METHOD AND APPARATUS TO REMOVING NOISE FROM ELECTROCARDIOGRAPHY (ECG) SENSOR SIGNAL

• US 20170340288A1
• Filed: 04/12/2017
• Published: 11/30/2017
• Est. Priority Date: 05/26/2016
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: BAE, Chisung, YUN, Jinhyun, KIM, Sang Joon
• Granted Patent: US 11,064,949 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 5/117 Identification of persons methods or arrangements for recognising patterns, e.g. fingerprints, G06F18/00, G06V40/00; identification of persons by analysing their voice or speech G10L17/00
• CPC Class Codes: A61B 5/25 Bioelectric electrodes therefor
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/6898 Portable consumer electronic devices, e.g. music players, telephones, tablet computers
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00

Abstract

A method and an apparatus to remove a noise from an electrocardiography (ECG) sensor signal are provided. A noise removing method includes: receiving a sensor signal collected by an electrocardiography (ECG) sensor; extracting an ECG estimation signal from the sensor signal based on a peak value of the sensor signal; determining a first comparison value between the ECG estimation signal and a first reference signal indicating an average form of ECG signals; and classifying the ECG estimation signal as one of an ECG signal and a noise by comparing the first comparison value to a first threshold value.

Claims

1. A noise removing method comprising:

receiving a sensor signal collected by an electrocardiography (ECG) sensor;

extracting an ECG estimation signal from the sensor signal based on a peak value of the sensor signal;

determining a first comparison value between the ECG estimation signal and a first reference signal indicating an average form of ECG signals; and

classifying the ECG estimation signal as one of an ECG signal and a noise by comparing the first comparison value to a first threshold value.

2. The method of claim 1, wherein the first reference signal is generated based on an average of the ECG signals collected from at least one user.

3. The method of claim 1, further comprising:

determining a second comparison value between the ECG estimation signal and a second reference signal indicating an average form of contact noise signals.

4. The method of claim 3, wherein:

the first comparison value and the second comparison value are determined based on one of a cosine distance and a Euclidean distance; and

the classifying comprises classifying the ECG estimation signal as the ECG signal, in response to the first comparison value being less than the first threshold value and the second comparison value being greater than a second threshold value.

5. The method of claim 1, wherein the first comparison value is determined based on one of a cosine distance between the ECG estimation signal and the first reference signal, a correlation between the ECG estimation signal and the first reference signal, and a Euclidean distance between the ECG estimation signal and the first reference signal.

6. The method of claim 1, wherein the first threshold value is experimentally determined to remove the noise from the ECG estimation signal and classify users based on ECG.

7. The method of claim 1, further comprising:

performing user authentication based on the ECG signal.

8. The method of claim 1, wherein the determining comprises:

generating an inverted signal of the ECG estimation signal based on a sign of the first comparison value; and

determining a comparison value between the inverted signal and the first reference signal as the first comparison value.

9. The method of claim 1, further comprising:

accumulating the ECG signals; and

adjusting the first threshold value based on a distribution of the accumulated ECG signals.

10. The method of claim 1, wherein the ECG sensor is configured to collect the sensor signal through a dry type electrode.

11. The method of claim 1, wherein the ECG sensor comprises:

a first electrode disposed in a bezel of a portable device and configured to collect the sensor signal from a hand of the user in contact with the first electrode; and

a second electrode disposed in a home button of the portable device and configured to collect the sensor signal from another hand of the user in contact with the second electrode.

12. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the method of claim 1.

13. A noise removing apparatus comprising:

an extractor configured to receive a sensor signal collected by an electrocardiography (ECG) sensor, and extract an ECG estimation signal from the sensor signal based on a peak value of the sensor signal; and

a comparer configured to determine a first comparison value between the ECG estimation signal and a first reference signal indicating an average form of ECG signals, and classify the ECG estimation signal as one of an ECG signal and a noise by comparing the first comparison value to a first threshold value.

14. The apparatus of claim 13, wherein the first reference signal is generated based on an average of the ECG signals collected from at least one user.

15. The apparatus of claim 13, wherein the comparer is configured to determine a second comparison value between the ECG estimation signal and a second reference signal indicating an average form of contact noise signals.

16. The apparatus of claim 15, wherein:

the first comparison value and the second comparison value are determined based on a cosine distance or a Euclidean distance; and

the comparer is configured to classify the ECG estimation signal as the ECG signal, in response to the first comparison value being less than the first threshold value and the second comparison value being greater than a second threshold value.

17. The apparatus of claim 13, wherein the ECG signal is used to perform user authentication.

18. A noise removing method comprising:

collecting a sensor signal associated with electrocardiography (ECG) of a user using an ECG sensor;

extracting an ECG estimation signal from the sensor signal based on a peak value of the sensor signal;

determining a first comparison value between the ECG estimation signal and a first reference signal indicating an average form of ECG signals;

determining a second comparison value between the ECG estimation signal and a second reference signal indicating an average form of contact noise signals, in response to the first comparison value being greater than a first threshold value;

classifying the ECG estimation signal as an ECG signal, in response to the second comparison value being less than the second reference signal; and

performing user authentication based on the ECG signal.

19. The method of claim 18, further comprising:

classifying the ECG estimation signal as a noise, in response to the first comparison value being greater than the first threshold value, wherein the first comparison value and the second comparison value are determined based on one of a cosine distance and a Euclidean distance.

20. The method of claim 18, further comprising:

classifying the ECG estimation signal as a noise, in response to the second comparison value being less than a second threshold value, wherein the first comparison value and the second comparison value are determined based on a cosine distance or a Euclidean distance.

21. The method of claim 18, wherein the first reference signal is generated based on an average of the ECG signals collected from at least one user.

22. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the method of claim 18.