Systems, methods, applications for smart sensing, motion activity monitoring, and motion activity pattern recognition

• US 9,681,827 B2
• Filed: 10/04/2014
• Issued: 06/20/2017
• Est. Priority Date: 10/09/2013
• Status: Active Grant

• Current Assignee: Ledo Network, Inc.
• Original Assignee: Ledo Network, Inc.
• Inventors: Wang, Hong, Huang, Bryan He
• Primary Examiner(s): Huynh, Phuong
• Application Number:
  US14/506,633
• Publication Number:
  US 20150100245A1
• Time in Patent Office: 990 Days
• CPC Class Codes: A61B 2560/0242 adapted to measure environmental factors, e.g. temperature, pollution
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 2562/0223 Magnetic field sensors
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/0024 for multiple sensor units attached to the patient, e.g. using a body or personal area network
• 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: A61B 5/7267 involving training the classification device
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A computer-implemented method for recognizing a user'"'"'s activity pattern includes pre-storing activity data in a computer system, automatically determining locations of one or more sensors on a user'"'"'s body, obtaining time series of measured activity parameters by the one or more sensors, automatically segmenting the time series of measured activity parameters into two or more activity periods, determining a spatial range of the movement in an activity period, and recognizing an activity in the activity period based at least in part on the measured activity parameters and the pre-stored activity data.

Claims

1. A computer-implemented method for recognizing a user'"'"'s activity pattern, comprising:

pre-storing activity data in a computer system;

automatically determining locations of one or more sensors on a user'"'"'s body;

obtaining time series of measured activity parameters by the one or more sensors;

automatically segmenting the time series of measured activity parameters into two or more activity periods;

determining a spatial range of the movement in an activity period; and

recognizing an activity in the activity period based at least in part on the measured activity parameters and the pre-stored activity data.

2. The computer-implemented method of claim 1, wherein the step of determining locations comprises:

computing Euler angles or Quaternion angles of the one or more sensors to determine locations of one or more sensors on the user'"'"'s body.

3. The computer-implemented method of claim 1, wherein the step of automatically segmenting the time series of measured activity parameters comprises:

calculating a first average speed in a first time period;

calculating a second average speed in a second time period; and

separating the first period and the second period into different activity periods if a ratio of the first average speed to the second average speed is higher than a predetermined threshold.

4. The method of claim 3, wherein the predetermined threshold is between 2 and 3.

5. The computer-implemented method of claim 1, wherein the step of automatically segmenting the time series of measured activity parameters comprises:

calculating a first average acceleration in a first time period;

calculating a second average acceleration in a second time period; and

separating the first period and the second period into different activity periods if a ratio of the first average acceleration to the second average acceleration is higher than a predetermined threshold.

6. The method of claim 1, wherein the activity is recognized in the activity period based in part on the spatial range of the movement in the activity period.

7. The method of claim 1, further comprising:

extracting a signature pattern using the time series of measured activity parameters,

wherein the activity data pre-stored in the computer system comprise a plurality of signature patterns each corresponding to a known activity,

wherein the activity in the activity period is recognized in part by matching the signature pattern extracted using the time series of measured activity parameters to the one of the plurality of signature patterns stored in the computer system.

8. The method of claim 7, wherein the signature pattern is personalized and specific to the user'"'"'s behavior in the activity.

9. The method of claim 1, wherein the measured activity parameters comprise movement parameters including positions, displacements, distances, speeds, angular velocities, or altitude, physiological parameters including body temperature, heart rate, pulse rate, beat-to-beat heart variability, blood pressure, body fat, or calorie, or environmental characteristics including such as ambient temperature, humility, air quality, light intensity, water quality, sound quality, location.

10. The method of claim 1, wherein the activity recognized in the activity period comprises walking, running, stair climbing, mountain climbing, hiking, driving, taking elevator, dancing, playing soccer, basketball, tennis or ping pong, swimming, diving, sleeping, sitting, driving, jumping, or rotating.

11. The method of claim 1, further comprising:

based on the activity recognized in the activity period, sending control data from the computer system to control an actuator in the sensor, which guides the user to adjust his or her movements.

12. The method of claim 11, wherein the actuator is configured to produce sound, music, voice, light, vibrations, or heat to guide the user to adjust his or her movements.

13. A computer system for recognizing a user'"'"'s activity pattern, comprising:

one or more sensors configured to be worn on a user'"'"'s body and to obtain time series of measured activity parameters;

a computer storage configured to store activity data;

a computer processor configured to automatically determine locations of the one or more sensors on the user'"'"'s body, wherein the computer processor is configured to automatically segment the time series of measured activity parameters into two or more activity periods, to determine a spatial range of the movement in an activity period, and to recognize an activity in the activity period based at least in part on the measured activity parameters and the pre-stored activity data.

14. The computer system of claim 13, wherein the computer processor is configured to compute Euler angles or Quaternion angles of the one or more sensors to determine locations of one or more sensors on the user'"'"'s body.

15. The computer system of claim 13, wherein the computer processor is configured to:

calculating a first average speed in a first time period;

calculating a second average speed in a second time period; and

separating the first period and the second period into different activity periods if a ratio of the first average speed to the second average speed is higher than a predetermined threshold.

16. The computer system of claim 15, wherein the predetermined threshold is between 2 and 3.

17. The computer system of claim 13, wherein the computer processor is configured to:

calculate a first average acceleration in a first time period;

calculate a second average acceleration in a second time period; and

separate the first period and the second period into different activity periods if a ratio of the first average acceleration to the second average acceleration is higher than a predetermined threshold.

18. The computer system of claim 13, wherein the activity is recognized in the activity period based in part on the spatial range of the movement in the activity period.

19. The computer system of claim 13, wherein the computer processor is configured to extract a signature pattern using the time series of measured activity parameters,

wherein the activity data pre-stored in the computer system comprise a plurality of signature patterns each corresponding to a known activity,

wherein the activity in the activity period is recognized in part by matching the signature pattern extracted using the time series of measured activity parameters to the one of the plurality of signature patterns stored in the computer system.

20. The computer system of claim 19, wherein the signature pattern is personalized and specific to the user'"'"'s behavior in the activity.