• 대한방사선기술학회지:방사선기술과학
• /
• 제46권6호
• /
• pp.535-542
• /
• 2023

This study aimed to implement a deep learning model that can perform quantitative quality control through ACTS software used for quantitative evaluation of ACR phantom in CT quality control and evaluate its usefulness. By changing the scanning conditions, images of three modules of the ACR phantom's slice thickness (ST), low contrast resolution (LC), and high contrast resolution (HC) were obtained and classified as ACTS software. The deep learning model used ResNet18, implementing three models in which ST, HC, and LC were learned with epoch 50 and an integrated model in which three modules were learned with Epoch 10, 30, and 50 at once. The performance of each model was evaluated through Accuracy and Loss. When comparing and evaluating the accuracy and loss function values of the deep learning models by ST, LC, and HC modules, the Accuracy and Loss of the HC model were the best with 100% and 0.0081, and in the integrated model according to the Epoch value, Accuracy and Loss with epoch 50 were the best with 96.29% and 0.1856. This paper showed that quantitative quality control is possible through a deep learning model, and it can be used as a basis and evidence for applying deep learning to the CT quality control.

• 한국해안·해양공학회논문집
• /
• 제26권6호
• /
• pp.405-412
• /
• 2014

적조에 관한 관심이 고조되면서 적조모형 개발에 관한 연구가 활발하게 지속적으로 추진되어 다양한 적조모형이 개발 적용되고 있는 실정이다. 적조는 연안생태환경 및 양식어업에 직접적인 피해를 주며, 모형을 이용한 적조 발생 및 이동양상의 정확한 예측결과는 사전 피해저감 대책수립 및 관리에 활용할 수 있기 때문에 모형의 예측 성능평가도 중요하다. 그러나 적조모형은 적조생물을 포함하는 생태모형 또는 환경생태모형이라는 유사한 용어가 명확한 구분 없이 사용되고 있어 혼동을 유발하고 있다. 각각의 모형은 유사한 용어를 사용한다 할지라도 모형의 개발 목표, 구조와 예측성능에서 차이가 나기 때문에 적절한 기준에 근거한 분류와 오차분석에 근거한 모형의 성능평가가 요구된다. 따라서 본 연구에서는 다양한 적조 모형의 구조 및 요소모형을 고려한 분류기준을 제시하고, 분류된 적조모형의 구조를 고려한 장 단점 및 한계를 제시하고, 모형 활용과정에서 실질적으로 가장 중요한 정량적인 성능평가(오차평가) 기법을 제안한다. 모형의 성능평가는 모형의 보정 및 검정과정으로 분류하여 제시하였다. 제시된 기준이나 기법은 모형의 불확실성을 고려한 정책결정 및 대책수립, 환경관리에 기여할 것으로 판단된다.

• 한국시스템다이내믹스학회:학술대회논문집
• /
• 한국시스템다이내믹스학회 1999년도 창립학술대회발표논문집
• /
• pp.105-132
• /
• 1999

If a system such as a port has a large boundary and complexity, and the system's substance is considered as a black box, forecast accuracy will be very low. Furthermore various components in a port exert significant influence on each other. To copy with these problem the form of structure models were introduced by using SD method. The Competitive Ports Model had several sub-systems consisting of each Unit Port models, and each Unit Port model was made by quantitative, qualitative factors and their feedback loops. The fact that all components of one port have influence on the components of the other ports should be taken into account to construct Competitive Port Models. However, with the current approach that is impossible, and in this paper, therefore, models were simplified by HFP adapted to integrate level variables of unit port models. Although many studies on modelling of port competitive situation have been conducted, both theoretical frame and methodology are still very weak. In this study, a new algorithm called ESD(Extensional System Dynamics) for the evaluation of port competition was presented, and applied to simulate port systems in northeast Asia.

• 한국경영과학회지
• /
• 제41권4호
• /
• pp.95-112
• /
• 2016

The purpose of this study is to develop a quantitative model to evaluate the performance of the servitized business model. We aim to quantitatively analyze the decisions of participants in the servitized supply chains, and provide methods to maximize the performance. We consider servitized supply chains consisting of a manufacturer and a service provider, that can be integrated, separated or coordinated based on the relationship between the manufacturer and the service provider. The decision models in each case are developed, and performance and profitability are analyzed. Utilizing the decision models in different cases, we compare the performances of different business models of the servitization. Since our models can be applied to analyze a wide range of the servitization business models, we expect this study can contribute to promote servitization in manufacturing companies by providing methods to evaluate the profitability of the servitization business model.

• International Journal of Vascular Biomedical Engineering
• /
• 제4권1호
• /
• pp.9-16
• /
• 2006

In this article we introduce computer models that have been developed in the past to determine the concentration of metabolic gases, the oxygen and carbon dioxide, along the pulmonary circulation. The terminal concentration of these gases in the arterial blood is related with the total change of the partial pressure of the same gases in the alveoli for the time beginning with inspiration and ending with expiration. It is affected not only by the ventilation-perfusion ratio and the gas diffusion capacity of the lung membrane but also by the pulmonary defect such as shunt, dead space, diffusion impairment and ventilation-perfusion mismatch. Some pathological pulmonary symptoms such as ARDS and CDPD can be understood through the mathematical models of these pulmonary dysfunctions. Quantitative study on the blood oxygenation process using various computer models is therefore of foremost importance in order to monitor not only the pulmonary health but also the cardiac output and cell metabolism. Reviewed in this paper include the basic and advanced methods that enable numerical study on the gas exchange and on the arterial oxygenation process, which might depend on the various heart and lung physiological conditions listed above.

• 물과 미래
• /
• 제23권4호
• /
• pp.487-497
• /
• 1990

원자력·화력, 제철소 등의 임해공업시설로부터 온수 방출의 확산에 대한 정성, 정량적 예측은 환경관리 및 냉각수 취·배수로 설계에 매우 중요하다. 본 연구는 난류 및 부력효과가 강한 온배수의 주요 물리적 특성을 규명하고 실무에 많이 사용되고 있는 MIT 및 PDS 적분모델의 비교평가를 실시하였다. 일반적으로 MIT 및 PDS 모델은 성층화되지 않은 수역에서 주위수 및 제트 방출각도를 고려하여 온배수 거동을 산정하는 모델이다. 해석결과는 그 구성의 상이성에 의해 매우 다름이 규명되어, 온배수의 정확한 산정을 위해서는 난류모델을 이용한 수치모델의 개발 및 이의 적용이 요구된다.

• Structural Engineering and Mechanics
• /
• 제71권6호
• /
• pp.739-749
• /
• 2019

This article deals with the application of reliability analysis for determining the safety of simply supported beam under the uniformly distributed load. The uncertainties of the existing methods were taken into account and hence reliability analysis has been adopted. To accomplish this aim, Generalized Regression Neural Network (GRNN), Extreme Learning Machine (ELM) and Gaussian Process Regression (GPR) models are developed. Reliability analysis is the probabilistic style to determine the possibility of failure free operation of a structure. The application of probabilistic mathematics into the quantitative aspects of a structure and improve the qualitative aspects of a structure. In order to construct the GRNN, ELM and GPR models, the dataset contains Modulus of Elasticity (E), Load intensity (w) and performance function (${\delta}$) in which E and w are inputs and ${\delta}$ is the output. The achievement of the developed models was weighed by various statistical parameters; one among the most primitive parameter is Coefficient of Determination ($R^2$) which has 0.998 for training and 0.989 for testing. The GRNN outperforms the other ELM and GPR models. Other different statistical computations have been carried out, which speaks out the errors and prediction performance in order to justify the capability of the developed models.

• Journal of Acupuncture Research
• /
• 제39권2호
• /
• pp.77-88
• /
• 2022

The purpose of this review was to identify research trends in acupuncture training systems and models and to analyze acupuncture training using phantom models. Articles on acupuncture training were retrieved from domestic and foreign electronic databases (PubMed, CNKI, CiNii, NDSL, KISS, RISS and KMBase). The search included studies conducted from January 1, 2010 to October 1, 2021. Acupuncture training was analyzed by categorization into acupoint location training and needling training. Acupuncture training was most frequently studied in China, acupoint location training was the most studied in 2012, and needling training was the most studied in 2013 and 2020. Among them, a silicone model with a sensor was used for training in acupoint location, and silicone and agarose gel were frequently used for needling training. Classifications of the phantom models for needling training by topic included phantom development, phantom-based education and evaluation system, phantom-based quantitative measurement, comparison of kinematic characteristics of hand motion between experts and beginners, and phantom models for acupoint location and needling training. Further research on the development of acupuncture practice training systems to improve practical skills is needed.

• 컴퓨터교육학회논문지
• /
• 제7권1호
• /
• pp.79-88
• /
• 2004

사이버 교수-학습환경이 활성화되면서 그 교육 과정의 핵심 요소로 상호작용의 중요성이 강조되고 있다. 그럼에도 사이버 학습에서의 상호작용성의 중요성을 강조한 연구는 쉽게 찾아볼 수 있으나 상호작용성의 특성상, 그 과정 자체를 확인하고 평가하는 방법에 대해서는 별다른 진전이 없었고 또 이를 계량적으로 평가하는데 어려움이 있었다. 이에, 본 연구는 이러한 추상적인 상호작용의 과정을 평가하고자 사이버 체제의 교수-학습과정에서 나타나는 상호작용 과정을 확인할 수 있는 정량적 데이터를 수집하였다. 이 데이터를 기초로 DEA기법과 가중치 적용기법의 두 가지 방법을 이용하여 상호작용서의 수준을 계량적으로 평가해 보았다. 이 두 가지 정량적 평가모형을 월별로 적용한 결과간의 상관계수와 서열상관계수를 살펴본 결과, 이 두 모형의 결과에는 큰 차이가 없음을 확인 할 수 있었다. 추상적인 상호작용의 과정을 정량적 접근을 통해 평가해 봄으로써 학습과정에서 발생하는 상호작용성의 정도를 검증할 수 있는 방법론을 제안하였다.

• 한국콘텐츠학회논문지
• /
• 제18권11호
• /
• pp.430-446
• /
• 2018

본 논문에서는 전파자원 활용과 관련한 정책 및 투자 방안 수립에 대한 경제적 근거 및 기초자료로서의 파급 효과 분석 방법론에 관한 비교연구를 수행하였다. 정책 및 투자 방안 간 객관적 비교 및 선정을 위해 수치적 결과를 제공하는 방법론을 분석 대상으로 하였고 수학적인 모형에 기반을 둔 정량적 방법론인 계량경제모형, 산업연관분석, 연산일반균형, 시스템 다이내믹스 방법에 대해 분석 비용 등 다양한 관점에서 효용과 한계를 비교 분석하였다. 또한, 전파자원 활용의 효과 분석 측면에서 이들 방법론을 비교하고, 분석된 방법론의 장점들을 활용하고 한계를 상쇄시키기 위해 단일 방법론들을 결합한 혼합형 모형에 대한 최근 연구결과를 논의하였다. 연구결과는 전파정책 및 투자 방안 실행의 효율성 검증을 위한 다양한 분석방법 중 분석의 목적과 우선순위에 부합하는 방법을 선정하는 데 참고 지표로 활용할 수 있다.