Intervention-Aware Epidemic Prediction by Enhanced Whale Optimization

In recent decades, new epidemics have seriously endangered people's lives and are now the leading cause of death in the world. The prevention of pandemic diseases has therefore become a top priority today. However, effective prevention remains a difficult challenge due to factors such as transmission mechanisms, lack of documentation of clinical outcomes, and population control. To this end, this paper proposes a susceptible-exposed-infected-quarantined (hospital or home)-recovered (SEIQHR) model based on human intervention strategies to simulate and predict recent outbreak transmission trends and peaks in Changchun, China. In this study, we introduce Levy operator and random mutation mechanism to reduce the possibility of the algorithm falling into a local optimum. The algorithm is then used to identify the parameters of the model optimally. The validity and adaptability of the proposed model are verified by fitting experiments to the number of infections in cities in China that had COVID-19 outbreaks in previous periods (Nanjing, Wuhan, and Xi'an), where the peaks and trends obtained from the experiments largely match the actual situation. Finally, the model is used to predict the direction of the disease in Changchun, China, for the coming period. The results indicated that the number of COVID-19 infections in Changchun would peak around April 3 and continue to decrease until the end of the outbreak. These predictions can help the government plan countermeasures to reduce the expansion of the epidemic.