Heart rate correction

• US 9,949,694 B2
• Filed: 02/02/2016
• Issued: 04/24/2018
• Est. Priority Date: 10/05/2015
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Albadawi, Haithem, Fung, Han Yee Mimi, Liu, Zongyi
• Primary Examiner(s): VOORHEES, CATHERINE M
• Application Number:
  US15/013,886
• Publication Number:
  US 20170095212A1
• Time in Patent Office: 812 Days
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/112 Gait analysis
• 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 5/6801 specially adapted to be attached to or worn on the body surface
• CPC Class Codes: A61B 5/721 using a separate sensor to detect motion or using motion information derived from signals other than the physiological signal to be measured
• CPC Class Codes: A61B 5/7221 Determining signal validity, reliability or quality A61B5/7207 and A61B5/7217 take precedence

Abstract

A wearable heart rate monitoring device includes an optical sensor configured to translate test light reflected from a wearer of the wearable heart rate monitoring device into a machine-readable heart rate signal. The wearable heart rate monitoring device also includes a motion sensor configured to translate motion of the wearable heart rate monitoring device into a machine-readable motion signal. The wearable heart rate monitoring device also includes a heart rate reporting machine, configured to determine a type of activity currently being performed by the wearer of the wearable heart rate monitoring device based at least in part on the machine-readable motion signal, and output an estimated heart rate based on at least the machine-readable heart rate signal and the type of activity.

Claims

1. A computing device, comprising:

a hardware sensor interface configured to receive a machine-readable heart rate signal and a machine-readable wearer activity signal describing one or more aspects of a current activity of a wearer of the computing device; and

a heart rate reporting machine configured to;

estimate a first candidate heart rate of the wearer based on the machine-readable heart rate signal using a first heart rate estimation approach;

estimate a second candidate heart rate of the wearer based on a frequency domain transformation of the machine-readable heart rate signal using a second heart rate estimation approach different than the first heart rate estimation approach; and

output the first candidate heart rate when the first candidate heart rate is more consistent with the machine-readable wearer activity signal than the second candidate heart rate;

or

output the second candidate heart rate when the second candidate heart rate is more consistent with the wearer activity signal than the first candidate heart rate.

2. The computing device of claim 1, where the machine-readable wearer activity signal is usable to determine a type of activity currently being performed by the wearer.

3. The computing device of claim 2, where the machine-readable wearer activity signal indicates a wearer motion frequency indicating a current rate of motion of the wearer.

4. The computing device of claim 3, where the wearer motion frequency indicates a footfall frequency of the wearer.

5. The computing device of claim 3, where the first heart rate estimation approach includes:

generating a motion-corrected heart rate signal by filtering the wearer motion frequency from the machine-readable heart rate signal; and

estimating the first candidate heart rate by evaluating an average length of time between crossings of a zero-axis by the motion-corrected heart rate signal.

6. The computing device of claim 2, where the second heart rate estimation approach includes:

identifying a highest occurrence frequency within a frequency search window of the machine-readable heart rate signal for each of a plurality of time intervals, a range of the frequency search window varying according to the type of activity currently being performed by the wearer; and

based on determining that a majority of the identified highest occurrence frequencies fall within a similarity threshold, selecting an average highest occurrence frequency as the second candidate heart rate.

7. The computing device of claim 6, where based on determining the type of activity to be walking, a lower bound of the frequency search window is set equal to a footfall frequency of the wearer, and an upper bound of the frequency search window is set equal to twice the footfall frequency of the wearer.

8. The computing device of claim 6, where based on determining the type of activity to be running, a lower bound of the frequency search window is set equal to a footfall frequency of the wearer multiplied by a constant, and an upper bound of the frequency search window is set equal to 200 bpm.

9. The computing device of claim 2, where the second candidate heart rate is determined to be more consistent with the machine-readable wearer activity signal than the first candidate heart rate when the type of activity is determined to be walking and the second candidate heart rate is lower than the first candidate heart rate.

10. The computing device of claim 3, where the second candidate heart rate is determined to be more consistent with the machine-readable wearer activity signal than the first candidate heart rate when the type of activity is determined to be running and a difference between the second candidate heart rate and twice the motion frequency is greater than a running disparity threshold.

11. The computing device of claim 10, where the running disparity threshold is equal to 10 beats per minute.

12. A wearable heart rate monitoring device, comprising:

an optical sensor configured to translate test light reflected from a wearer of the wearable heart rate monitoring device into a machine-readable heart rate signal;

a motion sensor configured to translate motion of the wearable heart rate monitoring device into a machine-readable motion signal; and

a heart rate reporting machine configured to;

motion-correct the machine-readable heart rate signal to a motion-corrected heart rate signal based on the machine-readable motion signal;

estimate a first candidate heart rate of the wearer from a time domain representation of the motion-corrected heart rate signal using a first heart rate estimation approach;

estimate a second candidate heart rate of the wearer from a frequency domain representation of the motion-corrected heart rate signal using a second heart rate estimation approach different from the first heart rate estimation approach;

determine a type of activity of the wearer of the wearable heart rate monitoring device from the machine-readable motion signal; and

output the first candidate heart rate when the first candidate heart rate is more consistent with the machine-readable motion signal than the second candidate heart rate;

or

output the second candidate heart rate when the second candidate heart rate is more consistent with the machine-readable motion signal than the first candidate heart rate.

13. The wearable heart rate monitoring device of claim 12, where the machine-readable motion signal indicates a footfall frequency of the wearer.

14. The wearable heart rate monitoring device of claim 12, where the first heart rate estimation approach includes estimating the first candidate heart rate by evaluating an average length of time between crossings of a zero-axis by the time domain representation of the motion-corrected heart rate signal.

15. The wearable heart rate monitoring device of claim 12, where the second heart rate estimation approach includes:

identifying a highest occurrence frequency within a frequency search window of the frequency domain representation of the motion-corrected heart rate signal for each of a plurality of time intervals, a range of the frequency search window varying according to the type of activity currently being performed by the wearer; and

based on determining that a majority of the identified highest occurrence frequencies fall within a similarity threshold, selecting an average highest occurrence frequency as the second candidate heart rate.

16. The wearable heart rate monitoring device of claim 12, where the second candidate heart rate is determined to be more consistent with the machine-readable motion signal than the first candidate heart rate when the type of activity is determined to be walking and the second candidate heart rate is lower than the first candidate heart rate.

17. The wearable heart rate monitoring device of claim 12, where the second candidate heart rate is determined to be more consistent with the machine-readable motion signal than the first candidate heart rate when the type of activity is determined to be running and a difference between the second candidate heart rate and twice a motion frequency of the wearer is greater than a running disparity threshold of 10 beats per minute.

18. A wearable heart rate monitoring device, comprising:

an optical sensor configured to translate test light reflected from a wearer of the wearable heart rate monitoring device into a machine-readable heart rate signal;

a motion sensor configured to translate motion of the wearable heart rate monitoring device into a machine-readable motion signal; and

a heart rate reporting machine configured to;

determine a type of activity currently being performed by the wearer of the wearable heart rate monitoring device from the machine-readable motion signal; and

output an estimated heart rate from a frequency domain transformation of the machine-readable heart rate signal and the type of activity.

19. The wearable heart rate monitoring device of claim 18, where the machine-readable motion signal indicates a footfall frequency of the wearer.

20. The wearable heart rate monitoring device of claim 18, where the type of activity is either walking or running.