검색어 빈도 데이터를 반영한코로나 19 확진자수 예측 딥러닝 모델

정성욱 한국정보처리학회 2023 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.12 No.9

코로나 19 유행은 인류 생활 방식과 패턴에 큰 영향을 주었다. 코로나 19는 침 방울(비말)은 물론 공기를 통해서도 감염되기 때문에 가능한대면 접촉을 피하고 많은 사람이 가까이 모이는 장소는 피할 것을 권고하고 있다. 코로나 19 환자와 접촉했거나 코로나 19 환자가 발생한 장소에있었던 사람이 코로나 19에 감염되었을 것을 염려한다면 구글에서 코로나 19 증상을 찾아볼 것이라고 충분히 예상해 볼 수 있다. 본 연구에서는과거 독감 감시와 관리에 중요 역할을 했었던 구글 트렌드(Google Trends)를 다시 소환하고 코로나 19 확진자수 데이터와 결합하여 미래의 코로나19 확진자수를 예측할 수 있을지 딥러닝 모델(DNN & LSTM)을 사용한 탐색적 데이터 분석을 실시하였다. 특히 이 연구에 사용된 검색어 빈도데이터는 공개적으로 사용할 수 있으며 사생활 침해의 우려도 없다. 심층 신경망 모델(DNN model)이 적용되었을 때 한국에서 가장 많은 인구가사는 서울(960만 명)과 두 번째로 인구가 많은 부산(340만 명)에서는 검색어 빈도 데이터를 포함하여 예측했을 때 더 낮은 오류율을 기록했다. 이와 같은 분석 결과는 검색어 빈도 데이터가 일정 규모 이상의 인구수를 가진 도시에서 중요한 역할을 할 수 있다는 것을 보여주는 것이다. 우리는이와 같은 예측이 더 강력한 예방 조치의 실행이나 해제 같은 정책을 결정하는데 근거 자료로 충분히 사용될 수 있을 것으로 믿는다. The COVID-19 outbreak has significantly impacted human lifestyles and patterns. It was recommended to avoid face-to-face contactand over-crowded indoor places as much as possible as COVID-19 spreads through air, as well as through droplets or aerosols. Therefore,if a person who has contacted a COVID-19 patient or was at the place where the COVID-19 patient occurred is concerned that he/shemay have been infected with COVID-19, it can be fully expected that he/she will search for COVID-19 symptoms on Google. In thisstudy, an exploratory data analysis using deep learning models(DNN & LSTM) was conducted to see if we could predict the number ofconfirmed COVID-19 cases by summoning Google Trends, which played a major role in surveillance and management of influenza, againand combining it with data on the number of confirmed COVID-19 cases. In particular, search term frequency data used in this studyare available publicly and do not invade privacy. When the deep neural network model was applied, Seoul (9.6 million) with the largestpopulation in South Korea and Busan (3.4 million) with the second largest population recorded lower error rates when forecasting includingsearch term frequency data. These analysis results demonstrate that search term frequency data plays an important role in cities witha population above a certain size. We also hope that these predictions can be used as evidentiary materials to decide policies, suchas the deregulation or implementation of stronger preventive measures.

Steel D&I Can 몸체성형을 위한 FEM 해석 ( Finite Element Analysis for the Body-making Process of Steel D&I Can )

정성욱,정창규,남재복,진영술,한경섭 대한기계학회 2001 대한기계학회 춘추학술대회 Vol.2 No.1

NaBH4를 이용한 수소발생반응의 촉매에 관한 연구

정성욱,조은애,오인환,홍성안,김성현,서용교 한국수소및신에너지학회 2003 한국수소 및 신에너지학회논문집 Vol.14 No.2

Steel D&I Can의 Doming 및 Necking 공정의 FEM 해석 ( FE Analysis on Doming & Necking Process of Steel D&I Can )

정성욱,남재복,유치상,진영술,한경섭 대한기계학회 2000 대한기계학회 춘추학술대회 Vol.- No.-

교류형 전기유전유체 복합적층보의 진동특성에 관한 연구 ( A Study on Vibration Characteristics of AC ER Fluid Laminated Composite Beam )

정성욱,윤자걸,박현철,황운봉,한경섭 대한기계학회 1995 대한기계학회 춘추학술대회 Vol.- No.-

고등학교 생물 2 교과서에서의 용어 표기 형태에 대한 연구

정성욱,신영준 韓國生物敎育學會 2002 생물교육 Vol.30 No.3

This study was conducted focusing on terminology declaration structures in high school biology Ⅱ textbooks. For this research, four kinds' indexes which passed the Ministry of Education's inspections on June, eleventh of 1996 among eleven kinds' Biology Ⅱ textbooks of the sixth education course were analyzed. Mainly terminology declaration structures and their characteristics were researched. All languages are classified as words written in Chinese characters, words of foreign origin, Korean, and symbolic expressions standards. If a term has two or more standards, it is classified as mixed structure. Results on the total of 1,546 categories, the words written in Chinese characters are 1,116 categories which take 72.2% of the entire languages, the words of foreign origin are 137 categories which take 11.2%, Korean is 38 categories which take 2.5%, the symbolic expressions are 19 categories which take 1.2%, and the mixed structures are 200 categories which take 12.9%. The words written in Chinese characters are the most widely used in no matter of Biology Ⅱ textbook's chapters and learning fields. The words of foreign origin were frequently used in unit chosen the term such as enzymes, hormones, and chemical combinations. Korean is frequently used in ecology related documents for animal/plant's names rather than academic terms. The symbolic expressions are categories other than the words written in Chinese characters, the words of foreign origin and Korean, and they are classified with 18 categories. The mixed structures seems to be showing high frequency ranking next to the words written Chinese characters. The reason behind this is complication of terms while converting the words of foreign origin into the words written in Chinese characters and Korean, and the words written in Chinese characters into Korean.

해외 박물관 수장고의 환경계획에 관한 조사연구 ( A Study on the Environment Planning of Overseas Museum Storage )

정성욱,임채진 대한건축학회 2002 대한건축학회논문집 Vol.18 No.2

시뮬레이션 기법을 이용한 셀프 서비스 시스템 연구

정성욱,양홍석,김수욱 한국경영과학회 2010 한국경영과학회 학술대회논문집 Vol.2010 No.10

In recent years, the service delivery system employing a self-service way is rapidly increasing. Particularly, transferring the entire service delivery system to a self service system, several service providers are exploiting various positive effects. In contrast, a few providers defer the decision of utter transfer to a self service system until the credible forecast to the effects which the new system will bring about is gained. Based on the current situation, this research attempts to predict the utilization and benefits which the self service system causes in a self-gas station. First, under the assumption that learning effect and customer-helper exist, this research figures out how much time would be spent on self service-providing. Also, due to the theory of price elasticity and qualitative effects, the change in a customer arrival rate is estimated. Subsequently, utilizing a simulation method, the change in three performance measurements such as average number of customer, average waiting time, and utilization are observed according to the alterations in price difference and helper-operating time. In this research, the optimal operation strategy for price differentiation and helper-operating time is proposed in accordance with the level of modification term and learning rate. Although this research confines the scope of the study to the self gas station model, the result from this research can be applied to any type of self-service system.

연결망 분석도구를 이용한 크리스토퍼 알렉산더 패턴언어 활용 가능성에 관한 연구

정성욱,김문덕 한국실내디자인학회 2016 한국실내디자인학회논문집 Vol.25 No.3

연결망 분석도구를 이용한 크리스토퍼 알렉산더의 패턴언어 활용 가능성 확대를 위해 진행한 본 연구의 진행과 결과를 정리하면 다음과 같다. 패턴언어의 복잡한 관계구조를 이해하기 위해 연결망 분석도구를 이용해 전체 패턴언어를 분석하였다. 이를 통해 도시, 건축, 시공의 ‘보다 큰’ 패턴과 ‘보다 작은’ 패턴이 연결되는 관계구조의 특징을 정리하였고, 6개의 모듈을 통해서 새로운 패턴을 선택하는 방법을 제시하였다. 또한 패턴언어 사용도구로써의 연결망 도구의 가능성을 시험하기 위해 알렉산더가 제시한 4개의 사례를 연결망 배치도로 제작하였다. 이를 통해 기존 패턴언어 사용방법의 문제점을 해결하였으며, 패턴언어의 완성도를 높일 수 있는 가능성을 제시하였다. 또한 새롭게 추가되는 패턴의 관계연결 문제점을 밝히며 이후 연구과제의 방향을 제시하였다. This study is aimed to increase the possibility of using the Christopher Alexander’s pattern language. The methodology of this study is (i) to analyze the pattern language by using the network analysis tool in order to understand the complicate network structure of the pattern language, and (ii) to apply the Alexander’s method of using the pattern language by using the network analysis tool (Gephi) and to examine the feasibility of the network analysis tool as a tool for using the pattern language. Firstly, as a result of analysing the pattern language, (i) the pattern language classified by pattern number is distinguished by the patterns of towns, buildings and construction, among which the pattern of buildings plays a key function in the networks; (ii) the buildings functions a medium connecting between the towns and the construction; and (iii) the pattern language is divided into 6 sub-modules, through which the user can select a pattern. Secondly, the result of using the network analysis tool as a tool for using the pattern language (i) suggests the new method of using the pattern language by using the network analysis tool (Gephi); (ii) makes it possible to easily figure out the characteristics of the links between the patterns; and (iii) increases the completeness of the pattern language by making it easy to find out the sub-patterns in selecting a pattern.

박물관 보존과학계 공간의 계획 데이터 구축 모형에 관한 연구

정성욱 한국문화공간건축학회 2006 한국문화공간건축학회논문집 Vol.- No.16

Generally, museum collections may be entered to a storage after curators interpret the materials and conservators do treatment for conservation. Even in the case of museum collections the curators previously investigated or researched, has to be provided with suitable environments for conservation analysis and treatment prior to exhibition so as to prevent or delay deterioration. Considering circle mechanism of museum collections, extracted required space by flexible change and prepared the systematical basis as a guidance for each space planning, considering basic planning conditions presented until now. Based on studies connecting conservative position to architectural planning under perception that these architectural planning is the most important for the function and purpose of museums. So, the primary objective of this study to propose a model for the development and implementation of design index of conservation space in a museum, which enables contractual participants to easily access and use the data of the judicial precedents related to plan a museum