Application of multiple linear regression model and long short-term memory with compartmental model to forecast dengue cases in Selangor, Malaysia based on climate variables

Despite the implementation of various initiatives, dengue remains a significant public health concern in Malaysia. Given that dengue has no specific treatment, dengue prediction remains a useful early warning mechanism for timely and effective deployment of public health preventative measures. This...

Full description

Bibliographic Details
Main Authors: Lu, Xinyi, Teh, Su Yean, Tay, Chai Jian, Nur Faeza, Abu Kassim, Fam, Pei Shan, Soewono, Edy
Format: Article
Language:English
Published: KeAi Communications Co. 2025
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/43811/
http://umpir.ump.edu.my/id/eprint/43811/1/Application%20of%20multiple%20linear%20regression%20model%20and%20long%20short-term%20memory.pdf
_version_ 1848826964647870464
author Lu, Xinyi
Teh, Su Yean
Tay, Chai Jian
Nur Faeza, Abu Kassim
Fam, Pei Shan
Soewono, Edy
author_facet Lu, Xinyi
Teh, Su Yean
Tay, Chai Jian
Nur Faeza, Abu Kassim
Fam, Pei Shan
Soewono, Edy
author_sort Lu, Xinyi
building UMP Institutional Repository
collection Online Access
description Despite the implementation of various initiatives, dengue remains a significant public health concern in Malaysia. Given that dengue has no specific treatment, dengue prediction remains a useful early warning mechanism for timely and effective deployment of public health preventative measures. This study aims to develop a comprehensive approach for forecasting dengue cases in Selangor, Malaysia by incorporating climate variables. An ensemble of Multiple Linear Regression (MLR) model, Long Short-Term Memory (LSTM), and Susceptible-Infected mosquito vectors, Susceptible-Infected-Recovered human hosts (SI-SIR) model were used to establish a relation between climate variables (temperature, humidity, precipitation) and mosquito biting rate. Dengue incidence subject to climate variability can then be projected by SI-SIR model using the forecasted mosquito biting rate. The proposed approach outperformed three alternative approaches and expanded the temporal horizon of dengue prediction for Selangor with the ability to forecast approximately 60 weeks ahead with a Mean Absolute Percentage Error (MAPE) of 13.97 for the chosen prediction window before the implementation of the Movement Control Order (MCO) in Malaysia. Extended validation across subsequent periods also indicates relatively satisfactory forecasting performance (with MAPE ranging from 13.12 to 17.09). This research contributed to the field by introducing a novel framework for the prediction of dengue cases over an extended temporal range.
first_indexed 2025-11-15T03:53:11Z
format Article
id ump-43811
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:53:11Z
publishDate 2025
publisher KeAi Communications Co.
recordtype eprints
repository_type Digital Repository
spelling ump-438112025-02-13T08:38:48Z http://umpir.ump.edu.my/id/eprint/43811/ Application of multiple linear regression model and long short-term memory with compartmental model to forecast dengue cases in Selangor, Malaysia based on climate variables Lu, Xinyi Teh, Su Yean Tay, Chai Jian Nur Faeza, Abu Kassim Fam, Pei Shan Soewono, Edy Q Science (General) QA Mathematics Despite the implementation of various initiatives, dengue remains a significant public health concern in Malaysia. Given that dengue has no specific treatment, dengue prediction remains a useful early warning mechanism for timely and effective deployment of public health preventative measures. This study aims to develop a comprehensive approach for forecasting dengue cases in Selangor, Malaysia by incorporating climate variables. An ensemble of Multiple Linear Regression (MLR) model, Long Short-Term Memory (LSTM), and Susceptible-Infected mosquito vectors, Susceptible-Infected-Recovered human hosts (SI-SIR) model were used to establish a relation between climate variables (temperature, humidity, precipitation) and mosquito biting rate. Dengue incidence subject to climate variability can then be projected by SI-SIR model using the forecasted mosquito biting rate. The proposed approach outperformed three alternative approaches and expanded the temporal horizon of dengue prediction for Selangor with the ability to forecast approximately 60 weeks ahead with a Mean Absolute Percentage Error (MAPE) of 13.97 for the chosen prediction window before the implementation of the Movement Control Order (MCO) in Malaysia. Extended validation across subsequent periods also indicates relatively satisfactory forecasting performance (with MAPE ranging from 13.12 to 17.09). This research contributed to the field by introducing a novel framework for the prediction of dengue cases over an extended temporal range. KeAi Communications Co. 2025 Article PeerReviewed pdf en cc_by_nc_nd_4 http://umpir.ump.edu.my/id/eprint/43811/1/Application%20of%20multiple%20linear%20regression%20model%20and%20long%20short-term%20memory.pdf Lu, Xinyi and Teh, Su Yean and Tay, Chai Jian and Nur Faeza, Abu Kassim and Fam, Pei Shan and Soewono, Edy (2025) Application of multiple linear regression model and long short-term memory with compartmental model to forecast dengue cases in Selangor, Malaysia based on climate variables. Infectious Disease Modelling, 10 (1). pp. 240-256. ISSN 2468-2152. (Published) https://doi.org/10.1016/j.idm.2024.10.007 https://doi.org/10.1016/j.idm.2024.10.007
spellingShingle Q Science (General)
QA Mathematics
Lu, Xinyi
Teh, Su Yean
Tay, Chai Jian
Nur Faeza, Abu Kassim
Fam, Pei Shan
Soewono, Edy
Application of multiple linear regression model and long short-term memory with compartmental model to forecast dengue cases in Selangor, Malaysia based on climate variables
title Application of multiple linear regression model and long short-term memory with compartmental model to forecast dengue cases in Selangor, Malaysia based on climate variables
title_full Application of multiple linear regression model and long short-term memory with compartmental model to forecast dengue cases in Selangor, Malaysia based on climate variables
title_fullStr Application of multiple linear regression model and long short-term memory with compartmental model to forecast dengue cases in Selangor, Malaysia based on climate variables
title_full_unstemmed Application of multiple linear regression model and long short-term memory with compartmental model to forecast dengue cases in Selangor, Malaysia based on climate variables
title_short Application of multiple linear regression model and long short-term memory with compartmental model to forecast dengue cases in Selangor, Malaysia based on climate variables
title_sort application of multiple linear regression model and long short-term memory with compartmental model to forecast dengue cases in selangor, malaysia based on climate variables
topic Q Science (General)
QA Mathematics
url http://umpir.ump.edu.my/id/eprint/43811/
http://umpir.ump.edu.my/id/eprint/43811/
http://umpir.ump.edu.my/id/eprint/43811/
http://umpir.ump.edu.my/id/eprint/43811/1/Application%20of%20multiple%20linear%20regression%20model%20and%20long%20short-term%20memory.pdf