Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/40209
Title: | Code supporting the paper: High-speed predictions of post-burn contraction using a neural network trained on 2D-finite element simulations | Data Creator - person: | Egberts, Ginger VERMOLEN, Fred Zuijlen, Paul van |
Data Creator - organization: | Delft University of Technology | Data Curator - person: | Egberts, Ginger | Data Curator - organization: | Delft University of Technology | Rights Holder - person: | Egberts, Ginger | Rights Holder - organization: | Delft University of Technology | Publisher: | 4TU.ResearchData | Issue Date: | 2023 | Abstract: | This online resource shows three archived folders: Matlab, Python, and App that contain relevant code and data for the article: High-speed predictions of post-burn contraction using a neural network trained on 2D-finite element simulations. Within the Matlab folder, one finds the codes used for the generation of the large dataset. Here, the file Main.m is the main file and from there, one can run the Monte Carlo simulation. Within the Python folder, one finds the codes used for training the neural networks and creating the online application. The file Data.mat contains the data generated by the Matlab Monte Carlo simulation. The files run_bound.py, run_rsa.py, and run_tse.py train the neural networks, of which the best scoring ones are saved in the folder Training. The DashApp folder contains the code for the creation of the Application. Within the App folder, one finds the executable nn_R2_app.exe that one can run, once the archived folder is unzipped. When running the app, it opens in a browser. This was checked in Windows. | Research Discipline: | Engineering and technology > Computer engineering, information technology and mathematical engineering > Scientific computing > Numerical computation (02080305) | Keywords: | Applied Mathematics;FOS: Mathematics;Numerical and Computational Mathematics;Statistics;Machine learning;Post-burn contraction;Feedforward neural network;Online application;Monte Carlo simulations | DOI: | 10.4121/21257199 | Link to publication/dataset: | https://data.4tu.nl/articles/_/21257199 | Source: | 4TU.ResearchData. 10.4121/21257199 https://data.4tu.nl/articles/_/21257199 | Publications related to the dataset: | 10.3389/fams.2023.1098242 | License: | European Union Public License 1.2 (EUPL-1.2) | Access Rights: | Open Access | Version: | 1.0 | Category: | DS | Type: | Dataset |
Appears in Collections: | Datasets |
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.