Predicting Malaria Dynamics in Burundi Using Deep Learning Models
| dc.contributor.author | Sakubu, Daxelle | |
| dc.contributor.author | Et al. | |
| dc.date.accessioned | 2025-11-21T06:10:49Z | |
| dc.date.available | 2025-11-21T06:10:49Z | |
| dc.date.issued | 2024-08 | |
| dc.description | Article de recherche | |
| dc.description.abstract | Malaria continues to be a major public health problem on the African continent, particularly in Sub-Saharan Africa despite the ongoing efforts and significant progress that has been made. In the case of Burundi, malaria remains a major public health concern in the general population. In the literature, there are limited malaria prediction models for Burundi knowing that such tools are much needed for intervention design. In this study, deep-learning models are built to estimate malaria cases in Burundi. The forecast of malaria cases was carried out both at the provincial and national levels. Long short term memory (LSTM) model, a type of deep learning model, has been used to achieve best results using climate-change related factors such as temperature, rainfall, relative humidity, together with malaria historical data and human population. With this model, the results showed that different parameter tuning can be used to determine the minimum and maximum expected malaria cases. The univariate version of that model (LSTM), which learns from previous dynamics of malaria cases, gives more precise estimates, but both univariate and multivariate models have the same overall trends at the province level and country level. | |
| dc.identifier.uri | https://repository.ub.edu.bi/handle/123456789/2149 | |
| dc.language.iso | en | |
| dc.publisher | Journal of Applied Mathematics and Physics, | |
| dc.title | Predicting Malaria Dynamics in Burundi Using Deep Learning Models | |
| dc.type | Article |