Last Updated: 27/03/2026
Network-based modeling, reasoning and optimization methods and their empirical research in malaria surveillance
Objectives
This project aims to present a computational epidemiology framework consisting of modules about network-based system modeling, network inference, and network optimization so as to achieve optimal resource allocation for disease surveillance and control. Specifically, this project will focus on the implementation and study of this framework on the malaria transmission and control in Yunnan, China.
The transmission of infectious diseases, which can be affected by various interactive impact factors, has induced enormous damages on human health and security. First, to model the impact of human movement on the spatial transmission of malaria, we will present a network-based transmission model by taking into consideration various dynamically changing impact factors, such as temperature and rainfall. Then, combing with the reported spatial and temporal malaria cases, this project further aims to learn or infer model parameters and underlying transmission networks by design two kinds of machine learning algorithms. The learning results will be empirically validated by frontline workers in Yunnan. Finally, based on the inferred malaria transmission networks and the concept of network optimization, this project will further study two kinds of resource allocation problems during malaria surveillance and control. With respect to the real-world situation, the focus is mainly on the problem of how to design an incentive mechanism such that resources can be optimally allocated at the system level by the self-organization and cooperation of authorities/organizations at the local level. This demonstrated framework, models, and methods in this project will offer new insights into the surveillance and control of other infectious diseases.
Jan 2015 — Dec 2017
$35,187
Related Resources
