Device and method for classifying the activity and/or counting steps of a user

Abstract

Device and method for classifying the activity and/or counting steps of a user. A method for classifying the activity of a user can comprise measuring accelerometer data for a plurality of axes; identifying a most active one of the plurality of axes based on the accelerometer data; and classifying the activity of the user based on a signal amplitude of the accelerometer data for the most active axis and one or more threshold values.

1 . A device for counting the number of steps taken by a user wearing the device, the device comprising:
 an accelerometer for measuring accelerometer data for at least one axis; and   a processor configured to:
 apply a derivative operator to the accelerometer data in successive processing windows; 
 count peaks in the derivative of the accelerometer data in each processing window; and 
 eliminate over counted peaks based on time difference between a first peak in a current window and a last peak in a preceding processing window. 
   
     
     
         2 . The device as claimed in  claim 1 , wherein the processor is configured to count the peaks based on a first threshold value if the current processing window is a first processing window after transiting from a light activity state to a moderate or a heavy activity state. 
     
     
         3 . The device as claimed in  claim 1 , wherein the processor is further configured to update an adaptive threshold for the next window. 
     
     
         4 . The device as claimed in  claim 3 , wherein the adaptive threshold for the next window is based on the difference in signal amplitude for a last successive peak and valley pair in the current processing window. 
     
     
         5 . The device as claimed in  claim 4 , wherein the adaptive threshold for the next window is between about >0 to 50% of the difference in signal amplitude for the last successive peak and valley pair in the current processing window. 
     
     
         6 . The device as claimed in  claim 1 , wherein the processor is configured to eliminate peaks from the peak count in the current window if the time difference between the first peak in the current window and the last peak in the preceding processing window is smaller than a second threshold value. 
     
     
         7 . The device as claimed in  claim 6 , wherein the second threshold value is about ¼ seconds. 
     
     
         8 . The device as claimed in  claim 1 , wherein the derivative operator comprises a Pan Tomkins derivative operator. 
     
     
         9 . The device as claimed in  claim 1 , wherein the device is implemented in a wearable device. 
     
     
         10 . The device as claimed in  claim 1 , wherein the device is implemented in an assembly comprising a wearable device and a communication device. 
     
     
         11 . The device as claimed in  claim 1 , wherein the device is implemented in an assembly comprising a wearable device and a wireless communication device. 
     
     
         12 . A method for counting the number of steps taken by a user, the method comprising:
 measuring accelerometer data for at least one axis;   applying a derivative operator to the accelerometer data in successive processing windows;   counting peaks in the derivative of the accelerometer data in each processing window; and   eliminating over counted peaks based on time difference between a first peak in a current window and a last peak in a preceding processing window.   
     
     
         13 . The method as claimed in  claim 12 , comprising counting the peaks based on a first threshold if the current processing window is a first processing window after transiting from a light activity state to a moderate or a heavy activity state. 
     
     
         14 . The method as claimed in  claim 12 , further comprising updating an adaptive threshold for the next window. 
     
     
         15 . The method as claimed in  claim 14 , wherein the adaptive threshold for the next window is based on the difference in signal amplitude for a last successive peak and valley pair in the current processing window. 
     
     
         16 . The method as claimed in  claim 15 , wherein the adaptive threshold for the next window is between about >0 to 50% of the difference in signal amplitude for the last successive peak and valley pair in the current processing window. 
     
     
         17 . The method as claimed in  claim 12 , comprising eliminating peaks from the peak count in the current window if the time difference between the first peak in the current processing window and the last peak in the preceding processing window is smaller than a second threshold value. 
     
     
         18 . The method as claimed in  claim 17 , wherein the second threshold value is about ¼ seconds. 
     
     
         19 . The method as claimed in  claim 1 , wherein the derivative operator comprises a Pan Tomkins derivative operator.