• 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

重复时间序列交叉验证：一种提高马来西亚新冠疫情预测准确性的新方法。

Repeated time-series cross-validation: A new method to improved COVID-19 forecast accuracy in Malaysia.

作者信息

Abdul Aziz Azlan, Yusoff Marina, Yaacob Wan Fairos Wan, Mustaffa Zuriani

机构信息

College of Computing, Informatics and Mathematics, Universiti Teknologi MARA (UiTM) Cawangan Perlis, Arau 02600, Perlis, Malaysia.

Statistical Analytics, Forecasting & Innovation (SAFI) Research Interest Group, Universiti Teknologi MARA Cawangan Perlis, Arau 02600, Perlis, Malaysia.

出版信息

MethodsX. 2024 Oct 30;13:103013. doi: 10.1016/j.mex.2024.103013. eCollection 2024 Dec.

DOI:10.1016/j.mex.2024.103013
PMID:39559463
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11570750/
Abstract

Forecasting COVID-19 cases is challenging, and inaccurate forecast values will lead to poor decision-making by the authorities. Conversely, accurate forecasts aid Malaysian government authorities and agencies (National Security Council, Ministry of Health, Ministry of Finance, Ministry of Education, and Ministry of International Trade and Industry) and financial institutions in formulating action plans, regulations, and legal acts to control COVID-19 spread in the country. Therefore, this study proposes Repeated Time-Series Cross-Validation, a new data-splitting strategy to identify the best forecasting model that is capable of producing the lowest error measures value and a high percentage of forecast accuracy for COVID-19 prediction in Malaysia. Some of the highlights of the proposed method are:•A total of 21 models, five data partitioning sets, and four error measures to improve the forecast accuracy of daily COVID-19 cases in Malaysia.•The best model selected produces the lowest error measure value for the Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Scaled Error (MASE).•The average 8-day forecast accuracy is 90.2 %. The lowest and highest forecast accuracy was 83.7 % and 98.7 %.

摘要

预测新冠肺炎病例具有挑战性，不准确的预测值会导致当局做出错误决策。相反，准确的预测有助于马来西亚政府当局和机构（国家安全委员会、卫生部、财政部、教育部和国际贸易与工业部）以及金融机构制定行动计划、法规和法律行为，以控制该国新冠肺炎的传播。因此，本研究提出了重复时间序列交叉验证，这是一种新的数据拆分策略，用于识别能够产生最低误差测量值和高预测准确率的最佳预测模型，以预测马来西亚的新冠肺炎情况。该方法的一些亮点包括：

• 共有21种模型、五个数据划分集和四种误差测量方法，以提高马来西亚每日新冠肺炎病例的预测准确率。

• 所选的最佳模型在均方根误差（RMSE）、平均绝对误差（MAE）、平均绝对百分比误差（MAPE）和平均绝对尺度误差（MASE）方面产生最低的误差测量值。

• 平均8天预测准确率为90.2%。最低和最高预测准确率分别为83.7%和98.7%。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/7aff9dfc425d/gr7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/8a124b44ca90/ga1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/efb1477f066c/gr1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/f520a07e599f/gr2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/9af7eb5aacd5/gr3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/dc2179aecbf3/gr4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/249a70a528ed/gr5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/33d088b4aeae/gr6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/7aff9dfc425d/gr7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/8a124b44ca90/ga1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/efb1477f066c/gr1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/f520a07e599f/gr2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/9af7eb5aacd5/gr3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/dc2179aecbf3/gr4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/249a70a528ed/gr5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/33d088b4aeae/gr6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/139f/11570750/7aff9dfc425d/gr7.jpg

相似文献

1
Repeated time-series cross-validation: A new method to improved COVID-19 forecast accuracy in Malaysia.重复时间序列交叉验证：一种提高马来西亚新冠疫情预测准确性的新方法。
MethodsX. 2024 Oct 30;13:103013. doi: 10.1016/j.mex.2024.103013. eCollection 2024 Dec.
2
Forecasting COVID-19 Case Trends Using SARIMA Models during the Third Wave of COVID-19 in Malaysia.利用 SARIMA 模型预测马来西亚第三波 COVID-19 期间的 COVID-19 病例趋势。
Int J Environ Res Public Health. 2022 Jan 28;19(3):1504. doi: 10.3390/ijerph19031504.
3
Artificial Intelligence based accurately load forecasting system to forecast short and medium-term load demands.基于人工智能的精确负荷预测系统，用于预测短期和中期负荷需求。
Math Biosci Eng. 2020 Dec 4;18(1):400-425. doi: 10.3934/mbe.2021022.
4
A COVID-19 Pandemic Artificial Intelligence-Based System With Deep Learning Forecasting and Automatic Statistical Data Acquisition: Development and Implementation Study.一种基于人工智能的新冠肺炎大流行深度学习预测与自动统计数据采集系统：开发与实施研究
J Med Internet Res. 2021 May 20;23(5):e27806. doi: 10.2196/27806.
5
Analyzing and Forecasting Pediatric Fever Clinic Visits in High Frequency Using Ensemble Time-Series Methods After the COVID-19 Pandemic in Hangzhou, China: Retrospective Study.中国杭州新冠疫情后基于集成时间序列方法的高频儿科发热门诊就诊情况分析与预测：一项回顾性研究
JMIR Med Inform. 2023 Sep 20;11:e45846. doi: 10.2196/45846.
6
Developing forecasting model for future pandemic applications based on COVID-19 data 2020-2022.基于 2020-2022 年 COVID-19 数据开发未来大流行应用预测模型。
PLoS One. 2023 May 12;18(5):e0285407. doi: 10.1371/journal.pone.0285407. eCollection 2023.
7
Predictive accuracy of time series models applied to economic data: the European countries retail trade.应用于经济数据的时间序列模型的预测准确性：欧洲国家的零售贸易。
J Appl Stat. 2023 Jul 25;51(9):1818-1841. doi: 10.1080/02664763.2023.2238249. eCollection 2024.
8
A novel bidirectional LSTM deep learning approach for COVID-19 forecasting.一种用于 COVID-19 预测的新型双向 LSTM 深度学习方法。
Sci Rep. 2023 Oct 20;13(1):17953. doi: 10.1038/s41598-023-44924-8.
9
Predictive performance of multi-model ensemble forecasts of COVID-19 across European nations.多模型集成预测对欧洲各国 COVID-19 疫情的预测性能。
Elife. 2023 Apr 21;12:e81916. doi: 10.7554/eLife.81916.
10
Forecasting COVID-19 in Pakistan.预测巴基斯坦的 COVID-19 疫情。
PLoS One. 2020 Nov 30;15(11):e0242762. doi: 10.1371/journal.pone.0242762. eCollection 2020.

引用本文的文献

1
A hybrid simple exponential smoothing-barnacles mating optimization approach for parameter estimation: Enhancing COVID-19 forecasting in Malaysia.一种用于参数估计的混合简单指数平滑-藤壶交配优化方法：增强马来西亚的新冠疫情预测
MethodsX. 2025 May 1;14:103347. doi: 10.1016/j.mex.2025.103347. eCollection 2025 Jun.

本文引用的文献

1
Cross-validation: what does it estimate and how well does it do it?交叉验证：它估计的是什么，效果如何？
J Am Stat Assoc. 2024;119(546):1434-1445. doi: 10.1080/01621459.2023.2197686. Epub 2023 May 15.
2
Impact of the Choice of Cross-Validation Techniques on the Results of Machine Learning-Based Diagnostic Applications.交叉验证技术的选择对基于机器学习的诊断应用结果的影响。
Healthc Inform Res. 2021 Jul;27(3):189-199. doi: 10.4258/hir.2021.27.3.189. Epub 2021 Jul 31.
3
Sample-size dependence of validation parameters in linear regression models and in QSAR.
线性回归模型和定量构效关系中验证参数的样本量依赖性。
SAR QSAR Environ Res. 2021 Apr;32(4):247-268. doi: 10.1080/1062936X.2021.1890208. Epub 2021 Mar 22.
4
Cross-validation of three Advanced Clinical Solutions performance validity tests: Examining combinations of measures to maximize classification of invalid performance.三种高级临床解决方案性能有效性测试的交叉验证：研究测量方法的组合以最大化无效性能的分类。
Appl Neuropsychol Adult. 2021 Jan-Feb;28(1):24-34. doi: 10.1080/23279095.2019.1585352. Epub 2019 Apr 15.