Determining energy expenditure of a user

• US 10,512,423 B2
• Filed: 01/11/2010
• Issued: 12/24/2019
• Est. Priority Date: 01/21/2009
• Status: Active Grant

• Current Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Yin, Bin, Dillen, I, Paulus Henricus Antonius
• Primary Examiner(s): Kuan, John C
• Application Number:
  US13/144,379
• Publication Number:
  US 20110276304A1
• Time in Patent Office: 3,634 Days
• Field of Search: None
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/4866 Evaluating metabolism A61B5/083 takes precedence

Abstract

The invention relates to an electronic device for estimating energy consumption of a person. The electronic device uses a mathematical model based on acceleration data for estimating the person'"'"'s energy consumption as a function of the actual performed activity and acceleration values. The acceleration values are converted to an estimate of energy consumption of a given activity by scaling a value of time integrated acceleration data with an activity scaling parameter. The activity scaling parameters for different activities have been determined off-line by comparing measured energy consumptions over e.g. a day with estimated energy consumptions over the same period, where the estimated values are determined using the mathematical model.

Claims

1. A device for determining an energy expenditure of a user of a plurality of users performing a plurality of activities, the device comprising:

one or more ports for receiving acceleration data of the user as a function of time and one or more user parameters characterizing the user, wherein the acceleration data represents movement of an accelerometer device worn by the user;

a display device;

a memory having instructions stored therein and having constant parameters and scaling parameters representing a function of respective ones of the plurality of activities performed by the user stored thereon wherein the instructions include;

instructions for defining a single mathematical model for estimating energy expenditure, wherein the single mathematical model processes input acceleration data using the constant parameters to produce an output estimation of energy expenditure; and

a processor in communication with the display device, a Global Positioning System (GPS) sensor carried by the user, and the memory having the instructions, the constant parameters and the scaling parameters stored therein, wherein the processor is configured to execute the instructions stored in the memory to perform the acts of;

obtaining measurement of energy expenditure values and acceleration data over a predetermined period wherein the acceleration data represents movement of respective other accelerometer devices worn by a plurality of users,

calculating by the processor values of energy expenditure of activities of the plurality of users in a loop to determine the constant parameters and scaling parameters in accordance with the single mathematical model;

minimizing by the processor a difference between the measurement of energy expenditure values and the calculated energy expenditure values by obtaining an activity count value for each data pair of the measurement of energy expenditure values and the acceleration data over the predetermined period of each user of the plurality of users by accumulating a product of the scaling parameters and activity values over the activities during the predetermined period;

determining by the processor an energy expenditure of a current activity of the plurality of activities performed by the user wearing the accelerometer device by;

accumulating, from the accelerometer device, current acceleration data of the current activity from the user for a duration of the current activity,

identifying the current activity as cycling based on velocity data received from the GPS sensor in conjunction with the current acceleration data of the current activity, wherein the identifying is based on comparisons of the velocity data to a first threshold and the current acceleration data to a second threshold;

selecting a scaling parameter of the scaling parameters that is associated with cycling, and

applying the single mathematical model, including scaling the current acceleration data using the selected scaling parameter, to obtain an energy expenditure estimate associated with the cycling current activity, whereby the scaling parameters adapt application of the single mathematical model to human-worn accelerometer data generated according to any of the plurality of activities; and

rendering a graphical user interface on the display device, wherein the graphical user interface comprises energy expenditure estimates associated with the user wearing the accelerometer device.

2. The device according to claim 1, wherein the scaling parameters are greater than a threshold value for the activities having the activity value determined from the acceleration data which underestimates an actual energy expenditure, and wherein the scaling parameters are smaller than the threshold value for the activities having the activity value determined from the acceleration data which overestimates the actual energy expenditure.

3. The device according to claim 1, wherein the processor is further configured to execute the instructions stored in the memory to determine a time profile of actual energy expenditure values based on the energy expenditure estimates.

4. The device according to claim 1, wherein the one or more user parameters include age, weight and height, and an accumulation of said product and the one or more user parameters are scaled by the constant parameters and the duration of the current activity.

5. The device according to claim 1, further comprising an acceleration sensor for measuring the acceleration data of the user in one or more acceleration directions, wherein the activity value of the current activity is determined by accumulating the acceleration data of the user over the duration of the activity for each of the one or more acceleration directions of the acceleration sensor.

6. The device of claim 1, wherein identifying the current activity as cycling is further based on data from a microphone.

7. The device of claim 1, wherein identifying the current activity as cycling is further based on data from a heartbeat sensor, a blood pressure sensor and a microphone.

8. A device for determining an energy expenditure of a user performing a plurality of activities, the device comprising:

one or more ports for receiving acceleration data of the user as a function of time and one or more user parameters characterizing the user, wherein the acceleration data represents movement of an accelerometer device worn by the user,

a display device;

a memory having instructions stored therein and having constant parameters and scaling parameters representing a function of respective ones of the plurality of activities performed by the user stored thereon wherein the instructions include;

instructions for defining a single mathematical model for estimating energy expenditure, wherein the single mathematical model processes input acceleration data using the constant parameters to produce an output estimation of energy expenditure; and

a processor in communication with the display device, a Global Positioning System (GPS) sensor carried by the user, and the memory having the instructions, the constant parameters and the scaling parameters stored thereon, wherein the processor is configured to execute the instructions stored in the memory to perform acts of;

transforming by the processor the acceleration data accumulated over duration of a current activity of the plurality of activities performed by the user into an activity value of the current activity performed by the user,

identifying the current activity as cycling based on velocity data received from the GPS sensor in conjunction with current acceleration data of the current activity, wherein the identifying is based on comparisons of the velocity data to a first threshold and the current acceleration data to a second threshold;

estimating by the processor an energy expenditure value by adding at least one of the user parameters scaled by the constant parameters and the duration of the current activity to a product of the scaling parameter of the plurality of scaling parameters that is associated with cycling and the activity value, and

rendering a graphical user interface on the display device, wherein the graphical user interface includes, as part of a temporal sequence of estimated values of energy expenditure for different activities of the plurality of activities, graphical indications of the cycling and the energy expenditure of the cycling;

wherein the scaling parameters are determined by minimizing a difference between a measured energy expenditure value obtained for a predetermined period comprising one or more activities of the plurality of activities and an accumulation of estimated energy expenditure values for the one or more activities over the predetermined period, and

wherein the difference is minimized using the single mathematical model by accumulating acceleration data over a duration of an activity and producing and accumulating products of the accumulated acceleration data and the scaling parameters, whereby the scaling parameters adapt application of the single mathematical model to human-worn accelerometer data generated according to any of the plurality of activities.

9. The device of claim 8, wherein the scaling parameters are determined from a plurality of pairs of measured energy expenditure values and acceleration data of a plurality of users measured over a predetermined period.

10. A method for determining an energy expenditure of a user on a portable device having at least one input port, a processor, and a memory having instructions stored thereon, wherein the processor executes the instructions to determine the energy expenditure, the method comprising acts of:

obtaining a current activity performed by the user using one of data entry and an automatic activity recognition algorithm, wherein the automatic activity recognition algorithm identifies the current activity as cycling based on velocity data received from a Global Positioning System (GPS) sensor in conjunction with acceleration data representing movement of an accelerometer device worn by the user, wherein the identification by the automatic activity recognition algorithm is based on comparisons of the velocity data to a first threshold and the acceleration data to a second threshold;

transforming by the processor the acceleration data accumulated over a duration of the current activity into an activity value of the current activity performed by the user;

selecting by the processor a scaling parameter associated with cycling from a plurality of scaling parameters stored in the memory, each of the plurality of scaling parameters being a function of a possible activity of the user and the selected scaling parameter being a function of the current activity of the user;

determining by the processor an estimated energy expenditure value by adding at least one of user parameters multiplied by the constant parameters and by the duration of the current activity to a product of the selected scaling parameter and the activity value; and

rendering a graphical user interface on the display device, wherein the graphical user interface includes graphical indications of the cycling and the estimated energy expenditure value,

wherein the plurality of scaling parameters is determined by minimizing a difference between a measured energy expenditure value obtained for a predetermined period comprising one or more activities of the plurality of activities and an accumulation of estimated energy expenditure values for the one or more activities over the predetermined period, and

wherein the difference is minimized using a single mathematical model stored in the memory by accumulating acceleration data over a duration of an activity and producing and accumulating products of the accumulated acceleration data and the scaling parameters, whereby the scaling parameters adapt application of the single mathematical model to human-worn accelerometer data generated according to any of the plurality of activities.

11. The method of claim 10, wherein the automatic activity recognition algorithm identifies the current activity as cycling further based on data from a microphone.

12. The method of claim 10, wherein the automatic activity recognition algorithm identifies the current activity as cycling further based on data from a heartbeat sensor, a blood pressure sensor and a microphone.

13. A device for determining an energy expenditure of a user of a plurality of users performing a plurality of activities, the device comprising:

one or more ports for receiving acceleration data of the user as a function of time and one or more user parameters characterizing the user, wherein the acceleration data represents movement of an accelerometer device worn by the user;

one or more output components;

a memory having instructions stored therein and having constant parameters and scaling parameters representing a function of respective ones of the plurality of activities performed by the user stored thereon wherein the instructions include;

instructions for defining a single mathematical model for estimating energy expenditure, wherein the single mathematical model processes input acceleration data using the constant parameters to produce an output estimation of energy expenditure; and

a processor in communication with the one or more output components, a Global Positioning System (GPS) sensor carried by the user, and the memory having the instructions, the constant parameters and the scaling parameters stored therein, wherein the processor is configured to execute the instructions stored in the memory to perform the acts of;

obtaining measurement of energy expenditure values and acceleration data over a predetermined period wherein the acceleration data represents movement of respective other accelerometer devices worn by a plurality of users,

calculating by the processor values of energy expenditure of activities of the plurality of users in a loop to determine the constant parameters and scaling parameters in accordance with the single mathematical model;

minimizing by the processor a difference between the measurement of energy expenditure values and the calculated energy expenditure values by obtaining an activity count value for each data pair of the measurement of energy expenditure values and the acceleration data over the predetermined period of each user of the plurality of users by accumulating a product of the scaling parameters and activity values over the activities during the predetermined period;

determining by the processor an energy expenditure of a current activity of the plurality of activities performed by the user wearing the accelerometer device by;

accumulating, from the accelerometer device, current acceleration data of the current activity from the user for a duration of the current activity,

identifying the current activity as cycling based on velocity data received from the GPS sensor in conjunction with the current acceleration data of the current activity, wherein the determining is based on comparisons of the velocity data to a first threshold and the current acceleration data to a second threshold;

selecting a scaling parameter of the scaling parameters that is associated with cycling, and

applying the single mathematical model, including scaling the current acceleration data using the selected scaling parameter, to obtain an energy expenditure estimate associated with the cycling current activity, whereby the scaling parameters adapt application of the single mathematical model to human-worn accelerometer data generated according to any of the plurality of activities; and

rendering, at one or more of the output components, indications of the cycling and the energy expenditure estimate of the cycling.