Clustering County-wise COVID-19 Dynamics in North Carolina, USA

• 발행기관: 한국자료분석학회
• 저자명: Seong-Tae Kim Man Sik Park
• 간행물 정보: 『Journal of The Korean Data Analysis Society (JKDAS)』Vol.23 No.6, 2535~2546쪽, 전체 12쪽
• 주제분류: 자연과학 > 통계학
• 파일형태: PDF
• 발행일자: 2021.12.31

영문 초록

The COVID-19 pandemic has caused unprecedented impacts along with an enormous number of confirmed cases and deaths in the United States. This study aims to identify hidden clusters among counties in North Carolina using the COVID-19 data. Since individual states implement their own policies to cope with the COVID-19 pandemic, our study is limited to a single state, North Carolina. We incorporated two clustering techniques, dynamic time warping and deep learning autoeconder. Our study used the North Carolina county-wise COVID-19 data from GitHub COVID-19 Data Set, which is the data repository for the COVID-19 Visual Dashboard of the Johns Hopkins University Center for Systems Science and Engineering. From this repository, we selected the daily confirmed cases and deaths of COVID-19 from March 3, 2020 to September 19, 2020. These clustering techniques identified similar hierarchical clusters separating the three metropolitan areas from the remaining regions for both COVID-19 contraction and fatality data, which are significantly correlated with demographic variables such as population size and proportion of elderly people. Our findings suggest the importance of the population density and connectivity for the COVID-19 outbreak.

목차

1. Introduction

2. Methodology

3. Data Description

4. Results

5. Discussion and Conclusion

키워드

COVID-19 clustering dynamic time warping deep learning autoencoder