粒子群可拓的新冠肺炎建模与仿真  

Modeling and Simulation of COVID-19 Based on Extension of Particle Swarm Optimization

作　　者：孙群[1,2] 袁宏俊[2,3] SUN Qun;YUAN Hongjun(Anhui Vocational College of Electronics&Information Technology,Bengbu,China,233030;School of Mathematical&Computational Science,Anhui University,Hefei,China,230039;School of Statistics and Applied Mathematics,Anhui University of Finance&Economics,Bengbu,China,230039)

机构地区：[1]安徽电子信息职业技术学院,安徽蚌埠233030 [2]安徽大学数学与计算科学学院,安徽合肥230039 [3]安徽财经大学统计与应用数学学院,安徽蚌埠233030

出　　处：《福建电脑》2021年第1期17-19,共3页Journal of Fujian Computer

基　　金：安徽省教育厅高校人文社会科学重点研究项目“模糊信息集成算子的构建及在经济预测中应用的研究”(No.SK2018A0431)资助。

摘　　要：本文提出了一种基于粒子群可拓神经网络预测模型。根据国外近段时间每日新增新冠肺炎确诊人数,利用可拓神经网络模型对国外日新增新冠肺炎确诊人数进行预测,并利用粒子群算法(PSO)对权值进行优化,最后与LSSVM、ABC-LSSVM及PSO-LSSVM模型进行比较。结果表明:采用文中提出的粒子群可拓神经网络模型拟合效果较好,精度较高,性能优于其他三种模型,适用于COVID-19的疫情研究。An extension neural network prediction model based on particle swarm optimization(PSO)is proposed,the number of newly diagnosed coronary pneumonia in foreign countries was fitted and predicted by extension neural network model,and the weight was optimized by particle swarm optimization(PSO),compared with LSSVM,ABC-LSSVM and PSO-LSSVM models.The results show that the particle swarm extension neural network model proposed in this paper has a better fitting effect,higher precision and better performance than the other three models.It is suitable for the epidemic research of COVID-19.

关 键 词：粒子群群算法 可拓神经网络 新冠肺炎确诊人数 预测分析 

分 类 号：TU311[建筑科学—结构工程]