• Korean Journal of Radiology
• /
• 제23권10호
• /
• pp.1009-1018
• /
• 2022

Objective: This study aimed to investigate the feasibility of using artificial intelligence (AI) to identify normal chest radiography (CXR) from the worklist of radiologists in a health-screening environment. Materials and Methods: This retrospective simulation study was conducted using the CXRs of 5887 adults (mean age ± standard deviation, 55.4 ± 11.8 years; male, 4329) from three health screening centers in South Korea using a commercial AI (Lunit INSIGHT CXR3, version 3.5.8.8). Three board-certified thoracic radiologists reviewed CXR images for referable thoracic abnormalities and grouped the images into those with visible referable abnormalities (identified as abnormal by at least one reader) and those with clearly visible referable abnormalities (identified as abnormal by at least two readers). With AI-based simulated exclusion of normal CXR images, the percentages of normal images sorted and abnormal images erroneously removed were analyzed. Additionally, in a random subsample of 480 patients, the ability to identify visible referable abnormalities was compared among AI-unassisted reading (i.e., all images read by human readers without AI), AI-assisted reading (i.e., all images read by human readers with AI assistance as concurrent readers), and reading with AI triage (i.e., human reading of only those rendered abnormal by AI). Results: Of 5887 CXR images, 405 (6.9%) and 227 (3.9%) contained visible and clearly visible abnormalities, respectively. With AI-based triage, 42.9% (2354/5482) of normal CXR images were removed at the cost of erroneous removal of 3.5% (14/405) and 1.8% (4/227) of CXR images with visible and clearly visible abnormalities, respectively. In the diagnostic performance study, AI triage removed 41.6% (188/452) of normal images from the worklist without missing visible abnormalities and increased the specificity for some readers without decreasing sensitivity. Conclusion: This study suggests the feasibility of sorting and removing normal CXRs using AI with a tailored cut-off to increase efficiency and reduce the workload of radiologists.

• 한국전자거래학회지
• /
• 제21권2호
• /
• pp.121-133
• /
• 2016

모든 산업은 ICT 기술의 적용 및 산업기술의 급속한 발전에 따라 신기술 개발 및 확보를 위한 연구 투자가 확대되고 있으며, 이러한 신기술을 보호하려는 노력도 동시에 강화되고 있다. 하지만 이러한 기술보호에 대한 노력은 단순히 기업에서 이루어져야 하는 것이 아니라 국가 경쟁력 차원에서 여러 정부기관이 관심을 가지고 다양한 산업보안 활동을 수행해야 한다. 본 논문에서는 산업자산 보호 및 기술유출 방지를 위해 산업보안 활동을 수행하고 있는 산업보안 유관기관에 대해 조사해보고 각 기관의 산업보안 업무에 대해서 알아보고자 한다. 또한 본 논문에서는 산업보안 유관기관 조사 및 비교를 통해 현재 정부기관의 산업보안 운영에 대한 문제점을 논의해보고 산업보안 발전 및 효율적 업무를 위한 정부 내 산업보안 담당부서의 필요성에 대해 제고해보려고 한다.

• 한국전자통신학회논문지
• /
• 제14권2호
• /
• pp.303-308
• /
• 2019

스프링 프레임워크는 우리나라 공공기관의 웹서비스 개발도구의 표준이라 할 만큼 전자정부 프레임워크의 기반 기술로 많이 사용되고 있다. 그러나 최근 스프링 프레임워크를 이용한 애플리케이션에서 원격코드 실행 취약점(CVE-2018-1270)이 발견되었다. 본 논문은 스프링 프레임워크를 서버를 대상으로 발생한 취약점의 위험성을 해킹 시나리오 POC(Proof Of Concept)를 이용한 취약점 실험 분석 방법을 제안한다. 종국적 대응방안으로 버전 4.3.16와 버전 5.0.5 이상으로 패치를 제안한다. 아울러 제안한 해킹시나리오 취약점 실험분석이 보안 프로그램의 성능향상 및 새로운 인증체계의 구축을 위한 자료로 활용될 것으로 기대한다.

• 한국전자거래학회지
• /
• 제26권2호
• /
• pp.45-59
• /
• 2021

4차 산업혁명의 핵심 동인으로서 Software(이하 SW)의 중요성이 더욱 커짐에 따라, 정부는 국가 경쟁력 강화를 위해 SW R&D 투자를 늘리고 SW 관련 정책을 지속적으로 수립하고 있다. 하지만 SW 연구개발에 대한 정부의 지속적인 투자에 비해, SW 연구개발 투자성과에 대한 체계적 분석은 부족한 실정이다. 본 연구에서는 Data Envelopment Analysis(DEA) 기법을 이용하여 SW 국가연구개발 사업의 분야별 효율성을 분석하였다. 2008년~2018년까지 정보통신산업진흥원(NIPA)에서 수행된 1,463개 과제정보를 토대로 효율성을 정태적/동태적 관점에서 측정하였다. 정태적 관점의 규모효율성 측정을 통해 비효율성 원인을 규모와 기술문제로 분석하였다. DEA/Window 모형을 이용한 동태적 효율성 분석 결과를 제시하고 효율성-안정성 매트릭스를 이용해 분야별 대응 모델을 제시하였다. 본 연구는 SW 국가연구 개발사업 전체를 대상으로 효율성 분석을 수행했다는 점에 의의가 있으며, 정태적/동태적 효율성 분석결과는 향후 SW 국가연구개발사업 기획 시 기초자료로 활용이 가능할 것으로 기대된다.

• 품질경영학회지
• /
• 제30권3호
• /
• pp.203-236
• /
• 2002

Environmental Performance Evaluation(EPE) is a key process of Corporate Environmental Management. This paper presents the results of an empirical survey on the status of current practices in EPE of Korean firms. Based on a corporate environmental management(CEM) model, which is initially developed by Hibbitt and Kamp-Roelands(2001) and modified in terms of EPE, the survey is peformed on the population of Korean firms, which are composed of firms certified as "environmentally friendly" by Korean government and/or certified under Is014001, and compares its results with those of Europe's. Although the relatively low response rate and some methodological limitations makes us be cautious about the interpretation, the results shows many interesting aspects of the current states of Korean firms' EPE practices. That is, the levels of EPE implementation in the environmentally-leading companies of Korea are almost the same as that of European companies, I. e., in the-final-part-of-developing-stage (3rd stage) level of the CEM model. It is also shown that as In Europe's case, Korean firms are also moving slower in external relationships than in internal control and management, are more developed in the parameters like environmental policy, Internal control, Information system, which are requirements of certification under Is014001, than in parameters like life cycle analysis and full cost accounting, which requires more research efforts, etc.orts, etc.

• 유통과학연구
• /
• 제21권2호
• /
• pp.77-89
• /
• 2023

Purpose: At the end of the pandemic, many digital startups had negative performances. For that, this study aims to analyze the mediating role of entrepreneurial competence and digital entrepreneur career maturity. Seven hypotheses were proposed, namely the effect of entrepreneurship orientation, digital entrepreneurship experience, and digital entrepreneur career maturity on digital entrepreneurial competence, the effect of digital entrepreneurial experience on digital entrepreneurial career maturity, the influence of entrepreneurial orientation, entrepreneurial competence, and digital entrepreneur career maturity on business performance. Research design, data and methodology: The population is digital entrepreneurs in Central Java, Indonesia with a business duration of more than 4 years. The number of samples as many as 184 people were carried out by questionnaire distribution through face-to-face, email, and Google forms. Partial Least Square Structural Equation Modeling was used to test the path coefficient statistics. Results: The results showed that all the hypotheses proposed were accepted. Digital entrepreneurial competencies and digital entrepreneurial career maturity are also proven to have a mediating role. Conclusions: The findings of this study can contribute to the development of digital entrepreneurship research. Practically, the government's role is needed to facilitate the three main elements of digital business: e-commerce, payment methods, and distribution channels.

• 융합경영연구
• /
• 제3권3호
• /
• pp.7-23
• /
• 2015

Women are more disadvantaged than men in many fronts and this confines them to informal sector livelihood activities. Any attempt to improve women's economic status will require information on the organization, cost and returns to investment in the livelihood activities in which they predominate. This is the issue for this study which compared yield performance in artisanal fishing and fresh fish marketing. Primary data collected through multi-stage sampling method were analyzed using inferential statistics, budgeting and regression models. Empirical findings revealed that about 75.0% of fisher folks either had no formal education or acquired only primary school education while 50.0% of marketers had secondary school education. The budgeting model revealed fisher-folks' and marketers' annual net profit to be N2,882,626.00 and N640,227.00, respectively. Profit from fishing was significantly higher than that of fish marketing. At 53.2% for fishing and 40.3% for marketing, returns to investment was better in fishing. Regression model results showed the significant factors influencing returns to each livelihood strategy to include fishing ground, distance covered and years of experience. The major constraint faced by operators of both livelihoods groups was insufficient credit. Despite this, the livelihood strategies were shown to be profitable ventures which contributed to households' consumption expenditure. Organizing women informal sector operators into groups to enhance access to government support and formal credit are recommended for improving livelihood strategy performance.

• 기술혁신연구
• /
• 제3권1호
• /
• pp.1-34
• /
• 1995

Since 1982, the government of Korea has actively promoted vertical cooperative R&D programs between government-sponsored research institutes (GRIs) and private firms. A number of firms participated in the programs because cooperative R&D could lower the risk and could contribute to rapid commercialization of many technologies. This paper examines the effectiveness of vertical cooperative R&D projects by the modes of cooperation between GRIs and industrial firms, and analyzes the performance of participating firms' technology sourcing strategies for commercial utilization of cooperative R&D results at the project performed from 1982 to 1989 under the Government-Industry Cooperative R&D Program sponsored by the Ministry of Science and Technology(MOST) in Korea. The cooperative R&D projects are classified into 4 groups by two criteria, i.e., the level of participation of firms, and the breadth of cooperation. The findings suggest that firms should actively participate in cooperative R&D projects. In addition, in order to enhance commercial success, cooperation between GRIs and industrial firms should not be limited to R&D stage only. The breadth of cooperation should be extended to commercialization stage. Small- and medium-sized firms participating in vertical cooperative R&D projects in Korea usually lack internal technological capabilities that are needed to commercialize the results of cooperative R&D. Three different technology sourcing strategies - exclusive cooperative R&D strategy, in-house development augmented cooperative R&D strategy, and licensing-in supplemented cooperative R&D strategy - are empirically derived through cluster analysis of the relative usage rates cooperative R&D and of other supplementary technology acquisition methods. The findings suggest that the firms participating in vertical cooperative R&D projects should try to utilize other supplementary technology acquisition methods in order to achieve commercial utilization of the vertical cooperative R&D results.

• Advances in Computational Design
• /
• 제7권2호
• /
• pp.113-128
• /
• 2022

Water consumption is strongly affected by numerous factors, such as population, climatic, geographic, and socio-economic factors. Therefore, the implementation of a reliable predictive model of water consumption pattern is challenging task. This study investigates the performance of predictive models based on multi-layer perceptron (MLP), multiple linear regression (MLR), and support vector regression (SVR). To understand the significant factors affecting water consumption, the stepwise regression (SW) procedure is used in MLR to obtain suitable variables. Then, this study also implements three predictive models based on these significant variables (e.g., SWMLR, SWMLP, and SWSVR). Annual data of water consumption in Thailand during 2006 - 2015 were compiled and categorized by provinces and distributors. By comparing the predictive performance of models with all variables, the results demonstrate that the MLP models outperformed the MLR and SVR models. As compared to the models with selected variables, the predictive capability of SWMLP was superior to SWMLR and SWSVR. Therefore, the SWMLP still provided satisfactory results with the minimum number of explanatory variables which in turn reduced the computation time and other resources required while performing the predictive task. It can be concluded that the MLP exhibited the best result and can be utilized as a reliable water demand predictive model for both of all variables and selected variables cases. These findings support important implications and serve as a feasible water consumption predictive model and can be used for water resources management to produce sufficient tap water to meet the demand in each province of Thailand.

• 한국컴퓨터산업학회논문지
• /
• 제5권3호
• /
• pp.345-354
• /
• 2004

현재 인터넷은 HTTP 프로토콜을 중심으로 구성되어 있다. 전자상거래, 전자정부, 인터넷 멀티미디어, 흠 네트워킹 등 현재 인터넷으로 가능한 서비스는 점점 증가하고 있지만, 비교적 단순한 메시지의 전송에 기반 해 설계된 HTTP가 현재의 이러한 복잡한 서비스와는 적합하지 않는 경우도 있다. 즉, 점점 더 다양해지는 서비스로 인해, 서버 쪽에서는 클라이언트당 점점 더 많은 양의 데이터를 전송하게 되는 것이다. 이러한 웹 서버 측의 메시지 전송 부담과 전송 시간, 대역폭의 절감을 위해서, HTTP 프로토콜의 압축전송헤더를 이용한 실시간 압축 전송 아키텍쳐를 개발하였다. 이를 이용하여, 정적 페이지를 실시간으로 압축/전송함으로써, 웹 서버 측의 대역폭을 절감하였고, 전송속도를 증가시켰다. 또한, 상대적으로 CPU 집중적인 압축연산을 커널 영역에서 수행하여, 압축연산으로 인한 서버 측의 CPU 자원사용을 최소화하였다.