , further comprising:

when the current user cadence matches the step cadence of a user profile, using a stored step cadence window of the user profile to identify the time frame within which to monitor for the next step.