• 실천공학교육논문지
• /
• 제15권1호
• /
• pp.31-38
• /
• 2023

본 논문에서는 비전공자들을 위한 기초 머신러닝 모델 학습 및 활용교육 커리큘럼을 제안하고, Orange 머신러닝 모델 학습 및 분석 도구를 활용한 교육 방법을 제안하였다. Orange는 오픈 소스기반 머신러닝 및 데이터 시각화 도구로서, 복잡한 프로그래밍 없이 시각적인 위젯을 사용하여, 데이터를 학습시켜 머신러닝 모델을 만들 수 있다. Orange는 비전공자 학부생부터 전문가 그룹까지 다양하게 사용되는 플랫폼이다. 본 논문에서는 한 학기 분량의 기초 머신러닝 모델 학습 및 활용교육 커리큘럼과 주별 실습 내용을 제시하였다. 그리고, 머신러닝 모델 학습 및 활용에 대한 교육 내용 실체를 실증하기 위해, Orange 도구를 활용하여, 분류 데이터(Categorical Data) 표본과 수치 데이터(Numerical Data) 표본으로부터 머신러닝 모델을 학습시키고, 모델을 활용하여 모집단의 결과를 예측하는 활용 사례들을 제안하였다. 마지막으로 본 커리큘럼에 대한 교육 만족도를 비전공자 대상으로 조사 및 분석하였다.

• 한국환경복원기술학회지
• /
• 제25권4호
• /
• pp.49-65
• /
• 2022

Since trees in the city are green assets that create a healthy environment for the city, systematic management of trees improves urban ecosystem services. The sporadic urban tree information centered on the site is vast, and it is difficult to manage the data, so efforts to increase efficiency are needed. This paper summarizes tree data inventory based on data constructed by Seoul Green Trust activists and constructs and discloses online database maps using Tableau Software. In order to verify the utilization of the map, we divided into consumer and supplier aspects to collect various opinions and reflect feedback to implement tree database maps for each area and species of Seoul Forest. As a result, the utilization value of tree database in urban parks was presented. The technical significance of this study is to systematically record the process of constructing and implementing a dashboard directly using the Mapbox platform and Tableau Software in the field of landscaping for the first time in Korea. In addition, the implications and supplements of landscape information were derived by collecting user opinions on the results. This can be used as an exploratory basis in the process of developing online-based services such as web and apps by utilizing landscaping tree information in the future. Although the visualization database currently constructed has limitations that ordinary users cannot interact in both directions because it utilizes business intelligence tools in terms of service provision it has affirmed both the database construction and its usability in web public format. In the future it is essential to investigate the assets of the trees in the city park and to build a database as a public asset of the city. The survey participants positively recognized that information is intuitively presented based on the map and responded that it is necessary to provide information on the overall urban assets such as small parks and roadside trees by using open source maps in the future.

• 대한한의학회지
• /
• 제42권1호
• /
• pp.12-25
• /
• 2021

Objectives: The aim of this study was to investigate influencing factors of using Korean medicine services (KMS) using the 2017 Korean Medicine Utilization Survey (KMUS). Methods: Demographic statistics of the survey were summarized and influencing factors of the KMS experience and the intention to visit KMS were analyzed using logistic regression model with complex sample design. Influencing factors were specified based on Andersen's behavioral model of health care utilization and factors associated with individual recognitions of KMS. Additionally, using the ordinary logistic regression model without complex sample design, the survey data were analyzed to compare the results. Results: In the logistic regression analysis, sex, age, health condition, presence of chronic disease, a degree of knowledge about Korean Medicine, and a view about herbal medicine safety were statistically significant both in the KMS experience, and the intention to visit KMS. Marital status was statistically significant in the KMS experience, while family income, a view about the cost of KMS were statistically significant in the intention to visit KMS. Conclusion: Individual recognitions of KMS and enabling components should be considered when establishing KMS policies. In addition, future studies analyzing KMUS need to take into account the complex sample design features of the survey to avoid statistically misleading results.

• 한국콘텐츠학회논문지
• /
• 제17권12호
• /
• pp.1-10
• /
• 2017

오픈 데이터는 전세계적으로 많은 관심을 받고 있다. 우리나라 정부는 데이터 개방에 많은 노력을 기울이고 있다. 그러나, 공공 데이터의 양적 증가에도 불구하고 데이터에 대한 부족함이 여전히 지적되고 있다. 본 논문은 공공 데이터를 의미적으로 연결해 데이터 공유 및 활용을 향상시키기 위한 방법을 제안한다. 첫째, 대한민국 행정구역의 정의와 행정구역 사이의 관계를 의미적으로 표현하기 위한 지식 모델을 제안한다. 행정구역은 국가의 영역을 국가 행정상의 목적에 따라 구분한 단위이다. 행정구역 지식모델은 지방자치법을 기준으로 행정구역체계의 구조, 행정단위별 관계를 정의한다. 둘째, 대한민국 행정구역 데이터에 대한 지식그래프를 소개한다. 공공 데이터를 의미적 수준에서 연결시키는 기준정보로써 행정구역 지식그래프의 특징과 이기종 공공데이터 연계 및 데이터 품질 개선을 위한 방법을 소개한다. 마지막으로 행정기관 데이터의 연계 결과를 통해 행정구역 지식그래프의 응용 방법을 살펴본다. 행정기관 명칭은 기관별로 상이하게 활용하고 있기 때문에 행정구역 그래프를 통한 데이터 식별 및 정제와 더불어 데이터 품질 개선에 효과적인 접근 방안으로 고려할 수 있다.

• Journal of Information Science Theory and Practice
• /
• 제10권spc호
• /
• pp.1-11
• /
• 2022

As data-based research activities and outcomes increase and ontact or non-face-to-face activities become common, the demand for easy utilization of resources, tools, functions, and easily accessible information required for research in the R&D sector has increased accordingly. With the rapid increase in the demand for collaborative research based on online platforms, research support institutions strive to provide venues for research activities that merge various information and functions. ScienceON, an integrated science & technology (S&T) knowledge infrastructure service developed and operated by the Korea Institute of S&T Information (KISTI), supports open collaboration by connecting and merging all the information, functions, and infrastructure required for research activities. This paper describes the online research activity support tool provided by ScienceON and the remarkable results achieved through this activity. Specifically, the excellent creation of the following flow of meta-material research activities in the ontact space is elucidated. First, the papers required for a meta-material analysis are retrieved, virtual simulation is conducted with the experimental data extracted from the papers, and research data are accumulated. ScienceON's tools for supporting ontact research activity will play a role as an important service in the era of digital transformation and open science.

• 한국학교보건학회지
• /
• 제32권3호
• /
• pp.144-151
• /
• 2019

Purpose: The purpose of this study is to examine academic stress, social support and learning management system(LMS) utilization satisfaction of learners attending online graduate schools and understand the factors influencing their academic persistence. Methods: The participants were students of K online graduate school and the data of 143 students, in total, were collected from April to May in 2019. For data analysis, frequency analysis, x² test, t-test, F-test, Pearson's correlation and multiple regression analysis were conducted using SPSS ver. 23. Results: Academic stress, social support, and LMS utilization satisfaction were associated with academic persistence of online graduate students. The multiple regression analysis of the factors influencing academic persistence showed that the model was significant (p<.001) with an explanatory power of 23% and that significant factors influencing it were academic stress (β=-.23, p=.002), LMS utilization satisfaction (β=.31, p<.001) and jobs (β=.23, p=.002). Conclusion: Although the online graduate students' level of academic persistence was high, it is required to develop strategies to alleviate their academic stress and increase LMS utilization rate in order to increase their persistence to academic success. In addition, it is necessary to provide the foundation on which the utilization of major knowledge regarding jobs can be enhanced, reflecting the characteristics of online graduate students. Furthermore, this study is expected to contribute to the extension of professional and advanced education in response to social needs by developing a variety of online high education learning systems beyond time and space.

• 한국치위생학회지
• /
• 제24권1호
• /
• pp.9-16
• /
• 2024

Objectives: The demand for dental care is expected to increase as the population ages. This study aimed to predict the utilization of dental implant care following the expansion of national health insurance benefits for dental implants. Methods: Multiple linear regression analysis was performed on HIRA big data open portal data and DNN-based artificial intelligence models to forecast the utilization of dental care in relation to the national health insurance coverage for dental implants. Results: National health insurance coverage of dental implants was found to be associated with the number of patients using dental implant services and demonstrated a statistical significance. The dental implant services utilization increased with the increased dental implant health insurance benefits for the elderly population, increased mean by region, increased number of dental institutions by region, and increased health insurance coverage rate for dental implants. However, the dental implant services utilization decreased with the increased number of older people living alone and increased size of dental institutions. Conclusions: With the expansion of the national health insurance coverage for dental implants, it is predicted that the utilization of dental implant medical services will increase in the future.

• 유통과학연구
• /
• 제20권2호
• /
• pp.101-108
• /
• 2022

Purpose: In this logistics disturbance period, this study conducts research of distribution and logistics firms in Korea. The purpose of this exploratory research is to analyze global competitive capability influence on business performance. And give managerial implications and contribute to academics. Research design, data, and methodology: This research empirically analyzes the relationship between global competitive capability and business performance. As for business performance this research considered non-financial performance and measured with business performance fulfillment. As for antecedent variables, this research measured three global competitive capability constructs; preparation, utilization, intensive capability. And each construct includes two capability concepts. This study used 2,316 executing direct export distribution and logistics industry firmsfrom KOTRA's GCL data. This research used frequency analysis, reliability analysis, correlation analysis, and step-wise regression analysis by SPSS26. Results: The result shows that all the variables except export infra showed statistically significant. As results show, mid/long strategy & global mind of preparation capability, both communication and marketing of utilization capability and market strategy and product/goods/service of intensive capability give a positive influence on business performance fulfillment. Conclusions: Based on the results, this research provide implication for practical management, contribution to academic, and suggestion for feature research.

• 시큐리티연구
• /
• 제60호
• /
• pp.91-111
• /
• 2019

꾸준히 늘어나고 있는 강력범죄의 예방은 언제나 인류의 중요 화두 중 하나이다. 최근의 대표적인 예방법은 도시에 범죄예방환경설계(CPTED)을 적용해 설계하는 것이다. 이 개념에서 가장 중요한 것이 감시와 접근통제인데, 그 중 일반적으로 많이 사용되는 방법은 기계적 감시에 속하는 것이지만 새로운 흐름에 맞추어 공공데이터를 활용한 다른 관점에서의 클래식 범죄예방 정책 제안이 필요하다. 이에 본 연구에서는 활용하는 공공데이터로 한국의 중심지인 서울시 데이터 포탈에서 제공되는 최근 년도의 자치구별 5대 범죄 발생현황통계를 중심으로 범위를 설정, 가장 개선이 필요한 부분에 범죄예방정책을 제안하도록 한다. 데이터 분석 및 시각화 방법으로는 오픈소스인 Python 분석 프로그램을 사용하였다.

• 한국지리정보학회지
• /
• 제22권4호
• /
• pp.215-228
• /
• 2019

해양관측 정지궤도 위성인 GOCI(Geostationary Ocean Color Imager) 데이터는 대용량 산출물을 효과적으로 저장, 배포하기 위해 HDF5 자료 형식을 사용하고 있다. 해양위성센터에서는 HDF5(Hierarchical Data Format version5) 포맷에 익숙지 않은 일반 사용자를 위해 GDPS(GOCI Data Processing System)를 개발하여 관측자료와 함께 제공하고 있다. 그럼에도 불구하고 위성데이터 특성에 대한 이해와 GDPS의 사용법을 익혀야 하는 점, 그리고 위치정보와 속성정보가 분리되어 있는 HDF5 형식의 자료를 병합하고 가공하는 일은 쉽지 않은 일이다. 따라서 본 연구에서는 오픈소스 R과 rhdf5, data.table, matrixStats 패키지를 이용하여 GDPS를 이용하는 과정 없이도 HDF5 형식의 위성데이터를 손쉽게 활용할 수 있는 알고리즘을 개발하였다.