期刊文献+

基于谱系聚类的全球各国新冠疫情时间序列特征分析 被引量:2

Analysis of Time Series Features of COVID-19 in Various Countries based on Pedigree Clustering
原文传递
导出
摘要 COVID-19暴发以来,世界各国疫情呈现出不同的时序特点,研究不同国家疫情发展模式的特点,揭示其背后的主导因素,可为未来防控策略提供参考。为了揭示不同国家疫情时间序列之间的异同,本文提取了主要疫情国家每日新增病例时间序列的标准差、Hurst指数、治愈率、增长时长、平均增长率、防控效率进行谱系聚类,并从经济、医疗、人文冲突方面对聚类结果进行了成因分析。结果表明,全球疫情发展模式可分为3大类:C型、S型和I型。C型国家时间序列的特点是持续波动上涨,治愈率较低,原因是其人文冲突不利于疫情防控,经济医疗资源经过长时间大量消耗已趋于匮乏,建议在防控中加强宣传疏导,改变观念,统筹分配经济、医疗资源;S型国家时间序列的特点是快速上升后立即下降,并最终保持稳定趋势,总体治愈率较高,其原因是这类国家国内稳定,经济医疗水平较高,以及防控措施及时,建议加强国际合作和科学研究,并为可能到来的二次疫情做好准备;I型国家时间序列特点是缓慢上涨,整体发展趋势不稳定,治愈率较低,原因是其暴发比较晚,程度较小,大部分经济医疗水平以及人文冲突不利于疫情防控,建议汲取较好的防控经验,实施严格的隔离措施,尽量满足疫情期间物资需求,优化治疗方法。 Since the outbreak of COVID-19, countries around the world have shown different time-series characteristics. Studying the characteristics of the development patterns of different countries and revealing the dominant factors behind them can provide references for future prevention and control strategies. In order to reveal the similarities and differences between the epidemic time series in different countries, this article extracts the standard deviation, Hurst index, cure rate, growth time, average growth rate, and prevention and control efficiency of the daily time series of new cases in the main epidemic countries for pedigree clustering. We also analyzes the causes of clustering results from the aspects of economics, medical treatment, and humanistic conflicts. The results show that the global epidemic development model can be divided into three categories: C-type, S-type, and I-type.The time series of C-type countries are characterized by continuous fluctuations and rising, and the cure rate is low.The reason is that humanistic conflicts are not conducive to epidemic prevention and control. Economic and medical resources have become scarce after a long period of large consumption. It is recommended to strengthen publicity and guidance in prevention and control, change concepts, and coordinate the allocation of economic and medical resources. The time series of S-type countries is characterized by a rapid rise and then an immediate decline, and eventually maintains a stable trend. The overall cure rate is relatively high. The reason is that these countries have domestic stability, high economic and medical standards, and timely prevention and control measures. It is recommended to strengthen international cooperation and scientific research, and prepare for the possible second epidemic. The time series of I-shaped countries is characterized by a slow rise, the overall development trend is unstable, and the cure rate is low. The reason is that its outbreak is relatively late and less severe. Most of the economic and medical levels and humanistic conflicts are not conducive to epidemic prevention and control. It is recommended to learn better prevention and control experience, implement strict isolation measures, try to meet the material needs during the epidemic, and optimize treatment methods.
作者 谢聪慧 吴世新 张晨 孙文涛 何海芳 裴韬 罗格平 XIE Conghui;WU Shixin;ZHANG Chen;SUN Wentao;HE Haifang;PEI Tao;LUO Geping(Key Laboratory of Desert and Oasis Ecology,Institute of Ecology and Geography,Xinjiang,Chinese Academy of Sciences,Xinjiang,Xinjiang,Urumqi 830011,China;Key Laboratory of Remote Sensing and GIS Applications,Xinjiang,Xinjiang,Urumqi 830011,China;Key Laboratory of Comprehensive and Highly Efficient Utilization of Salt Lake Resources,Qinghai Institute of Salt Lakes,Chinese Academy of Sciences,Xining 810008,China;Qinghai Provincial Key Laboratory of Geology and Environment of Salt Lakes,Xining 810008,China;State key laboratory of resource and Environmental Information Systems,Chinese Academy of Sciences,Beijing 100101,China;University of Chinese Academy of Sciences,Beijing 100049,China)
出处 《地球信息科学学报》 CSCD 北大核心 2021年第2期236-245,共10页 Journal of Geo-information Science
基金 中国科学院战略性先导科技专项(A类)(XDA23100000) 国家科技基础资源调查专项(2017FY101004) 国家自然科学基金项目(42041001)。
关键词 COVID-19 时间序列 数据挖掘 统计结构特征 谱系聚类 全球公共卫生 防控措施 COVID-19 time series data mining statistical structure characteristics pedigree clustering global public health prevention and control measures
  • 相关文献

参考文献2

二级参考文献48

  • 1Shumway R H, Stoffer D S. Time Series Analysis and Its Applications with R Examples. New York: Springer, 2009.
  • 2Han J W, Kamber M. Data Mining: Concepts and tech- niques. Singapore: Elsevier, 2006.
  • 3Ko~melj K, Batagelj V. Cross-sectional approach for clustering time varying data. Journal of Classification 1990, 7: 99-109.
  • 4Balasubramaniyan R, Hiillermeier E, Weskamp N, et al. Clustering of gene expression data using a local shape-based similarity measure. Bioinformatics 2005, 21 (7): 1069-1077.
  • 5Liao T W. Clustering of time series data: A survey. Pat- tern Recognition 2005, 38(11): 1857-1874.
  • 6Diaz S P, Vilar J A. Comparing several parametric and nonparametric approaches to time series clustering: A simulation study. Journal of Classification, 2010, 27(3): 333-362.
  • 7Keogh E J, Pazzani M J. An enhanced representation of time series which allows fast and accurate classification, Clustering and Relevance Feedback//Procs. of the 4th Conference on Knowledge Discovery in Databases, 1998: 239-241.
  • 8Chen Y G, Nascimento M A, Ooi B C, et al. SpADe: On shape-based pattern detection in streaming time series// Proceedings of the 23rd International Conference on Da- ta Engineering, IEEE, 2007: 786-795.
  • 9Wang X Z, Smith K, Hyndman R. Characteristic-based clustering for time series data. Data Mining and Knowl- edge Discovery, 2006, 13(3): 335-364.
  • 10Rose O. Estimation of the Hurst Parameter of Long-Range Dependent Time Series. Research Report, 1996.

共引文献29

同被引文献24

引证文献2

二级引证文献19

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部