SYSTEM AND METHOD FOR CHARACTERIZING BIOMECHANICAL ACTIVITY

• US 20170095181A1
• Filed: 09/30/2016
• Published: 04/06/2017
• Est. Priority Date: 10/02/2015
• Status: Active Grant

• Current Assignee: Lumo LLC
• Original Assignee: LUMO BodyTech, Inc.
• Inventors: Cowan, Ray Franklin, Hauenstein, Andreas Martin, Chang, Andrew Robert
• Granted Patent: US 10,314,520 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/1121 Determining geometric values, e.g. centre of rotation or angular range of movement
• CPC Class Codes: A61B 5/6823 Trunk, e.g., chest, back, abdomen, hip
• CPC Class Codes: A61B 5/6828 Leg
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes precedence
• CPC Class Codes: G01C 21/183 Compensation of inertial measurements, e.g. for temperature effects
• CPC Class Codes: G01C 22/006 Pedometers

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.

Claims

1. A method for personal activity monitoring comprising:

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 is a time series signal with values that characterize a biomechanical property during a segment, wherein generating the set of biomechanical signals comprises;

generating a first integration data set through data integration and baseline error correction across the set of segments of the 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.

2. The method of claim 1, wherein the activity monitoring system is a single activity monitoring device.

3. The method of claim 1, wherein the activity monitor system is a set of sensor devices that are each attached at distinct points on the user.

4. The method of claim 1, wherein segmenting at least a subset of the kinematic data streams into a set of segments is step segmentation that comprises identifying segmentation points through local extrema in a summation of accelerometer data.

5. The method of claim 4, further comprising adapting orientation of kinematic data streams to a participant orientation, which comprises orienting pitch and roll orientation and determining a forward-backward orientation.

6. The method of claim 1, wherein the set of biomechanical signals comprises ground contact time, braking, pelvic rotation, pelvic tilt, pelvic drop, vertical oscillation of the pelvis, forward velocity properties of the pelvis, and left-right detection.

7. The method of claim 1, wherein generating a first biomechanical signal of the set of biomechanical signals further comprises:

generating a second integration data set through data integration and baseline error correction across the set of segments of the first integration data set, and

determining at least a second biomechanical signal that is at least partially based on the second integration data set.

8. The method of claim 1, wherein the first integration data set is generated through data integration of accelerometer data;

wherein the first biomechanical signal is a braking biomechanical signal; and

further comprising;

determining a ground contact time signal at least partially based on the first integration data set and the segmentation;

generating a second integration data set through data integration and baseline error correction across the set of segments of data of the first integration data set, and

determining a vertical oscillation signal at least partially based on the second integration data set.

9. The method of claim 8, further comprising normalizing the set of kinematic data streams prior to segmenting the kinematic data, which comprises determining a rotational reference of a pelvic region of the participant;

and further comprising;

generating a gyroscopic integration data set through data integration of gyroscopic kinematic data and baseline error correction;

determining pelvic rotation and pelvic drop signals at least partially based on the gyroscopic integration layer and the rotational reference of the pelvic region.

10. The method of claim 1, wherein segmenting at least a subset of the kinematic data streams into a set of segments is step segmentation;

and further comprising classifying segments as left or right steps according to segmented angular velocity gyroscopic data.

11. The method of claim 10, wherein the set of biomechanical signals includes left and right biomechanical signals.

12. The method of claim 1, wherein applying the set of biomechanical signals comprises, at the activity monitoring system, averaging the biomechanical signal values over a window of consecutive segments and wirelessly communicating a sequence of averaged biomechanical signals to a secondary device.

13. The method of claim 12, wherein a rest period of the activity monitoring device is dynamically set according to the run distance of the activity or the consistency of the biomechanical signals.

14. The method of claim 1, wherein applying the set of biomechanical signals comprises generating user feedback according to the detected biomechanical signals during an activity session.

15. A system for tracking activity of a user comprising:

an activity monitoring device that comprises a housing, an inertial measuring system that collects a set of kinematic data streams, a signal processor module, and a connectivity module;

wherein the activity monitoring device is configured to;

segment the kinematic data streams into a set of segments according to the steps of the user,

generate a set of biomechanical signals from the kinematic data streams, wherein a biomechanical signal is a time series signal with values that characterize a biomechanical property during a segment; and

wherein the activity monitoring device is attachable to a user in the pelvic region.

16. The system of claim 15, wherein the activity monitoring device configured to generate the set of biomechanical signals is further configured to:

generate a first integration data set through data integration and baseline error correction across the set of segments of the set of kinematic data stream, and

determine a braking biomechanical signal that is at least partially based on the first integration data set;

determine a ground contact time signal at least partially based on the first integration layer and the segmentation;

generate a second integration data set through data integration and baseline error correction across the set of segments of data of the first integration data set, and

determine a vertical oscillation signal at least partially based on the second integration layer.

17. The system of claim 15, wherein the set of biomechanical signals comprises ground contact time, braking, pelvic rotation, pelvic tilt, pelvic drop, vertical oscillation of the pelvis, and forward velocity properties of the pelvis.

18. The system of claim 15, wherein the activity monitoring device is configured to segment the kinematic data streams into a set of segments is further configured to classify segments as left or right steps;

and wherein the set of biomechanical signals includes left and right biomechanical signals.

19. The system of claim 15, further comprising a user application operable on a computing device that is distinct from the activity monitoring device;

and wherein the activity monitoring device is configured to average biomechanical signal values over a window of consecutive segments and, at the communication module, wirelessly communicate the sequence of averaged biomechanical signals to the user application.