System and method for characterizing biomechanical activity

Abstract

A system and method for collecting a set of kinematic data streams from an activity tracking system with at least one activity monitoring system that is attached to a user; segmenting at least a subset of the kinematic data streams into a set of segments according to actions of the user; generating a set of biomechanical signals from the kinematic data streams wherein a biomechanical signal characterize a biomechanical property during a segment and includes generating a first integration data set through data integration and baseline error correction across the set of segments of the normalized kinematic data stream and determining at least a first biomechanical signal that is at least partially based on the first integration data set; and applying the set of biomechanical signals.

1 .- 19 . (canceled) 
     
     
         20 . A method for identifying movement activity of a user, comprising:
 receiving a plurality of kinematic raw data streams from a plurality of sensors, the plurality of sensors positioned adjacent to different regions of the user;   normalizing the plurality of kinematic raw data streams into a plurality of normalized data streams;   generating a set of biomechanical primitives based on the plurality of normalized data streams; and   controlling a user feedback device based on the set of biomechanical primitives.   
     
     
         21 . The method of  claim 20 , wherein each of the plurality of sensors comprises an accelerometer and a gyroscope. 
     
     
         22 . The method of  claim 20 , wherein the plurality of kinematic raw data streams comprises acceleration, velocity, displacement, force, angular velocity, angular displacement, and tilt/angle. 
     
     
         23 . The method of  claim 20 , wherein the plurality of kinematic data streams comprises at least one of acceleration, velocity, displacement, force, angular velocity, angular displacement, and tilt/angle. 
     
     
         24 . The method of  claim 20 , wherein the set of biomechanical primitives comprises ground contact time, braking, pelvic rotation, pelvic tilt, pelvic drop, forward velocity properties of the pelvis, and/or vertical oscillation of the pelvis. 
     
     
         25 . The method of  claim 20 , wherein the plurality of normalized data streams comprises an accelerometer data stream and a gyroscope data stream. 
     
     
         26 . The method of  claim 20 , further comprising:
 identifying an activity being performed by the user based on the set of biomechanical primitives.   
     
     
         27 . The method of  claim 26 , wherein the generating the set of biomechanical primitives comprises segmenting each of the plurality of kinematic raw data streams into a dynamically adjustable number of segments for a fixed time window, wherein the dynamically adjustable number of segments is based on the identified activity. 
     
     
         28 . The method of  claim 20 , further comprising:
 segmenting the plurality of kinematic raw data streams into a plurality of time-series data segments such that the plurality of time-series data segments align with a repeated motion or a predetermined motion.   
     
     
         29 . The method of  claim 28 , wherein the generating the set of biomechanical primitives is based on the plurality of time-series data segments and the plurality of normalized data streams. 
     
     
         30 . The method of  claim 28 , wherein the plurality of time-series data segments are used to populate the set of biomechanical primitives. 
     
     
         31 . A system for classifying activity of a user comprising:
 a plurality of sensors positioned adjacent to different locations of the user and operative to collect a plurality of kinematic raw data streams;   a user feedback device; and   a processor operative to:
 normalize the plurality of kinematic raw data streams into a plurality of normalized data streams; 
 generate a set of biomechanical primitives based on the plurality of normalized data streams; and 
 control the user feedback device based on the set of biomechanical primitives. 
   
     
     
         32 . The system of  claim 31 , wherein each of the plurality of sensors comprises an accelerometer and a gyroscope. 
     
     
         33 . The system of  claim 31 , wherein the plurality of kinematic raw data streams comprises acceleration, velocity, displacement, force, angular velocity, angular displacement, and tilt/angle. 
     
     
         34 . The system of  claim 31 , wherein the set of biomechanical primitives comprises ground contact time, braking, pelvic rotation, pelvic tilt, pelvic drop, forward velocity properties of the pelvis, and/or vertical oscillation of the pelvis. 
     
     
         35 . The system of  claim 31 , wherein the plurality of normalized data streams comprises an accelerometer data stream and a gyroscope data stream. 
     
     
         36 . The system of  claim 31 , wherein the processor is further operative to:
 identify an activity being performed by the user based on the set of biomechanical primitives.   
     
     
         37 . The system of  claim 36 , wherein the processor is further operative to segment each of the plurality of kinematic raw data streams into a dynamically adjustable number of segments for a fixed time window, wherein the dynamically adjustable number of segments is based on the identified activity. 
     
     
         38 . The system of  claim 31 , wherein the processor is operative to:
 segment the plurality of kinematic raw data streams into a plurality of time-series data segments such that the plurality of time-series data segments align with a repeated motion or a predetermined motion.