Standard

Encoder neural network in 2D acoustic tomography. / Prikhodko, A. Yu; Shishlenin, M. A.; Novikov, N. S. и др.

в: Applied and Computational Mathematics, Том 23, № 1, 2024, стр. 83-98.

Результаты исследований: Научные публикации в периодических изданиях › статья › Рецензирование

Harvard

Prikhodko, AY, Shishlenin, MA, Novikov, NS & Klyuchinskiy, DV 2024, 'Encoder neural network in 2D acoustic tomography', Applied and Computational Mathematics, Том. 23, № 1, стр. 83-98. https://doi.org/10.30546/1683-6154.23.1.2024.83

APA

Prikhodko, A. Y., Shishlenin, M. A., Novikov, N. S., & Klyuchinskiy, D. V. (2024). Encoder neural network in 2D acoustic tomography. Applied and Computational Mathematics, 23(1), 83-98. https://doi.org/10.30546/1683-6154.23.1.2024.83

Vancouver

Prikhodko AY, Shishlenin MA, Novikov NS, Klyuchinskiy DV. Encoder neural network in 2D acoustic tomography. Applied and Computational Mathematics. 2024;23(1):83-98. doi: 10.30546/1683-6154.23.1.2024.83

Author

Prikhodko, A. Yu ; Shishlenin, M. A. ; Novikov, N. S. и др. / Encoder neural network in 2D acoustic tomography. в: Applied and Computational Mathematics. 2024 ; Том 23, № 1. стр. 83-98.

BibTeX

@article{c2656598ac234a458d706d43371eb700,
title = "Encoder neural network in 2D acoustic tomography",
abstract = "We investigate deep learning approach in 2D dynamic ultrasound acoustic tomography. The mathematical model of acoustic tomography is described by a first-order hyperbolic system PDE and is based on conservation laws. This model guarantees us that the training sets of dynamic data are close to the physical solution. We train a neural network consisting of an encoder and a decoder with this data (they contain only one inclusion) and associate the data with a velocity coefficient. Numerical results show that we recover not only single inclusions, but also homogeneities consisting of two inclusions.",
keywords = "Acoustic Tomography, Coefficient Inverse Problem, Deep Learning, Neural Networks, Ultrasound",
author = "Prikhodko, {A. Yu} and Shishlenin, {M. A.} and Novikov, {N. S.} and Klyuchinskiy, {D. V.}",
note = "The work has been supported by RSCF under grant 19-11-00154 “Developing of new mathematical models of acoustic tomography in medicine. Numerical methods, HPC and software”.",
year = "2024",
doi = "10.30546/1683-6154.23.1.2024.83",
language = "English",
volume = "23",
pages = "83--98",
journal = "Applied and Computational Mathematics",
issn = "1683-3511",
publisher = "Institute of Applied Mathematics of Baku State University",
number = "1",

}

RIS

TY - JOUR

T1 - Encoder neural network in 2D acoustic tomography

AU - Prikhodko, A. Yu

AU - Shishlenin, M. A.

AU - Novikov, N. S.

AU - Klyuchinskiy, D. V.

N1 - The work has been supported by RSCF under grant 19-11-00154 “Developing of new mathematical models of acoustic tomography in medicine. Numerical methods, HPC and software”.

PY - 2024

Y1 - 2024

N2 - We investigate deep learning approach in 2D dynamic ultrasound acoustic tomography. The mathematical model of acoustic tomography is described by a first-order hyperbolic system PDE and is based on conservation laws. This model guarantees us that the training sets of dynamic data are close to the physical solution. We train a neural network consisting of an encoder and a decoder with this data (they contain only one inclusion) and associate the data with a velocity coefficient. Numerical results show that we recover not only single inclusions, but also homogeneities consisting of two inclusions.

AB - We investigate deep learning approach in 2D dynamic ultrasound acoustic tomography. The mathematical model of acoustic tomography is described by a first-order hyperbolic system PDE and is based on conservation laws. This model guarantees us that the training sets of dynamic data are close to the physical solution. We train a neural network consisting of an encoder and a decoder with this data (they contain only one inclusion) and associate the data with a velocity coefficient. Numerical results show that we recover not only single inclusions, but also homogeneities consisting of two inclusions.

KW - Acoustic Tomography

KW - Coefficient Inverse Problem

KW - Deep Learning

KW - Neural Networks

KW - Ultrasound

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85187486568&origin=inward&txGid=a1ab1dce9881d7c349693584b293611b

UR - https://www.mendeley.com/catalogue/6855091b-9e1a-3808-8852-cedada387d39/

U2 - 10.30546/1683-6154.23.1.2024.83

DO - 10.30546/1683-6154.23.1.2024.83

M3 - Article

VL - 23

SP - 83

EP - 98

JO - Applied and Computational Mathematics

JF - Applied and Computational Mathematics

SN - 1683-3511

IS - 1

ER -

ID: 60476570