Vol.14, No.1, February 2025.                                                                                                                                                                          ISSN: 2217-8309

                                                                                                                                                                                                                        eISSN: 2217-8333

TEM Journal

TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS

Association for Information Communication Technology Education and Science

Gated Recurrent Unit in Malaria Forecasting with Meteorological and Clinical Data

Romi Fadillah Rahmat, Opim Salim Sitompul, Fahmi Fahmi, Andrea Vicalina, Ayodhia Pitaloka Pasaribu, Muhammad Fermi Pasha

© 2025 Romi Fadillah Rahmat, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)

Citation Information: TEM Journal. Volume 14, Issue 1, Pages 5-17, ISSN 2217-8309, DOI: 10.18421/TEM141-01, February 2025.

Received:  17 July 2024.

Revised:    21 January 2025.
Accepted:  04 February 2025.
Published: 27 February 2025.

Abstract:

Malaria, a disease transmitted by Anopheles mosquitoes carrying the plasmodium parasite, is a significant issue in the health world. To effectively achieve the substantial decrease in malaria cases, it is crucial to accurately forecast the anticipated aggregate count of malaria instances and promptly implement suitable preventive actions following these projections. This study uses an inferential statistical methodology to examine climatic factors that impact the overall number of malaria cases. Additionally, it utilizes a deep learning technique called Gated Recurrent Unit (GRU) to forecast malaria occurrence for the next 12 weeks. The data used in this study comprises meteorological characteristics, including precipitation, ambient temperature, and wind velocity. The results show meteorological and clinical data has a great contribution in forecasting malaria outbreaks. In conclusion, our GRU model with its clinical and meteorological data processing and hyperparameter setup presents a low error result to forecast malaria outbreaks in a weekly time period.

Keywords – Gated Recurrent Unit, General Adversarial Network, Malaria prediction, Deep learning.

-----------------------------------------------------------------------------------------------------------

Full text PDF >  

-----------------------------------------------------------------------------------------------------------