Apparatus, method, and system for accurate estimation of total energy expenditure in daily activities

• US 9,474,472 B2
• Filed: 12/26/2012
• Issued: 10/25/2016
• Est. Priority Date: 12/30/2011
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Baxi, Amit S.
• Primary Examiner(s): HARWARD, SOREN T
• Application Number:
  US13/726,866
• Publication Number:
  US 20130173174A1
• Time in Patent Office: 1,399 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: A61B 2503/12 Healthy persons not otherwise provided for, e.g. subjects of a marketing survey
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• 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 5/222 combined with detection or measurement of physiological parameters, e.g. heart rate
• CPC Class Codes: A61B 5/6898 Portable consumer electronic devices, e.g. music players, telephones, tablet computers
• CPC Class Codes: A63B 24/0062 Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance
• CPC Class Codes: G16B 99/00 Subject matter not provided for in other groups of this subclass
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• CPC Class Codes: G16H 40/63 for local operation

Abstract

An apparatus, article, and system, the apparatus including a housing, a 3-axis accelerometer contained in the housing, a medium storing program instructions, and a processor to execute the program instructions stored in the memory to receive a signal from the 3-axis accelerometer indicative of a user'"'"'s activities, extract features from the received signals, classify the extracted features into a plurality of activity types, determine a total energy expenditure based on the classification of the extracted features; and provide a report of the total energy expenditure.

Claims

1. An apparatus comprising:

a housing;

a 3-axis accelerometer contained in the housing;

a medium storing program instructions; and

a processor to execute the program instructions stored in the memory to;

receive a signal from the 3-axis accelerometer indicative of a user'"'"'s activities;

receive an indication of a location of the housing on the user'"'"'s body;

extract features from the received signals based on the location of the housing on the user'"'"'s body and by examining turning points of the received signal, the extracted features comprising peaks and valleys associated with the turning points of the received signal from the 3-axis accelerometer;

classify the extracted features into activity types consisting of (i) activities characterized by periodic signals having a range of slow walking to running, (ii) activities characterized by non-periodic low intensity activities that have a metabolic equivalent less than 3, (ii) activities characterized as being non-periodic and high intensity that have a metabolic equivalent greater than 3;

determine a total energy expenditure based on the classification of the extracted features by processing each type of activity independently to produce an optimal energy expenditure estimation tailored to the particular activity type; and

provide a report of the total energy expenditure.

2. The apparatus of claim 1, wherein the determination of the total energy expenditure is further based on a location of the device on the user.

3. The apparatus of claim 1, further comprising the processor to:

determine, for the periodic activity type, an estimation of a step frequency and a step count; and

generate a dynamic estimate of a step length based on the step frequency and user height information.

4. The apparatus of claim 1, further comprising the processor to determine an estimation of metabolic equivalents based on an intensity of the activities and a position of the apparatus on the body of the user.

5. The apparatus of claim 1 wherein the peaks and valleys associated with the received signal from the 3-axis accelerometer are stored with temporal locations of the peaks and valleys.

6. The apparatus of claim 5, wherein a duration between peaks and their periodicity are derived from the stored peaks and valleys and their associated temporal locations.

7. The apparatus of claim 1, wherein the extracted features are used to control a frequency cut-off of digital filters.

8. The apparatus of claim 1, wherein the extracted features are used to control a moving average window.

9. A system comprising:

a memory;

a housing;

a 3-axis accelerometer contained in the housing;

a medium storing program instructions; and

a processor to execute the program instructions stored in the memory to;

receive a signal from the 3-axis accelerometer indicative of a user'"'"'s activities;

receive an indication of a location of the housing on the user'"'"'s body;

extract features from the received signals based on the location of the housing on the user'"'"'s body and by examining turning points of the received signal, the extracted features comprising peaks and valleys associated with the turning points of the received signal from the 3-axis accelerometer;

classify the extracted features into activity types consisting of (i) activities characterized by periodic signals having a range of slow walking to running, (ii) activities characterized by non-periodic low intensity activities that have a metabolic equivalent less than 3, (ii) activities characterized as being non-periodic and high intensity that have a metabolic equivalent greater than 3;

determine a total energy expenditure based on the classification of the extracted features by processing each type of activity independently to produce an optimal energy expenditure estimation tailored to the particular activity type; and

provide a report of the total energy expenditure.

10. The system of claim 9, wherein the determination of the total energy expenditure is further based on a location of the device on the user.

11. The system of claim 9, further comprising:

determining, for the periodic activity type, an estimation of a step frequency and a step count; and

generating a dynamic estimate of a step length based on the step frequency and user height information.

12. The system of claim 9, further comprising determining an estimation of metabolic equivalents based on an intensity of the activities and a position of the housing on the body of the user.