A Binary Particle Swarm Optimizer With Priority Planning and Hierarchical Learning for Networked Epidemic Control

The control of epidemics taking place in complex networks has been an increasingly active topic public health management. In this article, we propose efficient networked epidemic system, where a modified susceptible-exposed-infected-vigilant (SEIV) model is first built to simulate spreading. Then, different from existing continuous resource models which abstractly map resources parameters models, concrete description real-world goods/services and their allocation. Based on the two cost-constraint subset selection problem identified. To solve problem, swarm-based stochastic optimization policy proposed, each particle swarm can determine its own solutions according guidance superior peers historical searching experience whole swarm, without extra problem-relative information. Theoretical proof about system equilibrium provided, consistent with experimental observations. competitive performance proposed optimizer validated by theoretical analysis comparison experiments. Finally, application case provided illustrate practicability.