US 12,257,034 B2
Apparatus and method for estimating bio-information
Sang Kon Bae, Seongnam-si (KR); Joon-Hyuk Chang, Seoul (KR); Jin Woo Choi, Suwon-si (KR); Youn Ho Kim, Hwaseong-si (KR); Jehyun Kyung, Seoul (KR); Joon-Young Yang, Seoul (KR); Inmo Yeon, Seoul (KR); and Jeong-Hwan Choi, Seoul (KR)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR); and IUCF-HYU (INDUSTRY-UNIVERSITY COOPERATION FOUNDATION HANYANG UNIVERSITY), Seoul (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR); and IUCF-HYU (INDUSTRY-UNIVERSITY COOPERATION FOUNDATION HANYANG UNIVERSITY), Seoul (KR)
Filed on Jul. 7, 2021, as Appl. No. 17/369,199.
Claims priority of application No. 10-2021-0031320 (KR), filed on Mar. 10, 2021.
Prior Publication US 2022/0287571 A1, Sep. 15, 2022
Int. Cl. A61B 5/0205 (2006.01); A61B 5/00 (2006.01); A61B 5/02 (2006.01); A61B 5/022 (2006.01); G06N 3/045 (2023.01); G06N 3/0464 (2023.01)
CPC A61B 5/0205 (2013.01) [A61B 5/02007 (2013.01); A61B 5/02225 (2013.01); A61B 5/442 (2013.01); A61B 5/681 (2013.01); A61B 5/6843 (2013.01); A61B 5/6898 (2013.01); A61B 5/7239 (2013.01); A61B 5/7267 (2013.01); G06N 3/045 (2023.01); G06N 3/0464 (2023.01); A61B 2562/0247 (2013.01)] 25 Claims
OG exemplary drawing
 
1. An apparatus for estimating first bio-information and second bio-information, the apparatus comprising:
a pulse wave sensor comprising a light source and a detector and configured to measure a pulse wave signal from an object;
a force sensor comprising a strain gauge and configured to obtain a force signal by measuring an external force exerted onto the force sensor; and
a processor configured to:
obtain a first input value, a second input value, and a third input value based on the pulse wave signal and the force signal;
extract a feature vector by inputting the first input value, the second input value, and the third input value into a first neural network model; and
obtain the first bio-information by inputting the feature vector into a second neural network model,
wherein the bio-information comprises one or more of blood pressure, vascular age, arterial stiffness, aortic pressure waveform, vascular compliance, stress index, fatigue level, skin age, skin elasticity,
wherein the first neural network model comprises:
three neural networks into which the first input value, the second input value, and the third input value are input respectively, and
a first fully connected layer configured to output the feature vector by using outputs of the three neural networks as inputs; and
a second fully connected layer configured to output the second bio information based on the feature vector output by the first fully connected layer, and
wherein the second neural network model comprises:
a third fully connected layer using the feature vector as an input; and
a fourth fully connected layer outputting the first bio-information by using an output of the first fully connected layer as an input.