Risk-Aware Identification of Highly Suspected COVID-19 Cases in Social IoT: A Joint Graph Theory and Reinforcement...

Area of Science:

• Epidemiology
• Network Science
• Computer Science

Background:

• The COVID-19 pandemic necessitates early identification and risk prediction strategies.
• Controlling disease spread requires understanding transmission dynamics and social interactions.

Purpose of the Study:

• To develop a method for early COVID-19 case identification and spread control.
• To leverage Social Internet of Things (SIoT) for resource allocation to influential individuals.

Main Methods:

• Utilized differential contact intensity and infectious rates within a susceptible-exposed-infected-removed (SEIR) model.
• Transformed the problem into a minimum weight vertex cover (MWVC) problem in graph theory.
• Employed graph embedding and reinforcement learning for adaptive control in dynamic networks.

Main Results:

• The proposed adaptive scheme effectively reduced the epidemiological reproduction rate.
• Demonstrated the efficacy of the approach using real-life datasets.
• The technique shows potential for assisting in early COVID-19 case identification.

Conclusions:

• The SIoT-based approach offers a novel strategy for pandemic control.
• Resource allocation to high-degree individuals is crucial for mitigating disease propagation.
• This method can aid public health initiatives in managing infectious disease outbreaks.