Skip to main content

Research Repository

Advanced Search

Optimizing Pandemic Control Strategies: A Deep Reinforcement Learning Approach in Public Health Management

Ibraimoh, Raphael

Optimizing Pandemic Control Strategies: A Deep Reinforcement Learning Approach in Public Health Management Thumbnail


Authors

Raphael Ibraimoh



Contributors

Abstract

COVID-19, also known as the SARS-CoV-2 coronavirus, has paralysed the world and
forced people to change their lifestyles. Since COVID-19 deaths are increasing daily, the
disease has become a global public health issue. Different countries used different public
health guidelines to avoid human-to-human transmission. Personal hygiene, hand washing
and sanitization, face masks for social distance, comprehensive testing, and, in the worst
case, a lockdown and travel restriction are rules.
This research seeks the optimal lockdowns and border control approach for timely lockdown
and travel limitations. This thesis attempts to use UK data from the global pandemic
dataset. The data was trained using DRL algorithm to determine lockout and travel limitation
timing. This is the first study to use deep reinforcement learning to determine
the best UK lockdown and border control method. A unique base model, Duelling Double
Deep Q-Network (D3QN), a variation of the Deep Q-Network algorithm (DQN), was
used to train COVID-19 epidemic dataset and evaluated on test data. Public health and
government will be able to execute prompt and appropriate lockdown and border control
policies to minimise the disease’s spread, improving people’s quality of life and lowering
costs.
Initial lockdown and travel restrictions reduced COVID-19 load. However, our agency
advised the UK to lock down or restrict travel before or on the index case (the first deceased recoded). Moreover, the agent frequently called for a full lockdown, border closures, travel
restrictions, and more harsh security measures than public health. This study assesses the
positive effects of preventing COVID-19’s spread on population health while considering its
negative economic and social effects. Finally, average moving reward was used to compare
baselines.

Citation

Ibraimoh, R. (2024). Optimizing Pandemic Control Strategies: A Deep Reinforcement Learning Approach in Public Health Management. (Thesis). University of Salford

Thesis Type Thesis
Deposit Date May 24, 2024
Publicly Available Date Jul 1, 2024
Award Date May 31, 2024