Multi-stage COVID-19 Epidemic Modeling Based on PSO and SEIR

In this study, based on the characteristics and the transmission mechanism of COVID-19, SEIR epidemiological model is employed for modeling and analysis, utilizing the data of Hubei Province. To optimize the key epidemic parameters of the proposed SEIR model, a stochastic computational intelligence approach, the Particle Swarm Optimization (PSO) is introduced. To better analyze the epidemic, the data between January 20, 2020 to March 25, 2020 is selected and divided into four stages. The parameters are dynamically changeable at different stages of the epidemic, which shows the effectiveness of public health prevention and control measures. Moreover, the Genetic Algorithm (GA) and the Bacterial Foraging Optimization (BFO) are also executed for comparison. The experimental results demonstrate that all swarm intelligence algorithms mentioned above can help forecast COVID-19, and PSO shows the advantages of faster convergence speed and the capability of finding a better set of solutions in fewer iterations, particularly. © 2021, Springer Nature Switzerland AG.

[1]  Yaqing Fang,et al.  Transmission dynamics of the COVID‐19 outbreak and effectiveness of government interventions: A data‐driven analysis , 2020, Journal of medical virology.

[2]  I B Schwartz,et al.  Seasonality and period-doubling bifurcations in an epidemic model. , 1984, Journal of theoretical biology.

[3]  L. Yang,et al.  Preliminary estimation of the basic reproduction number of novel coronavirus (2019-nCoV) in China, from 2019 to 2020: A data-driven analysis in the early phase of the outbreak , 2020, International Journal of Infectious Diseases.

[4]  Zidong Wang,et al.  A new switching-delayed-PSO-based optimized SVM algorithm for diagnosis of Alzheimer's disease , 2018, Neurocomputing.

[5]  Liangrong Peng,et al.  Epidemic analysis of COVID-19 in China by dynamical modeling , 2020, medRxiv.

[6]  M Suchetha,et al.  PSO optimized 1-D CNN-SVM architecture for real-time detection and classification applications , 2019, Comput. Biol. Medicine.

[7]  G. Leung,et al.  Nowcasting and forecasting the potential domestic and international spread of the 2019-nCoV outbreak originating in Wuhan, China: a modelling study , 2020, The Lancet.

[8]  Phase-adjusted estimation of the number of Coronavirus Disease 2019 cases in Wuhan, China. , 2020, Cell discovery.

[9]  Daozhou Gao,et al.  Estimating the Unreported Number of Novel Coronavirus (2019-nCoV) Cases in China in the First Half of January 2020: A Data-Driven Modelling Analysis of the Early Outbreak , 2020, Journal of clinical medicine.

[10]  W. Liang,et al.  Modified SEIR and AI prediction of the epidemics trend of COVID-19 in China under public health interventions , 2020, Journal of thoracic disease.