Modelling the Transmission of Dengue Fever Based on Spatial and Temporal Patterns

Dengue fever (DF) is a vector-borne disease that has transmit alarmingly in recent decades and has now affected the populations of roughly 100 nations, primarily in tropical and subtropical regions. Approximately 390 million cases of dengue fever are reported each year among people living in 128 countries, according to the World Health Organization (WHO). Viral, host, and vector interactions result in complex spatiotemporal patterns in dengue disease. Moreover, it has been previously indicated that the dengue fever epidemic is due to several climatic, social, environmental, and biological factors, and these factors vary from place to place and with time. Therefore, an accurate spatiotemporal prediction model is essential to understand disease patterns and improve the monitoring and control of potential threats. Several research gaps in previous DF spatiotemporal prediction models are addressed in this work: (i) the lack of a comprehensive framework that ensures better spatiotemporal prediction models; (ii) the lack of work on missing spatiotemporal data and data quality; (iii) the lack of testing and comparison between the performance of different traditional and advanced spatiotemporal modelling approaches; and (iv) the lack of consideration of simulation maps based on optimal pre-processing analysis as a means of controlling future disease threats. This research is intended to address these shortcomings and contributes to the literature by (i) improving the current understanding of the spatiotemporal patterns of DF; (ii) developing a comprehensive framework to improve the spatial and temporal prediction models' performance, and can effectively estimate the potential risk of disease that will help authorities allocate resources and implement effective control measures at a district scale; (iii) examining previous DF spatiotemporal modelling approaches and significant disease-related factors using a geographical information system and machine learning methods; (iv) analysing and improving the quality of collected data and investigating several traditional and advanced imputation approaches used to fill missing values in order to provide more reliable and unbiased results; and (v) visualising a simulation of potential future risk areas as a simple mechanism to assist decision-makers to control the disease.

Author dc:creator

• Siddiq, Ali Hasan M.

Statement dc:rights

• info:eu-repo/semantics/openAccess
• The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
• © 2023 Ali Hasan M. Siddiq
• au.edu.uts.lib/cph

Language dc:language.iso

en_US

Handle dc:identifier.uri

http://hdl.handle.net/10453/171489

OAI identifier oai:identifier

oai:opus.lib.uts.edu.au:10453/171489