System and method for processing motion-related sensor data with social mind-body games for health application

• US 9,474,970 B2
• Filed: 01/28/2013
• Issued: 10/25/2016
• Est. Priority Date: 01/26/2012
• Status: Expired due to Fees

• Current Assignee: Bongjoo Shin, David H. Kil
• Original Assignee: Bongjoo Shin, David H. Kil
• Inventors: Kil, David H., Shin, Bongjoo
• Primary Examiner(s): Shah, Milap
• Application Number:
  US13/752,373
• Publication Number:
  US 20130203475A1
• Time in Patent Office: 1,366 Days
• US Class Current: 1/1
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/1123 Discriminating type of movement, e.g. walking or running A61B5/1116, A61B5/112 take precedence
• CPC Class Codes: A63F 13/21 characterised by their sensors, purposes or types
• CPC Class Codes: A63F 13/212 using sensors worn by the player, e.g. for measuring heart beat or leg activity
• CPC Class Codes: A63F 13/428 involving motion or position input signals, e.g. signals representing the rotation of an input controller or a player's arm motions sensed by accelerometers or gyroscopes
• CPC Class Codes: A63F 13/44 involving timing of operations, e.g. performing an action within a time slot
• CPC Class Codes: A63F 13/65 automatically by game devices or servers from real world data, e.g. measurement in live racing competition
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G09B 19/003 Repetitive work cycles; Sequence of movements
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising

Abstract

A system and method for processing motion-related sensor data for health application examines motion-related signal from a motion sensor located on a subject on a frame-by-frame basis to detect physical activities performed by the subject. For each frame, a detected activity is classified into a category of activities and performance parameters of the detected activity are estimated.

Claims

1. A method for processing motion-related sensor data for health application, the method comprising:

receiving motion-related signals from motion sensors located on different subjects, wherein the motion sensors comprise at least one accelerometer and at least one gyroscope integrated within a smartphone;

processing the received motion-related signals on a frame-by-frame basis to detect distinct short-duration exercise motions performed by the subjects, the distinct short-duration exercise motions including arm motions, leg motions and full body motions, each frame representing a predefined time interval shorter than the total duration of a distinct short-duration exercise motion;

for each frame, performing a plurality of signal transformations to extract features for activity classification;

for each frame, performing hierarchical decision making using feature subsets for a plurality of different categories of short-duration exercise motions to classify a number of motion categories of the plurality of different categories of short-duration exercise motions;

for each frame, classifying a detected distinct short-duration exercise motion into one of the number of motion categories;

for each frame, estimating performance parameters of the detected distinct short-duration exercise motion, wherein the performance parameters define the performance of the detected distinct short-duration exercise motion in the frame; and

creating a picture-based mind-body and reward-based game that is associated to a particular subject of the different subjects, wherein the picture-based mind-body and reward-based game includes at least one of the distinct short-duration exercise motions to be performed using the smartphone to play the picture-based mind-body and reward-based game.

2. The method of claim 1, wherein the classifying includes classifying the detected distinct short-duration exercise motion into one of the different categories of distinct short-duration exercise motions using a learning algorithm.

3. The method of claim 1, wherein the estimating includes estimating the performance parameters of the detected distinct short-duration exercise motion using a bank of matched filters.

4. The method of claim 1, wherein the estimating the performance parameters of the detected distinct short-duration exercise motion includes estimating at least one of counts for each frame, range of motion for each frame, balance score for each frame, steps/strides per frame and revolution per frame.

5. The method of claim 1, wherein the received motion-related signals are from smartphones.

6. The method of claim 1, further comprising transmitting the picture-based mind-body and reward-based game to one or more recipients associated with the particular subject so that the picture-based mind-body and reward-based game can be played by at least one of the recipients.

7. The method of claim 6, further comprising matching the particular subject to at least one of the recipients based on at least one of activity compatibility, wellbeing index, playing patterns, user profile and social relationship of the subject and the recipients.

8. The method of claim 1, further comprising submitting results of the picture-based mind-body and reward-based game to a crowdsourcing community for feedback.

9. The method of claim 1, further comprising recommending the picture-based mind-body and reward-based game to the particular subject, wherein the picture-based mind-body and reward-based game involves using points to play, and wherein the points are accumulated by performing at least one of the distinct short-duration exercise motions.

10. A system for processing motion-related sensor data for health application, the system comprising:

computer memory;

processor configured to;

receive motion-related signals from motion sensors located on different subjects and to process the received motion-related signals on a frame-by-frame basis to detect distinct short-duration exercise motions performed by the subjects, the distinct short-duration exercise motions including arm motions, leg motions and full body motions, each frame representing a predefined time interval shorter than the total duration of a distinct short-duration exercise motion, wherein the motion sensors comprise at least one accelerometer and at least one gyroscope integrated within a smartphone;

perform, for each frame, a plurality of signal transformations to extract features for activity classification;

perform, for each frame, hierarchical decision making using feature subsets for a plurality of different categories of short-duration exercise motions to classify a number of motion categories of the plurality of different categories of short-duration exercise motions;

classify, for each frame, a detected distinct short-duration exercise motion into one of the number of motion categories;

estimate, for each frame, performance parameters of the detected distinct short-duration exercise motion, wherein the performance parameters define the performance of the detected distinct short-duration exercise motion in the frame; and

create a picture-based mind-body and reward-based game that is associated to a particular subject of the different subjects, wherein the picture-based mind-body and reward-based game includes at least one of the distinct short-duration exercise motions to be performed using the smartphone to play the picture-based mind-body and reward-based game.

11. The system of claim 10, wherein the processor is configured to classify the detected distinct short-duration exercise motion into one of the different categories of distinct short-duration exercise motions using a learning algorithm.

12. The system of claim 10, wherein the processor is configured to estimate the performance parameters of the detected distinct short-duration exercise motion using a bank of matched filters.

13. The system of claim 10, wherein the processor is configured to estimate at least one of counts for each frame, range of motion for each frame, balance score for each frame, steps/strides per frame and revolution per frame.

14. The system of claim 10, wherein the received motion-related signals are from smartphones.

15. The system of claim 10, wherein the processor is configured to transmit the picture-based mind-body and reward-based game to one or more recipients associated with the particular subject so that the picture-based mind-body and reward-based game can be played by at least one of the recipients.

16. The system of claim 15, wherein the processor is further configured to match the particular subject to at least one of the recipients based on at least one of activity compatibility, wellbeing index, playing patterns, user profile and social relationship of the subject and the recipients.

17. The system of claim 10, wherein the processor is configured to submit results of the picture-based mind-body and reward-based game to a crowdsourcing community for feedback.

18. The system of claim 10, wherein the processor is further configured to recommend the picture-based mind-body and reward-based game to the particular subject, wherein the picture-based mind-body and reward-based game involves using points to play, and wherein the points are accumulated by performing at least one of the distinct short-duration exercise motions.