A comparative study for determining Covid-19 risk levels by unsupervised machine learning methods
作者：
Highlights：
• Environmental variables should be used for restrictions.
• Unsupervised machine learning techniques should be used instead of threshold values.
• Fuzzy approaches are unsuccessful in determining risk groups.
• Gray relational clustering should be applied for healthier results.
• Five or more risk groups should be determined for Covid-19 restrictions.
摘要
•Environmental variables should be used for restrictions.•Unsupervised machine learning techniques should be used instead of threshold values.•Fuzzy approaches are unsuccessful in determining risk groups.•Gray relational clustering should be applied for healthier results.•Five or more risk groups should be determined for Covid-19 restrictions.
论文关键词：Covid-19,Risk levels,Restrictions,Unsupervised machine learning,Clustering,Gray relational clustering
论文评审过程：Received 18 June 2021, Revised 5 August 2021, Accepted 14 November 2021, Available online 19 November 2021, Version of Record 25 November 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.116243
