Your browser doesn't support javascript.
loading
A swarm-optimizer-assisted simulation and prediction model for emerging infectious diseases based on SEIR.
Shi, Xuan-Li; Wei, Feng-Feng; Chen, Wei-Neng.
Afiliación
  • Shi XL; School of Computer Science and Engineering, South China University of Technology, Guangzhou, 510006 China.
  • Wei FF; School of Computer Science and Engineering, South China University of Technology, Guangzhou, 510006 China.
  • Chen WN; School of Computer Science and Engineering, South China University of Technology, Guangzhou, 510006 China.
Complex Intell Systems ; 9(2): 2189-2204, 2023.
Article en En | MEDLINE | ID: mdl-36405533
Mechanism-driven models based on transmission dynamics and statistic models driven by public health data are two main methods for simulating and predicting emerging infectious diseases. In this paper, we intend to combine these two methods to develop a more comprehensive model for the simulation and prediction of emerging infectious diseases. First, we combine a standard epidemic dynamic, the susceptible-exposed-infected-recovered (SEIR) model with population migration. This model can provide a biological spread process for emerging infectious diseases. Second, to determine suitable parameters for the model, we propose a data-driven approach, in which the public health data and population migration data are assembled. Moreover, an objective function is defined to minimize the error based on these data. Third, based on the proposed model, we further develop a swarm-optimizer-assisted simulation and prediction method, which contains two modules. In the first module, we use a level-based learning swarm optimizer to optimize the parameters required in the epidemic mechanism. In the second module, the optimized parameters are used to predicate the spread of emerging infectious diseases. Finally, various experiments are conducted to validate the effectiveness of the proposed model and method.
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Prognostic_studies / Risk_factors_studies Idioma: En Revista: Complex Intell Systems Año: 2023 Tipo del documento: Article Pais de publicación: Alemania

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Tipo de estudio: Prognostic_studies / Risk_factors_studies Idioma: En Revista: Complex Intell Systems Año: 2023 Tipo del documento: Article Pais de publicación: Alemania