基于加权平均樽海鞘群算法和BP神经网络的COVID-19预测

Prediction of COVID-19 Based on the Weighted Average Salp Swarm Algorithm and BP Neural Network

新型冠状病毒肺炎以其高传染性和高致病性成为全球关注的问题之一.有效预测COVID-19的累计确诊人数对COVID-19的防控具有重要价值.本文提出加权平均樽海鞘群算法(AVSSA),通过23个基准函数验证了AVSSA的有效性,进而利用AVSSA优化BP神经网络建立预测模型AVSSA-BP,实现COVID-19的预测.实验结果表明预测模型AVSSA-BP有最小的误差和最高的确定性系数,验证了AVSSA-BP的有效性.

Corona Virus Disease 2019(COVID-19)is one of the global concerns due to its highly infectious and highly pathogenic coronavirus.It is of great value to effectively predict the cumulative number of confirmed cases of COVID-19 for the prevention and control of COVID-19.In this paper,the weighted average salp swarm algorithm is proposed,named by AVSSA,whose validation is performed by 23 benchmark functions.Then AVSSA is utilized to optimize the parameters of BP neural network to establish the predicted model AVSSA-BP for predicting the COVID-19.The experimental results show that the predicted model AVSSA-BP has the least errors and the highest coefficient of determination.Therefore,the proposed AVSSA is an effective algorithm.