The Research of SEIJR Model with Time-Delay based on 2019-nCov

Siyi, S.; Yangping, Z.

A global epidemic disease known as the novel coronavirus (2019-nCov) had seriously hit the most area around the whole world causing unpredictable loss of manpower and finance during the past one year. Modeling the spread and development of infectious diseases represented by new Coronavirus has become an important part of public health work in the world. Estimation of possible infection population and prospective suggestion of handling spread based on exist data are of crucial importance. Considering of the biology parameters obtained based on Chinese clinical data in Wuhan and real spread feature of 2019-nCov in Italy, we build a more applicable model called SEIJR with log-normal distributed time delay to forecast the trend of spreading. Adopting Particle Swarm Optimization (PSO), we estimate the early period average spreading velocity (α0) and implement inversion analysis of time point (T0) when the virus first hit the Italy. Based on fixed α0 and T0, we then obtained the average spreading velocity α1 after the area lockdown using PSO. The result shows that it will be helpful in addressing the infection by generating the prediction trends of different αwhich we considered. Finally, our research applies Logistic regression, Neutral Network embedding LSTM layer, which are two representative machine learning algorithms, to directly predict future infection trend and compare the forecast with result yielded by mathematical model adopting differential equations. Not only solved the complex, nondifferentiable equation of epidemic model, this research also performs well in inversion analysis based on PSO which conveys informative outcomes for further discussion on precautious action. The comparison with the machine learning algorithms shows that the 2019-nCov based epidemic dynamics assumption is reasonable and helpful to mathematical model, which is better than the data driven machine learning algorithms. Code can be freely downloaded from https://github.com/Summerwork/2019-nCov-Prediction. Author