Deep Learning-based Speed-of-Sound Reconstruction for Single-Sided Pulse-Echo Ultrasound using a Coherency Measure as Input Feature

Author(s):  
Marvin Heller ◽  
Georg Schmitz
2020 ◽  
Author(s):  
Geoffrey Schau ◽  
Erik Burlingame ◽  
Young Hwan Chang

AbstractDeep learning systems have emerged as powerful mechanisms for learning domain translation models. However, in many cases, complete information in one domain is assumed to be necessary for sufficient cross-domain prediction. In this work, we motivate a formal justification for domain-specific information separation in a simple linear case and illustrate that a self-supervised approach enables domain translation between data domains while filtering out domain-specific data features. We introduce a novel approach to identify domainspecific information from sets of unpaired measurements in complementary data domains by considering a deep learning cross-domain autoencoder architecture designed to learn shared latent representations of data while enabling domain translation. We introduce an orthogonal gate block designed to enforce orthogonality of input feature sets by explicitly removing non-sharable information specific to each domain and illustrate separability of domain-specific information on a toy dataset.


2021 ◽  
Author(s):  
Samuel Beuret ◽  
Baptiste Heriard-Dubreuil ◽  
Simon Canales ◽  
Jean-Philippe Thiran

2019 ◽  
Vol 54 (7) ◽  
pp. 419-427 ◽  
Author(s):  
Lisa Ruby ◽  
Sergio J. Sanabria ◽  
Katharina Martini ◽  
Konstantin J. Dedes ◽  
Denise Vorburger ◽  
...  

Energies ◽  
2020 ◽  
Vol 13 (19) ◽  
pp. 5046
Author(s):  
Marzena Dzida

1-Butanol can be considered as a good fuel additive, which can be used at high pressures. Therefore, the knowledge of high-pressure thermophysical properties is crucial for this application. In this paper, new experimental data on the speed of sound in 1-butanol in the temperature range from 293 to 318 K and at pressures up to 101 MPa are reported. The speed of sound at a frequency of 2 MHz was measured at atmospheric and high pressures using two measuring sets operating on the principle of the pulse–echo–overlap method. The measurement uncertainties were estimated to be better than ±0.5 m·s−1 and ± 1 m·s−1 at atmospheric and high pressures, respectively. Additionally, the density was measured under atmospheric pressure in the temperature range from 293 to 318 K using a vibrating tube densimeter Anton Paar DMA 5000. Using the experimental results, the density and isobaric and isochoric heat capacities, isentropic and isothermal compressibilities, isobaric thermal expansion, and internal pressure were calculated at temperatures from 293 to 318 K and at pressures up to 100 MPa.


1986 ◽  
Vol 18 (7) ◽  
pp. 683-689 ◽  
Author(s):  
G Tardajos ◽  
M Diaz Peña ◽  
E Aicart

2008 ◽  
Vol 124 (4) ◽  
pp. 2569-2569
Author(s):  
James M. Sabatier ◽  
Charles H. Sabatier ◽  
Celeste S. Taylor

2014 ◽  
Author(s):  
Michael Jaeger ◽  
Gerrit Held ◽  
Stefan Preisser ◽  
Sara Peeters ◽  
Michael Grünig ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document