GENERATION: An Efficient Denoising Autoencoders-Based Approach for Amputated Image Reconstruction

Leila Ben Othman, Parisa Niloofar, Sadok Ben Yahia

2024

Abstract

Missing values in datasets pose a significant challenge, often leading to biased analyses and suboptimal model performance. This study shows a way to fill in missing values using Denoising AutoEncoders (DAE), a type of artificial neural network that is known for being able to learn stable ways to represent data. The observed data are used to train the DAE, and then they are used to fill in missing values. Extensive tests on different image datasets, taking into account different mechanisms of missing data and percentages of missingness, are used to see how well this method works. The results of the experiments show that the DAE-based imputation works better than other imputation methods, especially when it comes to handling informative missingness mechanisms.

Paper Citation

in Harvard Style

Ben Othman L., Niloofar P. and Ben Yahia S. (2024). GENERATION: An Efficient Denoising Autoencoders-Based Approach for Amputated Image Reconstruction. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 1237-1244. DOI: 10.5220/0012460700003636

in Bibtex Style

@conference{icaart24,
author={Leila Ben Othman and Parisa Niloofar and Sadok Ben Yahia},
title={GENERATION: An Efficient Denoising Autoencoders-Based Approach for Amputated Image Reconstruction},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={1237-1244},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012460700003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - GENERATION: An Efficient Denoising Autoencoders-Based Approach for Amputated Image Reconstruction
SN - 978-989-758-680-4
AU - Ben Othman L.
AU - Niloofar P.
AU - Ben Yahia S.
PY - 2024
SP - 1237
EP - 1244
DO - 10.5220/0012460700003636
PB - SciTePress