A U-net segmentation model for predicting free convection over confined isothermal tubes

B Baghapour - International Communications in Heat and Mass …, 2024 - Elsevier
A deep-learning segmentation model was proposed to predict steady-state thermal fields.
The U-Net architecture was used in a reversed order, with the body segments serving as …

Diffusion coefficient of alginate microcapsules used in pancreatic islet transplantation, a method to cure type 1 diabetes

A Najdahmadi, JRT Lakey… - … Imaging, Sensing, and …, 2018 - spiedigitallibrary.org
Pancreatic islet transplantation is a promising approach of providing insulin in type 1
diabetes. One strategy to protect islets from the host immune system is encapsulation within …

MPI-CUDA parallel linear solvers for block-tridiagonal matrices in the context of SLEPc's eigensolvers

AL Davina, JE Roman - Parallel computing, 2018 - Elsevier
We consider the computation of a few eigenpairs of a generalized eigenvalue problem A x=
λ B x with block-tridiagonal matrices, not necessarily symmetric, in the context of Krylov …

GPU implementation of Krylov solvers for block-tridiagonal eigenvalue problems

A Lamas Daviña, JE Roman - … , PPAM 2015, Krakow, Poland, September 6 …, 2016 - Springer
In an eigenvalue problem defined by one or two matrices with block-tridiagonal structure, if
only a few eigenpairs are required it is interesting to consider iterative methods based on …

[PDF][PDF] An implicit multigrid solver for high-order compressible flow simulations on GPUs

V Esfahanian, M Hedayat, B Baghapour… - APCOM & ISCM …, 2013 - sci-en-tech.com
The multigrid method has proved to be effective for a large class of numerical methods. In
this study, a strategy based on Full Approximation Storage (FAS) scheme is implemented …

Dense and sparse parallel linear algebra algorithms on graphics processing units

A Lamas Daviña - 2018 - riunet.upv.es
One line of development followed in the field of supercomputing is the use of specific
purpose processors to speed up certain types of computations. In this thesis we study the …

[PDF][PDF] REAL-TIME DATA MINING FOR PROCESS OPERATIONS USING GRAPHICS PROCESSING UNIT (GPU)-BASED HIGH PERFORMANCE COMPUTING

L CHAN - 2014 - core.ac.uk
Data mining is a computational tool which is used to transform massive amount of process
data into useful forms like models, patterns, or rules. The mined information can provide …