Version 1
: Received: 5 November 2024 / Approved: 6 November 2024 / Online: 7 November 2024 (09:21:25 CET)
How to cite:
Cabrera, M.; Naranjo-Torres, J.; Cabrera, Á.; Zambrano, L.; Rodriguez-Morales, A. J. A Machine Learning Tool with An Integrated Dataset Towards the Construction of An Early Warning System for Dengue in Zulia State, Venezuela. Preprints2024, 2024110476. https://doi.org/10.20944/preprints202411.0476.v1
Cabrera, M.; Naranjo-Torres, J.; Cabrera, Á.; Zambrano, L.; Rodriguez-Morales, A. J. A Machine Learning Tool with An Integrated Dataset Towards the Construction of An Early Warning System for Dengue in Zulia State, Venezuela. Preprints 2024, 2024110476. https://doi.org/10.20944/preprints202411.0476.v1
Cabrera, M.; Naranjo-Torres, J.; Cabrera, Á.; Zambrano, L.; Rodriguez-Morales, A. J. A Machine Learning Tool with An Integrated Dataset Towards the Construction of An Early Warning System for Dengue in Zulia State, Venezuela. Preprints2024, 2024110476. https://doi.org/10.20944/preprints202411.0476.v1
APA Style
Cabrera, M., Naranjo-Torres, J., Cabrera, Á., Zambrano, L., & Rodriguez-Morales, A. J. (2024). A Machine Learning Tool with An Integrated Dataset Towards the Construction of An Early Warning System for Dengue in Zulia State, Venezuela. Preprints. https://doi.org/10.20944/preprints202411.0476.v1
Chicago/Turabian Style
Cabrera, M., Lysien Zambrano and Alfonso J. Rodriguez-Morales. 2024 "A Machine Learning Tool with An Integrated Dataset Towards the Construction of An Early Warning System for Dengue in Zulia State, Venezuela" Preprints. https://doi.org/10.20944/preprints202411.0476.v1
Abstract
Considering the sustained increase of dengue outbreaks in Latin America in recent years, this study proposes the use of machine learning (ML) tools with epidemiological data, meteorological climate parameters considering El Niño and La Niña (Niño 3.4 Index), and socioeconomic and demographic phenomena as a basis for the construction of an early warning system for dengue outbreaks in Zulia State, Venezuela. The study area covers 21 municipalities. Two ML models, support vector regression machine (SVM-R) and Gaussian process regression (GPR), were used. The data were used raw, standardised, and normalized for each model to be trained. The predictions of dengue outbreaks from the GPR and SVR algorithms show agreement with the dates of the real data; it was determined that there is a range of 2 to 3 weeks depending on the municipality. These coincide with previous studies showing that the algorithms do not work properly for some municipalities.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
