• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.149-152
• /
• 2021

본 논문은 실시간 코로나-19 전국 확진자 수를 이용하여 데이터를 추출하고 분리하여 시각적으로 표현했다. 추출된 데이터를을 각 지역에 따라 구분하고 전국 지도에 확진자 수를 표시하여 보기 쉽게 나타냈다. 확진자의 경로는 코로나-19 데이터에서 사후 관리를 위해 가장 중요한 데이터이다. 따라서 확진자의 경로는 정부에서 실시간으로 제공되고 있다. 하지만 이러한 데이터는 텍스트 형태로 되어있어 보기에 불편하다. 따라서 본 논문은 확진자 데이터를 분석하고 정리하여 지도에 표시하고자 한다. 이러한 시각화 방법은 확진자의 경로를 쉽게 파악 할 수 있고 감염 경로를 미리 예방 할 수 있게 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.697-700
• /
• 2022

Recently, as of March 18, 2022, Corona-19 (COVID-19) has 8,250,000 confirmed persons and 11,481 deaths, and has been increasing since the outbreak in 2020. By limiting the number of people and time, we are showing how our daily life changes depending on the number of confirmed coronas. Therefore, in this study, we implemented an algorithm that predicts the number of confirmed people the next day to help minimize damage to the limits of daily life. This algorithm is an algorithm that predicts the number of confirmed persons on the next day using the number of confirmed persons for 3 days. It is predicted by adding the RNN and Dense layers using the Sequential model, and the number of people is subdivided by region. In order to predict the limit, we matched the personnel limit based on the number of fixed persons per day based on Seoul.

• Knowledge Management Research
• /
• v.22 no.2
• /
• pp.227-246
• /
• 2021

In the context of the global pandemic caused by COVID-19, emergency alert text messages can violate the privacy of confirmed corona positive cases. This study used conjoint analysis to identify the essential information factors and the privacy invasion information factors of local government initiated safety notices. As a result of this study, we found eight essential information factors, including all routes of the confirmed case and ten privacy invasion factors of safety notices. In addition, we found that there is a similarity between the combinations of information perceived to be the most essential and perceived as the most significant privacy invasion; both combinations include the confirmed case's personal and route information. This study ultimately tried to suggest a way to lower the concern about privacy invasion of the confirmed cases without damaging the emergency alert text messages' essential information. We expect that this study will provide researchers and policymakers interested in disaster communication with valuable theoretical and practical implications.

• Journal of agricultural medicine and community health
• /
• v.45 no.4
• /
• pp.235-244
• /
• 2020

Objectives: Gyeongsangbuk-do has entered a super-aged society with 20.7% of the population aged 65 and older. As of April 30, 2020, the death rate of COVID-19(3.8 people) in Gyeongsangbuk-do is higher than the national mortality rate (2.3 people), and the fatality rate of COVID-19 by age accounts for more than half of the total of 58.6%, so it is time to propose to prevent infectious diseases in the event of additional infectious disease disasters COVID-19. Methods: We collected daily data on the number of confirmed cases and deaths due to COVID-19 from 19 February to 30 April 2020. The data collected was evaluated using the SPSS 21.0 statistical package. Results: As a result of comparing the incidence and death-related factors of confirmed patients in Gyeongsangbuk-do, there were significant differences in age group (p<0.001), underlying disease (p<0.001), and residence type (p<0.033). Conclusion: Factors affecting the mortality rate of confirmed patients in Gyeongsangbuk-do have been combined with individual level factors(age, gender, underlying disease), which means individual characteristics that have existed since before the disease, and regional level factors(Type of Residence), which are external factors that enable the use of medical resources. Therefore, each local government is required to establish preventive measures considering individual and regional level factors.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.375-388
• /
• 2021

This paper aims to help prevent the spread of COVID-19 by analyzing confirmed cases of COVID-19 in Daejeon. A high volume of visitors, downtown areas, and psychological fatigue with prolonged social distancing were considered as risk factors associated with the spread of COVID-19. We considered the weekly confirmed cases in each administrative district as a response variable. Explanatory variables were the number of passengers getting off at a bus station in each administrative district and the elapsed time since the Korean government had imposed distancing in daily life. We employed a mixed-effects zero-inflated Poisson regression model because the number of cases was repeatedly measured with excess zero-count data. We conducted k-means clustering to identify three groups of administrative districts having different characteristics in terms of the number of bars, the population size, and the distance to the closest college. Considering that the number of confirmed cases might vary depending on districts' characteristics, the clustering information was incorporated as a categorical explanatory variable. We found that Covid-19 was more prevalent as population size increased and a district is downtown. As the number of passengers getting off at a downtown district increased, the confirmed cases significantly increased.

• Journal of Digital Convergence
• /
• v.18 no.8
• /
• pp.179-184
• /
• 2020

This study aims to investigate the effect that local government's information release range on Covid-19 patients' contact trace on consumer sentiment in the region. One hundred twenty-eight residents of Gangnam-gu and Seocho-gu participated in the study. The results showed that when ambiguity of information increased perceived anxiety on Covid-19 patients' contact trace, which in turn led lower intention to visit the commercial district near the Covid-19 patients' contact trace. Based on the findings, several suggestions was proposed for future research, including longitudinal studies covering even the "long-term" changes in consumer sentiment, the effect of implicit anxiety, and the behavioral difference between residence and non-residence.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2022.10a
• /
• pp.143-144
• /
• 2022

본 연구에서는 엄격성 지수(Strigency Index)분석에 따른 OECD 가입국들의 코로나19 대응 정책 엄격성의 효과성을 분석하였다. 코로나바이러스감염증-19(이하, 코로나19)발생 이후 전 세계 대다수 국가들은 점진적 일상회복 단계로 접어들어 'with corona' 시대로 가고 있다. 코로나19의 완전 방역을 이루며 이전과 같은 일상으로 돌아가고 있지만, 또다시 대규모 감염병이 발생할 수 있다는 가능성을 가지고 있다. 그리하여 본 연구에서는 옥스퍼드 코로나바이러스 정부대응추적 프로젝트(OxCGRT)에서 제시된 21개 지표 중 OurWorldinData서 엄격성 지수 분석에 활용되는 9개 지표를 분석하여 정책의 엄격성을 분석하여 추후 발생하는 대규모 감염병에 효과적으로 대응하기 위한 기초 자료가 되고자 한다. 엄격성 지수 분석 결과, 9개 지표 중 6개 지표에서 정책의 도입한 시점부터 확진자가 감소하는 추세를 보이는 유사한 변화를 찾을 수 있었다. 하지만, 엄격성 지수 분석을 통해 국가 대응의 적절성·효과성을 입증하기에는 판단 기준이 0~4점 사이의 임의의 기준으로 분류되고 있었으며, 변수설정 또한 제시되어 있지 않아 대응 정책의 엄격성을 평가하는 기준으로 활용하기에는 한계점이 있어 보인다. 본 연구에서 엄격성 지수 분석을 통한 감염병 대응 정책의 효과성을 찾고자 하였다. 지수와 확진자 추세 간 유사한 변화는 찾았지만, 엄격성 지수의 한계점이 존재하는 연구이다. 그러나 본 연구의 결과를 통해 추후 확진자 증감 대비 엄격성 지수 분석을 통한 상관관계 분석, 지표별 평균치와 확진자 추세 분석을 통한 공통적인 효과성 분석 등 다른 연구의 기초 자료가 될 수 있을 것이라 판단된다.

• Journal of Convergence for Information Technology
• /
• v.11 no.10
• /
• pp.138-143
• /
• 2021

As of this moment, we are tracing people who are closed contact with Covid-19 patients and trying to block the spread of Covid-19 through diagnostic tests. However, the incubation period of the confirmed case is two weeks, and it takes a lot of human resources, time, and money to trace the routes of the confirmed case. In particular, as the number of confirmed cases have been increasing, the cost for finding closed contacts and blocking them in advance exponentially have almost reached the limitation of the budget. In finding closed contacts, all citizens must record an electronic access list every time they visit an amenities such as a store or a restaurant. This is likely the invasion of the privacy of personal location information. In this study, we designed a system that keeps one's location in real time, it will download the movement information of the confirmed case which is collected by KDCA, and it will notify the user when there is an overlap. Moreover, then guide for diagnostic test in advance will be used. The proposed method can solve the difficulty of recording in an electronic access list when visiting a store, and it can block infringement of privacy without providing personal information from KDCA.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.68-68
• /
• 2022

코로나바이러스는(COVID-19)는 2019년 12일 중국 후베이성 우한시에서 시작된 코로나바이러스감염증으로 2020년 1월부터 전 세계로 퍼져, 일부 국가 및 지역을 제외한 대부분의 나라와 모든 대륙으로 확산되었다. 이에 WHO는 범 유행전염병(Pandemic)을 선언하였다. 2022년 3월 18일 현재 국내 누적 확진환자 8,657,609명과 11,782명의 사망자를 일으켰고 전 세계적으로도 많은 사상자를 내고 있는 실정이고 사회 및 경제적인 피해로도 계속 확대되고 있다. 많은 감염자와 사망자의수에 대한 예측은 코로나바이러스의 전염병을 예방하고 즉각적 조치를 취할 수 있는데 도움이 될 수 있다. 본 연구에서는 문화적 인자를 제외한 국내에서 연구 사례가 많지 않은 기상 요인을 인자로 포함하여 머신러닝 모델을 통해 확진자를 예측하였다. 그리고 여러 가지 모델을 성능 평가 기법인 Root Mean Square Error(RMSE) 및 Mean Absolute Percentage Error(MAPE)를 통해 성능을 평가하고 비교하여 정확도 높은 모델을 제시하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.513-514
• /
• 2021

본 논문에서는 코로나-19에 대한 국내외 코로나 확진자 정보에 대한 Infographic 제공 방법 개발을 제안한다. 코로나-19에 대한 국내외 코로나 정보는 행정안전부에서 운영하는 공공 데이터 포털의 open API를 사용함으로써 신뢰성 있는 정보를 바탕으로 일반적으로 Text 형식으로 제공되는 코로나-19 정보를 다양한 Infographic 방법으로 제시하여 사용자에게 보다 효과적으로 정보를 제공할 수 있도록 개발하였다.