Frequency domain projection algorithm

• US 10,201,286 B2
• Filed: 08/22/2014
• Issued: 02/12/2019
• Est. Priority Date: 08/22/2014
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Waydo, Stephen J.
• Primary Examiner(s): Akar, Serkan
• Application Number:
  US14/466,914
• Publication Number:
  US 20160051157A1
• Time in Patent Office: 1,635 Days
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/11 Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb for measuring pulse A61B5/02 ;A61B5/1038 takes precedence; motion detection to correct for motion artifacts in physiological signals A61B5/721
• 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
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity

Abstract

An algorithm for determining heart rate by removing motion artifacts from a PPG signal in the frequency domain utilizes a principal component analysis. Some examples of the present disclosure process PPG signals in combination with accelerometer signals to remove unwanted artifacts in the frequency domain. For example, principal components of the accelerometer signal can be generated and combined with the PPG signal to filter out acceleration contributions represented in the PPG signal to reveal heart rate peaks. Additionally, in some examples, templates may be stored for correlation with candidate heart rate peaks to select those peaks with the highest correlations with the stored templates.

Claims

1. A device for predicting heart rate (HR), comprising:

a first sensor configured to generate time domain raw HR signals;

a second sensor, distinct from the first sensor and configured to generate time domain acceleration signals along first, second and third directions; and

processing circuitry configured for;

performing a principal component analysis of the time domain acceleration signals to provide time domain principal components acceleration waveforms of the time domain acceleration signals having scores along the principal component axes PC1 and PC2;

generating a frequency domain (FD) representation of the time domain raw HR signals to provide a FD raw HR signal waveform;

generating a FD representation of the time domain principal components acceleration waveforms to provide FD acceleration signal waveforms corresponding to the principal component axes PC1 and PC2, the corresponding waveforms being FD PC1 acceleration signal waveforms and FD PC2 acceleration signal waveforms respectively; and

utilizing the FD PC1 acceleration signal waveforms, the FD PC2 acceleration signal waveforms and the FD raw HR signal waveform to predict the HR

wherein the processing circuitry further configured to utilize the FD PC1 acceleration signal waveforms, the FD PC2 acceleration signal waveforms and the FD raw HR signal waveform to predict the HR by;

forming a combination of the FD PC1 and FD PC2 acceleration signal waveforms;

subtracting the combination of the FD PC1 and FD PC2 acceleration signal waveforms from the FD raw HR signal waveform to obtain a FD projected HR signal waveform;

selecting a frequency corresponding to the maximum peak of the FD projected HR signal waveform;

predicting a HR based on the selected frequency; and

displaying the predicted HR.

2. The device of claim 1, wherein the first sensor is a photoplethysmogram (PPG) sensor and the time domain raw HR signals are time domain raw PPG signals.

3. The device of claim 1, wherein the combination of the FD PC1 and FD PC2 acceleration signal waveforms is of the form A{FD PC1 acceleration signal waveform}+B{FD PC2 acceleration signal waveform} respectively where A and B are scale factors.

4. The device of claim 3, wherein the scale factors A and B are determined by a successive approximation algorithm such as to minimize a residual value.

5. The device of claim 1, wherein the processing circuitry is further capable of:

generating groups of time domain raw HR signals and time domain acceleration signals such that the FD raw HR signal waveforms and the FD acceleration signal waveforms are based on discrete Fourier transforms of the groups of raw HR signals and acceleration signals; and

dynamically adjusting the size of the groups in response to at least the selected frequency and previously selected frequencies.

6. A device for predicting heart rate (HR), comprising:

a first sensor configured to generate time domain raw HR signals;

a second sensor, distinct from the first sensor, configured to generate time domain acceleration signals along first, second and third directions; and

processing circuitry configured for;

performing a principal component analysis of the time domain acceleration signals along the first, second and third directions to provide time domain principal components acceleration waveforms of the time domain acceleration signals having scores along the principal component axes PC1 and PC2;

generating a frequency domain (FD) representation of the time domain raw HR signals to provide a FD raw HR signal waveform;

generating a FD representation of the time domain principal components acceleration waveforms to provide FD acceleration signal waveforms corresponding to the principal component axes PC1 and PC2, the corresponding waveforms being FD PC1 acceleration signal waveforms and FD PC2 acceleration signal waveforms respectively; and

utilizing the FD PC1 acceleration signal waveforms, the FD PC2 acceleration signal waveforms, the FD raw HR signal waveform and a plurality of spectral heart rate templates to generate a plurality of correlation values to predict the HR;

wherein the processing circuitry further configured to utilize the FD PC1 acceleration signal waveforms, the FD PC2 acceleration signal waveforms, the FD raw HR signal waveform and a plurality of spectral heart rate templates to generate a plurality of correlation values to predict the HR by;

forming a combination of the FD PC1 and FD PC2 acceleration signal waveforms;

subtracting the combination of the FD PC1 and FD PC2 acceleration signal waveforms from the FD raw HR signal waveform to obtain a FD projected HR signal waveform;

correlating the FD projected HR signal waveform with the plurality of spectral heart rate templates to generate the plurality of correlation values;

predicting a heart rate based on the highest correlation value among the plurality of correlation values; and

displaying the predicted HR.

7. The device of claim 6, wherein the first sensor is a photoplethysmogram (PPG) sensor and the time domain raw HR signals are time domain raw PPG signals.

8. The device of claim 6, wherein the combination of the FD PC1 and FD PC2 acceleration signal waveforms is of the form A{FD PC1 acceleration signal waveform}+B{FD PC2 acceleration signal waveform} respectively where A and B are scale factors.

9. The device of claim 8, wherein the scale factors A and B are determined by a successive approximation algorithm such as to minimize a residual value.

10. The device of claim 6, wherein the processing circuitry is further capable of:

generating groups of time domain raw HR signals and time domain acceleration signals such that the FD raw HR signal waveforms and the FD acceleration signal waveforms are based on discrete Fourier transforms of the groups of raw HR signals and acceleration signals; and

dynamically adjusting the size of the groups in response to at least the correlation values.

11. The device of claim 10, wherein the processing circuitry is further capable of dynamically adjusting the size of the groups dependent on a currently predicted HR, a previously predicted HR and correlation values associated with the currently predicted HR and the previously predicted HR.

12. A method for predicting heart rate (HR), comprising:

generating time domain raw HR signals from a first sensor;

generating time domain acceleration signals along first, second and third directions from a second sensor, distinct from the first sensor;

configuring processing circuitry for;

performing a principal component analysis of the time domain acceleration signals along the first, second and third directions to provide time domain principal components acceleration waveforms of the time domain acceleration signals having scores along the principal component axes PC1 and PC2;

generating a frequency domain (FD) representation of the time domain raw HR signals to provide a FD raw HR signal waveform;

generating a FD representation of the time domain principal components acceleration waveforms to provide FD acceleration signal waveforms corresponding to the principal component axes PC1 and PC2 and designating the corresponding waveforms as FD PC1 acceleration signal waveforms and FD PC2 acceleration signal waveforms respectively; and

utilizing the FD PC1 acceleration signal waveforms, the FD PC2 acceleration signal waveforms and the FD raw HR signal waveform to predict the HR;

forming a combination of the FD PC1 and FD PC2 acceleration signal waveforms;

subtracting the combination of the FD PC1 and FD PC2 acceleration signal waveforms from the FD raw HR signal waveform to obtain a FD projected HR signal waveform;

selecting a frequency corresponding to the maximum peak of the FD projected HR signal waveform;

predicting a HR based on the selected frequency; and

displaying the predicted HR.

13. The method of claim 12, wherein the time domain raw HR signals is generated from a photoplethysmogram (PPG) sensor.

14. The method of claim 12, wherein the combination of the FD PC1 and FD PC2 acceleration signal waveforms is of the form A{FD PC1 acceleration signal waveform}+B{FD PC2 acceleration signal waveform} respectively where A and B are scale factors.

15. The method of claim 14, wherein the scale factors A and B are determined by a successive approximation algorithm such as to minimize a residual value.

16. The method of claim 12, further comprising:

generating groups of time domain raw HR signals and time domain acceleration signals such that the FD raw HR signal waveforms and the FD acceleration signal waveforms are based on discrete Fourier transforms of the groups of raw HR signals and acceleration signals; and

dynamically adjusting the size of the groups in response to at least the selected frequency and previously selected frequencies.

17. A method for predicting heart rate (HR), comprising:

generating time domain raw HR signals from a first sensor;

generating time domain acceleration signals along first, second and third directions from a second sensor, distinct from the first sensor;

configuring processing circuitry for;

performing a principal component analysis of the time domain acceleration signals along the first, second and third directions to provide time domain principal components acceleration waveforms of the time domain acceleration signals having scores along the principal component axes PC1 and PC2;

generating a frequency domain (FD) representation of the time domain raw HR signals to provide a FD raw HR signal waveform;

generating a FD representation of the time domain principal components acceleration waveforms to provide FD acceleration signal waveforms corresponding to the principal component axes PC1 and PC2 and designating the corresponding waveforms as FD PC1 acceleration signal waveforms and FD PC2 acceleration signal waveforms respectively; and

utilizing the FD PC1 acceleration signal waveforms, the FD PC2 acceleration signal waveforms, the FD raw HR signal waveform and a plurality of spectral heart rate templates to generate a plurality of correlation values to predict the HR;

forming a combination of the FD PC1 and FD PC2 acceleration signal waveforms;

subtracting the combination of the FD PC1 and FD PC2 acceleration signal waveforms from the FD raw HR signal waveform to obtain a FD projected HR signal waveform;

correlating the FD projected HR signal waveform with the plurality of spectral heart rate templates to generate the plurality of correlation values;

predicting a heart rate based on the highest correlation value among the plurality of correlation values; and

displaying the predicted HR.