10.4121/21407604.v1
Ginger Egberts
Ginger
Egberts
0000-0003-3601-6496
Fred Vermolen
Fred
Vermolen
0000-0003-2212-1711
Paul van Zuijlen
Paul van
Zuijlen
0000-0003-3461-8848
Code supporting the paper: 1D neural network
4TU.ResearchData
2022
Software
Applied Mathematics
Machine learning
Post-burn scar contraction
Morphoelasticity
Feed-forward neural network
Medical application
Monte Carlo simulations
Matlab
Python
TU Delft, Delft Institute of Applied Mathematics
University of Hasselt, Department of Mathematics and Statistics
2022-10-28
10.1007/s00521-021-06772-3
*.zip; *.m; *.mat; *.py; *.txt; *.png
1
CC BY-NC 4.0
<p>This online resource shows two archived folders: <em>Matlab</em> and <em>Python</em>, that contain relevant code for the article: <em>A Bayesian finite-element trained machine learning approach for predicting post-burn contraction</em>. </p>
<p><br></p>
<p>One finds the codes used to generate the large dataset within the <em>Matlab</em> folder. Here, the file <em>Main.m</em> is the main file and from there, one can run the Monte Carlo simulation. There is a README file.</p>
<p><br></p>
<p>Within the <em>Python</em> folder, one finds the codes used for training the neural networks and creating the online application. The file <em>Data.mat</em> contains the data generated by the Matlab Monte Carlo simulation. The files <em>run_bound.py, run_rsa.py</em>, and <em>run_tse.py</em> train the neural networks, of which the best scoring ones are saved in the folder <em>Training</em>. The<em> DashApp</em> folder contains the code for the creation of the Application.</p>
unknown
Dutch Burn Foundation, project 17.105