IP Library Granted Patent US 11,382,572
Granted Patent B2
US 11,382,572 · App. 16/128,060 · Granted Jul 12, 2022

Apparatus and method for estimating bio-information

Inventors: Chang Soon Park (Chungju-si, KR); Ui Kun Kwon (Hwaseong-si, KR)
Assignee: SAMSUNG ELECTRONICS CO., LTD.
A61B5/7278A61B5/02007A61B5/02116A61B5/02125A61B5/02416A61B5/165G16H50/20
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,382,572
App. No.
16/128,060
Granted
Jul 12, 2022
Kind
B2
Abstract

An apparatus for non-invasively estimating bio-information is provided. According to one exemplary embodiment, the apparatus may include a bio-signal acquirer configured to acquire a bio-signal; and a processor configured to extract a plurality of characteristic points from the bio-signal, determine internally dividing points of the plurality of characteristic points, and extract feature values from the bio-signal based on the internally dividing points to perform bio-information estimation.

Claims (21)

1. An apparatus for estimating bio information, the apparatus comprising:

a bio-signal acquirer comprising a photoplethysmogram (PPG) sensor configured to emit a light to an object and acquire a PPG signal by detecting the light reflected or scattered from the object, or a communication interface configured to receive the PPG signal from an external device; a processor configured to extract a plurality of characteristic points from the PPG signal; apply weights respectively to time values of the plurality of characteristic points; determine internally dividing points of the plurality of characteristic points based on a sum at the weights; extract feature values from the PPG signal based on the internally dividing points to estimate the bio-information;

determine an abnormality of the estimated bio-information by comparing the estimated bio-information to history of bio-information estimation of the object; and

generate a warning or an advisory to the object according to the determined abnormality.

2. The apparatus of claim 1 , wherein the processor is further configured to calculate the weights based on amplitude values of the plurality of characteristic points.

3. The apparatus of claim 1 , wherein the processor is further configured to calculate the weights based on differences between first amplitudes at a plurality of points in a derivative signal of the PPG signal and a second amplitude at a predetermined point in the derivative signal, and

wherein the plurality of points in the derivative signal correspond to the plurality of characteristic points extracted from the PPG signal.

4. The apparatus of claim 1 , wherein the processor is further configured to estimate the bio-information comprising at least one of blood pressure, vascular age, arterial stiffness, aortic pressure waveform, stress index, and fatigue based on the extracted feature values.

5. The apparatus of claim 1 , wherein the plurality of characteristic points comprise at least one of points associated with component pulses constituting the PPG signal, and a point at which an amplitude has a maximum value in a systolic region of the PPG signal.

6. The apparatus of claim 5 , wherein the processor is further configured to determine local minimum points in a second derivative signal of the PPG signal as the points associated with the component pulses.

7. The apparatus of claim 5 , wherein the processor is further configured to extract the feature values based on at least one of a ratio of an area of the PPG signal to an amplitude value at the point at which an amplitude has the maximum value in the systolic region of the PPG signal and a difference in time value between the internally dividing points the PPG signal.

8. A method of estimating bio-information, the method comprising:

acquiring a bio-signal; extracting a plurality of characteristic points from the bio-signal; applying weights respectively to time values of the plurality of characteristic points; determining internally dividing points of the plurality of characteristic points based on a sum of the weights; and extracting feature values from the bio-signal based on the internally dividing points to estimate the bio-information;

determine an abnormality of the estimated bio-information by comparing the estimated bio-information to history of bio-information estimation of an object; and

generate a warning or an advisory to the object according to the determined abnormality.

9. The method of claim 8 , wherein the determining the internally dividing points comprises calculating the weights based on amplitude values of the plurality of characteristic points.

10. The method of claim 8 , wherein the determining the internally dividing points comprises calculating the weights based on differences between first amplitudes at a plurality of points in a derivative signal of the bio-signal and a second amplitude at a predetermined point in the derivative signal, and wherein the plurality of points in the derivative signal correspond to the plurality of characteristic points extracted from the bio-signal.

11. The method of claim 8 , further comprising estimating the bio-information, which comprises at least one of blood pressure, vascular age, arterial stiffness, aortic pressure waveform, stress index, and fatigue, based on the extracted feature values.

12. The method of claim 8 , wherein the plurality of characteristic points comprise at least one of points associated with component pulses constituting the bio-signal, and a point at which an amplitude has a maximum value in a systolic region of the bio-signal.

13. The method of claim 12 , wherein the extracting of the characteristic points includes determining local minimum points in a second derivative signal of the bio-signal as the points associated with the component pulses.

14. The method of claim 12 , further comprising extracting the feature values based on at least one of a ratio of an area of the bio-signal to an amplitude value at the point at which an amplitude has the maximum value in the systolic region of the bio-signal and a difference in time value between the internally dividing points of the bio-signal.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 25, 2018
From: PARK, CHANG SOON; KWON, UI KUN
To: SAMSUNG ELECTRONICS CO., LTD.
Reel/Frame 046959/0814 →
Priority Claims (1)
KR 10-2017-0116935 · Sep 13, 2017 · national
Continuity (1)
Related Publication 20190076099A1 · Mar 14, 2019
Cited By (1)
US 12,697,029