[1]庞梦吟,王海宁,万通明,等.基于组合预测模型的疫情确诊人数预测[J].计算机技术与发展,2022,32(11):198-203.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 029]
　PANG Meng-yin,WANG Hai-ning,WAN Tong-ming,et al.Epidemic Data Prediction Based on Combined Prediction Model[J].,2022,32(11):198-203.[doi:10. 3969 / j. issn. 1673-629X. 2022. 11. 029]
点击复制

基于组合预测模型的疫情确诊人数预测()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年11期
页码:
198-203
栏目:
新型计算应用系统
出版日期:
2022-11-10

文章信息/Info

Title:
Epidemic Data Prediction Based on Combined Prediction Model
文章编号:
1673-629X(2022)11-0198-06
作者:
庞梦吟1 ; 王海宁1 ; 万通明1 ; 马 苗1; 2*
1. 陕西师范大学 计算机科学学院,陕西 西安 710119;
2. 空天地海一体化大数据应用技术国家工程实验室,陕西 西安 710129
Author(s):
PANG Meng-yin1 ; WANG Hai-ning1 ; WAN Tong-ming1 ; MA Miao1; 2*
1. School of Computer Science,Shaanxi Normal University,Xi’an 710119,China;
2. National Engineering Laboratory for Integrated Aero-space-ground-ocean Big Data Application Technology,Xi’an 710129,China
关键词:
Logistic 模型; LSTM 模型; 组合预测模型; 深度学习; 公共卫生安全事件
Keywords:
Logistic prediction model; LSTM; combined prediction model; deep learning; public health and safety incidents
分类号:
TP183
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 11. 029
摘要:
公共卫生安全事件常常是牵动着一个地区、一个国家,乃至整个世界的重大问题。 2019 年底爆发的新型冠状病毒(Corona Virus Disease 2019,COVID-19) 疫情迅速席卷了很多国家,及时了解疫情确诊人数变化,对协助挖掘肺炎疫情的传播模式和特征规律十分重要。 针对此问题,提出了一种组合预测模型来预测此次新型冠状病毒肺炎累计确诊人数数量。首先从国家卫生健康委员会等权威机构所发布的数据中获取历史累计确诊人数,然后再以 Logistic 模型和长短期记忆深度学习网络模型( Long Short-Term Memory,LSTM) 的预测结果为基础,选取一定时间段的累计确诊人数序列来训练线性组合参数,得到最终的组合预测模型,最后通过 RMSE 等预测性能评价指标对比所提模型和 Logistic、LSTM 和 SEIR 等三种模型的预测性能。 实验结果表明,所提模型的 RMSE 值为 10. 101 7,MAE 值为 7. 633 6,MAPE 值为 0. 008 3% ,其准确性和拟合效果均优于其他模型,能够为后续的疫情预测和防控工作提供技术支撑。
Abstract:
Public health security incidents are often major issues that affect a region,a country,and even the entire world. The outbreak ofcorona virus disease 2019 ( COVID-19) quickly swept across many countries,and timely understanding of the changes in the number ofconfirmed cases of the epidemic is very important to assist in the discovery of the transmission pattern and characteristics of thepneumonia epidemic. In response to this problem, we propose a combined prediction model to predict the cumulative number ofconfirmed cases of COVID-19. Firstly,? the historical cumulative number of diagnoses is obtained from the data released by the NationalHealth Commission and other authoritative institutions. Then based on prediction results of the Logistic model and the long short-termmemory deep learning network model ( LSTM) ,the sequence of the cumulative confirmed number of people in a certain period of time isselected? ?to train the linear combination parameters to obtain the final combined prediction model. Finally,the proposed model and thethree models of Logistic, LSTM and SEIR are compared in terms of performance according to the prediction performance evaluationindicators such as RMSE. The experimental results show that the RMSE of the proposed model is 10. 101 7,the MAE is? ? 7. 633 6,and theMAPE is 0. 008 3% . Its accuracy and fitting effect are better than other models, which can provide technical support for subsequentepidemic prediction and prevention and control.

相似文献/References:

[1]胡万亭,郭建英,张继永.一种基于改进 ELMO 模型的组织机构名识别方法[J].计算机技术与发展,2020,30(11):25.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 005]
　HU Wan-ting,GUO Jian-ying,ZHANG Ji-yong.An Organization Name Recognition Method Based on Improved ELMO Model[J].,2020,30(11):25.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 005]
[2]范禹辰,刘相坤,朱建生,等.基于 BERT 的服务网站 Web 攻击检测研究[J].计算机技术与发展,2022,32(08):168.[doi:10. 3969 / j. issn. 1673-629X. 2022. 08. 027]
　FAN Yu-chen,LIU Xiang-kun,ZHU Jian-sheng,et al.Research on Web Attack Detection of Service Website Based on BERT[J].,2022,32(11):168.[doi:10. 3969 / j. issn. 1673-629X. 2022. 08. 027]

更新日期/Last Update: 2022-11-10