• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

利用动力学信息神经网络进行COVID-19传播的预测建模：一种混合SEIRV-DNNs方法。

Leveraging dynamics informed neural networks for predictive modeling of COVID-19 spread: a hybrid SEIRV-DNNs approach.

作者信息

Cheng Cheng, Aruchunan Elayaraja, Noor Aziz Muhamad Hifzhudin

机构信息

Institute of Mathematical Sciences, Faculty of Science, Universiti Malaya, 50603, Kuala Lumpur, Malaysia.

Department of Decision Science, Faculty of Business and Economics, Universiti Malaya, 50603, Kuala Lumpur, Malaysia.

出版信息

Sci Rep. 2025 Jan 15;15(1):2043. doi: 10.1038/s41598-025-85440-1.

DOI:10.1038/s41598-025-85440-1
PMID:39814760
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11735935/
Abstract

A dynamics informed neural networks (DINNs) incorporating the susceptible-exposed-infectious-recovered-vaccinated (SEIRV) model was developed to enhance the understanding of the temporal evolution dynamics of infectious diseases. This work integrates differential equations with deep neural networks to predict time-varying parameters in the SEIRV model. Experimental results based on reported data from China between January 1, and December 1, 2022, demonstrate that the proposed dynamics informed neural networks (DINNs) method can accurately learn the dynamics and predict future states. Our proposed hybrid SEIRV-DNNs model can also be applied to other infectious diseases such as influenza and dengue, with some modifications to the compartments and parameters in the model to accommodate the related control measures. This approach will facilitate improving predictive modeling and optimizing public health intervention strategies.

摘要

为了更好地理解传染病的时间演变动态，开发了一种结合易感-暴露-感染-康复-接种（SEIRV）模型的动力学信息神经网络（DINNs）。这项工作将微分方程与深度神经网络相结合，以预测SEIRV模型中的时变参数。基于中国2022年1月1日至12月1日报告数据的实验结果表明，所提出的动力学信息神经网络（DINNs）方法能够准确学习动态并预测未来状态。我们提出的混合SEIRV-DNNs模型也可以应用于其他传染病，如流感和登革热，只需对模型中的隔室和参数进行一些修改，以适应相关的控制措施。这种方法将有助于改进预测建模和优化公共卫生干预策略。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/350d6f348f1b/41598_2025_85440_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/284269662ccf/41598_2025_85440_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/9c01eda7f183/41598_2025_85440_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/63b284d82a0c/41598_2025_85440_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/eeda09cee82c/41598_2025_85440_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/0a545ac811e1/41598_2025_85440_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/3060720c846e/41598_2025_85440_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/350d6f348f1b/41598_2025_85440_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/284269662ccf/41598_2025_85440_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/9c01eda7f183/41598_2025_85440_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/63b284d82a0c/41598_2025_85440_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/eeda09cee82c/41598_2025_85440_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/0a545ac811e1/41598_2025_85440_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/3060720c846e/41598_2025_85440_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/2536/11735935/350d6f348f1b/41598_2025_85440_Fig7_HTML.jpg

相似文献

1
Leveraging dynamics informed neural networks for predictive modeling of COVID-19 spread: a hybrid SEIRV-DNNs approach.利用动力学信息神经网络进行COVID-19传播的预测建模：一种混合SEIRV-DNNs方法。
Sci Rep. 2025 Jan 15;15(1):2043. doi: 10.1038/s41598-025-85440-1.
2
Epi-DNNs: Epidemiological priors informed deep neural networks for modeling COVID-19 dynamics.Epi-DNNs：基于流行病学先验信息的深度神经网络模型用于 COVID-19 动力学研究。
Comput Biol Med. 2023 May;158:106693. doi: 10.1016/j.compbiomed.2023.106693. Epub 2023 Feb 28.
3
A simple yet effective approach for predicting disease spread using mathematically-inspired diffusion-informed neural networks.一种使用受数学启发的扩散信息神经网络预测疾病传播的简单而有效的方法。
Sci Rep. 2025 Apr 29;15(1):15000. doi: 10.1038/s41598-025-98398-x.
4
A stochastic numerical analysis based on hybrid NAR-RBFs networks nonlinear SITR model for novel COVID-19 dynamics.基于混合 NAR-RBFs 网络非线性 SITR 模型的新型 COVID-19 动力学的随机数值分析。
Comput Methods Programs Biomed. 2021 Apr;202:105973. doi: 10.1016/j.cmpb.2021.105973. Epub 2021 Feb 7.
5
Physics-Informed Neural Networks Integrating Compartmental Model for Analyzing COVID-19 Transmission Dynamics.物理信息神经网络整合房室模型分析 COVID-19 传播动力学。
Viruses. 2023 Aug 16;15(8):1749. doi: 10.3390/v15081749.
6
Transmission dynamics informed neural network with application to COVID-19 infections.基于传播动力学的神经网络及其在 COVID-19 感染中的应用。
Comput Biol Med. 2023 Oct;165:107431. doi: 10.1016/j.compbiomed.2023.107431. Epub 2023 Sep 1.
7
Neural networks to model COVID-19 dynamics and allocate healthcare resources.用于模拟新冠疫情动态并分配医疗资源的神经网络。
Sci Rep. 2025 May 2;15(1):15326. doi: 10.1038/s41598-025-00153-9.
8
Understanding the implications of under-reporting, vaccine efficiency and social behavior on the post-pandemic spread using physics informed neural networks: A case study of China.利用物理信息神经网络理解漏报、疫苗效率和社会行为对大流行后传播的影响：以中国为例的案例研究。
PLoS One. 2023 Nov 16;18(11):e0290368. doi: 10.1371/journal.pone.0290368. eCollection 2023.
9
Prediction of SARS-CoV-2 infection cases based on the meta-SEIRS model.基于元 SEIRS 模型预测 SARS-CoV-2 感染病例。
Epidemiol Infect. 2024 Nov 18;152:e144. doi: 10.1017/S0950268824001274.
10
Modeling epidemic dynamics using Graph Attention based Spatial Temporal networks.基于图注意力的时空网络的传染病动力学建模。
PLoS One. 2024 Jul 15;19(7):e0307159. doi: 10.1371/journal.pone.0307159. eCollection 2024.

引用本文的文献

1
Modeling and analysis of a delayed fractional order COVID-19 SEIHRM model with media coverage in Malaysia.马来西亚考虑媒体报道的延迟分数阶 COVID-19 SEIHRM 模型的建模与分析
Sci Rep. 2025 Jul 13;15(1):25305. doi: 10.1038/s41598-025-99389-8.

本文引用的文献

1
Chaos theory in the understanding of COVID-19 pandemic dynamics.混沌理论在理解 COVID-19 大流行动力学中的作用。
Gene. 2024 Jun 20;912:148334. doi: 10.1016/j.gene.2024.148334. Epub 2024 Mar 7.
2
A study on the factors influencing the intention to receive booster shots of the COVID-19 vaccine in China based on the information frame effect.基于信息框架效应的中国民众对 COVID-19 疫苗加强针接种意愿影响因素研究。
Front Public Health. 2024 Feb 20;12:1258188. doi: 10.3389/fpubh.2024.1258188. eCollection 2024.
3
Combining the dynamic model and deep neural networks to identify the intensity of interventions during COVID-19 pandemic.
结合动态模型和深度神经网络识别 COVID-19 大流行期间干预措施的强度。
PLoS Comput Biol. 2023 Oct 18;19(10):e1011535. doi: 10.1371/journal.pcbi.1011535. eCollection 2023 Oct.
4
Transmission dynamics informed neural network with application to COVID-19 infections.基于传播动力学的神经网络及其在 COVID-19 感染中的应用。
Comput Biol Med. 2023 Oct;165:107431. doi: 10.1016/j.compbiomed.2023.107431. Epub 2023 Sep 1.
5
Physics-Informed Neural Networks Integrating Compartmental Model for Analyzing COVID-19 Transmission Dynamics.物理信息神经网络整合房室模型分析 COVID-19 传播动力学。
Viruses. 2023 Aug 16;15(8):1749. doi: 10.3390/v15081749.
6
On the Implementation of the Artificial Neural Network Approach for Forecasting Different Healthcare Events.关于人工神经网络方法在预测不同医疗事件中的应用
Diagnostics (Basel). 2023 Mar 31;13(7):1310. doi: 10.3390/diagnostics13071310.
7
Epi-DNNs: Epidemiological priors informed deep neural networks for modeling COVID-19 dynamics.Epi-DNNs：基于流行病学先验信息的深度神经网络模型用于 COVID-19 动力学研究。
Comput Biol Med. 2023 May;158:106693. doi: 10.1016/j.compbiomed.2023.106693. Epub 2023 Feb 28.
8
Optimizing deep neural networks to predict the effect of social distancing on COVID-19 spread.优化深度神经网络以预测社交距离对新冠病毒传播的影响。
Comput Ind Eng. 2022 Apr;166:107970. doi: 10.1016/j.cie.2022.107970. Epub 2022 Jan 29.
9
Comparison of ARIMA model, DNN model and LSTM model in predicting disease burden of occupational pneumoconiosis in Tianjin, China.比较中国天津职业性尘肺病疾病负担的 ARIMA 模型、DNN 模型和 LSTM 模型。
BMC Public Health. 2022 Nov 24;22(1):2167. doi: 10.1186/s12889-022-14642-3.
10
Effect of vaccination patterns and vaccination rates on the spread and mortality of the COVID-19 pandemic.疫苗接种模式和接种率对新冠疫情传播及死亡率的影响。
Health Policy Technol. 2023 Mar;12(1):100699. doi: 10.1016/j.hlpt.2022.100699. Epub 2022 Nov 18.