Data Balancing using Deep Convolutional Generative Adversarial Networks (DCGAN) in Patients with Congenital Syndrome by Zika Virus

Érika Assis, Mark Song, Luis Zárate, Cristiane Nobre

2022

Abstract

Class imbalance is a common health care problem and often affects the performance of machine learning algorithms. Unfortunately, the minority class, generally the one with the most significant interest, has their learning affected to the detriment of the majority class. This article proposes using Deep Convolutional Generative Adversarial Networks (DCGAN) for minority class oversampling, generating synthetic instances. For this, the ’RESP-Microcephaly’ database was used, which records suspected cases of congenital alteration due to Zika virus (ZIKV) infection. The database presents unbalanced data with 2904 and 7606 instances with and without congenital alteration, respectively. To evaluate the performance of DCGAN, we compared this method with an undersampling and an oversampling approach, using SMOTE with three classification algorithms. The use of DCGAN for balancing demonstrates a significant improvement in classification indices, especially about the minority class.

Download


Paper Citation


in Harvard Style

Assis É., Song M., Zárate L. and Nobre C. (2022). Data Balancing using Deep Convolutional Generative Adversarial Networks (DCGAN) in Patients with Congenital Syndrome by Zika Virus. In Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 4: HEALTHINF, ISBN 978-989-758-552-4, pages 93-102. DOI: 10.5220/0010842900003123


in Bibtex Style

@conference{healthinf22,
author={Érika Assis and Mark Song and Luis Zárate and Cristiane Nobre},
title={Data Balancing using Deep Convolutional Generative Adversarial Networks (DCGAN) in Patients with Congenital Syndrome by Zika Virus},
booktitle={Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 4: HEALTHINF,},
year={2022},
pages={93-102},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010842900003123},
isbn={978-989-758-552-4},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 4: HEALTHINF,
TI - Data Balancing using Deep Convolutional Generative Adversarial Networks (DCGAN) in Patients with Congenital Syndrome by Zika Virus
SN - 978-989-758-552-4
AU - Assis É.
AU - Song M.
AU - Zárate L.
AU - Nobre C.
PY - 2022
SP - 93
EP - 102
DO - 10.5220/0010842900003123