| Title |
Analysis of COVID-19 Influence Factors and Estimation of COVID-19 Risk Areas Using Spatial Regression Model and Machine Learning - Focusing on The Use of Data on COVID-19 Confirmed Cases in Seoul |
| Authors |
이조은(Lee, Jo-Eun) ; 이경환(Lee, Kyung-Hwan) |
| DOI |
https://doi.org/10.38195/judik.2023.08.24.5.127 |
| Keywords |
코로나19; 감염병 대응 도시계획; 지역 특성; 공간회귀분석; 머신러닝 COVID-19; Infectious Disease-Responsive Urban Plianning; Regional Characteristics; Spatial Regression Analysis; Machine Learning |
| Abstract |
The purpose of this study is to derive areas at risk of COVID-19 through analysis of various regional characteristics affecting the occurrence of COVID-19 in Seoul and to present urban design directions to effectively respond to infectious diseases by categorizing them. As a result of spatial regression analysis, average monthly income, number of living population, number of workers, land use mix, bus stops, subway exits, medical facilities, and multi-use facilities affect COVID-19 infection. In addition, the XGBoost model was used to estimate the risk area for COVID-19, and strategies for each type of spatial environment were presented to effectively respond to infectious diseases by categorizing them into five. This study is meaningful in that it established basic data for spatial planning in response to infectious diseases, empirically analyzed its impact, and presented a regional customized spatial environment strategy by estimating the risk area for infectious diseases using machine learning. |