Techniques for jointly calibrating load and aerobic capacity

• US 10,694,994 B2
• Filed: 03/22/2017
• Issued: 06/30/2020
• Est. Priority Date: 03/22/2016
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Alvarado, Alexander Singh, Mermel, Craig H., Pham, Hung A., Raghuram, Karthik Jayaraman, Tan, Xing
• Primary Examiner(s): Bloch, Michael R
• Application Number:
  US15/466,397
• Publication Number:
  US 20170273619A1
• Time in Patent Office: 1,196 Days
• Field of Search: None
• CPC Class Codes: A61B 2562/085 combined with means for recording calibration data
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02444 Details of sensor A61B5/02427 takes precedence
• CPC Class Codes: A61B 5/083 Measuring rate of metabolism by using breath test, e.g. measuring rate of oxygen consumption
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/4884 inducing physiological or psychological stress, e.g. applications for stress testing
• CPC Class Codes: A61B 5/681 Wristwatch-type devices

Abstract

A relationship relating a load of exercise and a user'"'"'s aerobic capacity may be determined as follows. A processor circuit of a device may retrieve, from a memory, a prior probability distribution of the load of exercise and a prior probability distribution of the user'"'"'s aerobic capacity. The processor circuit may compute a joint prior probability of the load of exercise and the user'"'"'s aerobic capacity. The processor circuit may compute a joint likelihood of the load of exercise and the user'"'"'s aerobic capacity based on data indicative of a measured time-stamped work rate and a measured time-stamped heart rate. The processor circuit may combine the joint prior probability and the joint likelihood to produce a joint posterior probability. The processor circuit may use the joint posterior probability to determine a relationship relating the load of exercise and the user'"'"'s aerobic capacity and output a calorie calculation.

Claims

1. A method for jointly calibrating both a load of exercise and a user'"'"'s aerobic capacity, the method comprising:

retrieving, by a processor circuit of a device from a memory of the device, a prior probability distribution of the load of exercise;

retrieving, by the processor circuit from the memory, a prior probability distribution of the user'"'"'s aerobic capacity;

determining, by the processor circuit, a joint prior probability of the load of exercise and the user'"'"'s aerobic capacity based on the prior probability distribution of the load of exercise and the prior probability distribution of the user'"'"'s aerobic capacity;

measuring, by one or more motion sensors of the device, data indicative of a time-stamped work rate;

measuring, by one or more heart rate sensors of the device, a time-stamped heart rate;

determining, by the processor circuit, a joint likelihood of the load of exercise and the user'"'"'s aerobic capacity based on the measured time-stamped work rate and the measured time-stamped heart rate;

combining, by the processor circuit, the joint prior probability and the joint likelihood to produce a joint posterior probability;

storing, by the processor circuit, the joint posterior probability in the memory of the device as a calibrated user calorie calculation parameter;

after the storing, detecting, by at least one of the one or more motion sensors and the one or more heart rate sensors, new sensor data;

detecting, by the processor circuit, an exercise activity from the new sensor data;

performing, by the processor circuit, a calorie calculation by estimating a metabolic equivalent prediction based on the calibrated user calorie calculation parameter and the new sensor data; and

outputting, by the processor circuit, the calorie calculation to a display of the device.

2. The method of claim 1, further comprising:

receiving, by the processor circuit, a user input indicating an exercise type; and

using, by the processor circuit, the exercise type to determine the prior probability distribution of the load of exercise.

3. The method of claim 2, where the processor circuit represents the prior probability distribution of the load of exercise by a distribution with a normalized variance and a mean based off the exercise type.

4. The method of claim 1, further comprising:

determining, by the processor circuit, user biometrics; and

using, by the processor circuit, the user biometrics to determine the prior probability distribution of the user'"'"'s aerobic capacity.

5. The method of claim 4, where the processor circuit represents the prior probability distribution of the user'"'"'s aerobic capacity by a distribution with a normalized variance and a mean based off the user biometrics.

6. The method of claim 1, further comprising:

determining, by the processor circuit, a likelihood of an observation associated with the load of exercise and a likelihood of an observation associated with the user'"'"'s aerobic capacity; and

computing, by the processor circuit, the joint likelihood for the load of exercise and the user'"'"'s aerobic capacity based on the likelihood of the observation associated with the load of exercise and the likelihood of the observation associated with the user'"'"'s aerobic capacity.

7. The method of claim 6, where the processor circuit determines the likelihood of the observation associated with the load of exercise by calculating a mean and a variance based on the time-stamped work rate.

8. The method of claim 6, where the processor circuit determines the likelihood of the observation associated with the user'"'"'s aerobic capacity by calculating a mean and a variance based on the time-stamped heart rate.

9. A system for jointly calibrating both a load of exercise and a user'"'"'s aerobic capacity comprising:

one or more motion sensors configured to execute instructions causing the one or more motion sensors to measure data indicative of a time-stamped work rate;

one or more heart rate sensors configured to execute instructions causing the one or more heart rate sensors to measure a time-stamped heart rate;

a display;

a memory; and

a processor circuit coupled to the one or more motion sensors, the one or more heart rate sensors, and the memory, the processor circuit configured to execute instructions causing the processor circuit to;

retrieve, from the memory, a prior probability distribution of the load of exercise;

retrieve, from the memory, a prior probability distribution of the user'"'"'s aerobic capacity;

determine a joint prior probability of the load of exercise and the user'"'"'s aerobic capacity based on the prior probability distribution of the load of exercise and the prior probability distribution of the user'"'"'s aerobic capacity;

determine a joint likelihood of the load of exercise and the user'"'"'s aerobic capacity based on the measured time-stamped work rate and the measured time-stamped heart rate;

combine the joint prior probability and the joint likelihood to produce a joint posterior probability;

store the joint posterior probability in the memory as a calibrated user calorie calculation parameter;

after the storing, detect, by at least one of the one or more motion sensors and the one or more heart rate sensors, new sensor data;

detect an exercise activity from the new sensor data;

perform a calorie calculation by estimating a metabolic equivalent prediction based on the calibrated user calorie calculation parameter and the new sensor data; and

output the calorie calculation to the display.

10. The system of claim 9, wherein the instructions further cause the processor circuit to:

receive a user input indicating an exercise type; and

use the exercise type to determine the prior probability distribution of the load of exercise.

11. The system of claim 10, wherein the instructions further cause the processor circuit to represent the prior probability distribution of the load of exercise by a distribution with a normalized variance and a mean based off the exercise type.

12. The system of claim 9, wherein the instructions further cause the processor circuit to:

determine user biometrics; and

use the user biometrics to determine the prior probability distribution of the user'"'"'s aerobic capacity.

13. The system of claim 12, wherein the instructions further cause the processor circuit to represent the prior probability distribution of the user'"'"'s aerobic capacity by a distribution with a normalized variance and a mean based off the user biometrics.

14. The system of claim 9, wherein the instructions further cause the processor circuit to:

determine a likelihood of an observation associated with the load of exercise and a likelihood of an observation associated with the user'"'"'s aerobic capacity; and

determine the joint likelihood for the load of exercise and the user'"'"'s aerobic capacity based on the likelihood of the observation associated with the load of exercise and the likelihood of the observation associated with the user'"'"'s aerobic capacity.

15. The system of claim 14, wherein the instructions further cause the processor circuit to determine the likelihood of the observation associated with the load of exercise by calculating a mean and a variance based on the time-stamped work rate.

16. The system of claim 14, wherein the instructions further cause the processor circuit to determine the likelihood of the observation associated with the user'"'"'s aerobic capacity by calculating a mean and a variance based on the time-stamped heart rate.

17. A mobile device comprising:

one or more motion sensors configured to execute instructions causing the one or more motion sensors to measure data indicative of a time-stamped work rate;

one or more heart rate sensors configured to execute instructions causing the one or more heart rate sensors to measure a time-stamped heart rate;

a display;

a memory; and

a processor circuit coupled to the one or more motion sensors, the one or more heart rate sensors, and the memory, the processor circuit configured to execute instructions causing the processor circuit to;

retrieve, from the memory, a prior probability distribution of the load of exercise;

retrieve, from the memory, a prior probability distribution of the user'"'"'s aerobic capacity;

determine a joint prior probability of the load of exercise and the user'"'"'s aerobic capacity based on the prior probability distribution of the load of exercise and the prior probability distribution of the user'"'"'s aerobic capacity;

determine a joint likelihood of the load of exercise and the user'"'"'s aerobic capacity based on the measured time-stamped work rate and the measured time-stamped heart rate;

combine the joint prior probability and the joint likelihood to produce a joint posterior probability;

store the joint posterior probability in the memory as a calibrated user calorie calculation parameter;

after the storing, detect, by at least one of the one or more motion sensors and the one or more heart rate sensors, new sensor data;

detect an exercise activity from the new sensor data;

perform a calorie calculation by estimating a metabolic equivalent prediction based on the calibrated user calorie calculation parameter and the new sensor data; and

output the calorie calculation to the display.

18. The mobile device of claim 17, wherein the instructions further cause the processor circuit to:

receive a user input indicating an exercise type; and

use the exercise type to determine the prior probability distribution of the load of exercise.

19. The mobile device of claim 18, wherein the instructions further cause the processor circuit to represent the prior probability distribution of the load of exercise by a distribution with a normalized variance and a mean based off the exercise type.

20. The mobile device of claim 17, wherein the instructions further cause the processor circuit to:

determine user biometrics; and

use the user biometrics to determine the prior probability distribution of the user'"'"'s aerobic capacity.

21. The mobile device of claim 20, wherein the instructions further cause the processor circuit to represent the prior probability distribution of the user'"'"'s aerobic capacity by a distribution with a normalized variance and a mean based off the user biometrics.

22. The mobile device of claim 17, wherein the instructions further cause the processor circuit to:

determine a likelihood of an observation associated with the load of exercise and a likelihood of an observation associated with the user'"'"'s aerobic capacity; and

determine the joint likelihood for the load of exercise and the user'"'"'s aerobic capacity based on the likelihood of the observation associated with the load of exercise and the likelihood of the observation associated with the user'"'"'s aerobic capacity.

23. The mobile device of claim 22, wherein the instructions further cause the processor circuit to determine the likelihood of the observation associated with the load of exercise by calculating a mean and a variance based on the time-stamped work rate.

24. The mobile device of claim 22, wherein the instructions further cause the processor circuit to determine the likelihood of the observation associated with the user'"'"'s aerobic capacity by calculating a mean and a variance based on the time-stamped heart rate.