• 시스템엔지니어링학술지
• /
• 제16권2호
• /
• pp.67-77
• /
• 2020

Traditionally nuclear thermal hydraulic and nuclear safety has relied on numerical simulations to predict the system response of a nuclear power plant either under normal operation or accident condition. However, this approach may sometimes be rather time consuming particularly for design and optimization problems. To expedite the decision-making process data-driven models can be used to deduce the statistical relationships between inputs and outputs rather than solving physics-based models. Compared to the traditional approach, data driven models can provide a fast and cost-effective framework to predict the behavior of highly complex and non-linear systems where otherwise great computational efforts would be required. The objective of this work is to develop an AI algorithm to predict the peak fuel cladding temperature as a metric for the successful implementation of FLEX strategies under extended station black out. To achieve this, the model requires to be conditioned using pre-existing database created using the thermal-hydraulic analysis code, MARS-KS. In the development stage, the model hyper-parameters are tuned and optimized using the talos tool.

• 한국엔터테인먼트산업학회논문지
• /
• 제15권2호
• /
• pp.1-10
• /
• 2021

본 연구의 목적은 엔터테인먼트 산업에 효과적인 고성과작업조직(high performance work system)을 모색, 제시하는 데 있다. 최근에 엔터테인먼트 산업 자체는 급격하게 성장하고 있으나, 엔터테인먼트 기업은 제조업과 달리 안정적 수익구조를 확보하기 어렵다는 특징이 있다. 엔터테인먼트 기업 및 프로젝트의 성과는 인적자원의 역량과 시너지에 의존하는 경향이 농후하기 때문이다. 이를 관리할 수 있는 체계적인 모델을 마련하고자, 본 연구는 ANP(analytic network process)를 활용하여 엔터테인먼트 기업에 경쟁우위를 제공할 수 있는 고성과작업조직을 제시하였다. 고성과작업조직의 성공적 특성을 평정한 쌍대비교 자료는 엔터테인먼트 기업에 종사하는 28명의 팀장급 리더를 대상으로 수집되었다. 연구 결과, '개발적 지원', '관리적 지원'에 비해 '참여기회 부여'가 가장 높은 중요도를 나타냈다. 구체적인 구성요소별 중요도는, '개방적 의사소통', '분산된 의사결정', '성과에 의한 보상'이 높게 나타났다. 본 연구의 결과에 기초하여 엔터테인먼트 기업에서 고성과작업조직을 성취하는 데 실질적 시사점과 실행의 우선순위를 제언하였다.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1516-1529
• /
• 2016

While global manufacturing is becoming more competitive due to variety of customer demand, increase in production cost and uncertainty in resource availability, the future ability of manufacturing industries depends upon the implementation of Smart Factory. With the convergence of new information and communication technology, Smart Factory enables manufacturers to respond quickly to customer demand and minimize resource usage while maximizing productivity performance. This paper presents the development of a big data analytics platform architecture for Smart Factory. As this platform represents a conceptual software structure needed to implement data-driven decision-making mechanism in shop floors, it enables the creation and use of diagnosis, prediction and optimization models through the use of data analytics and big data. The completion of implementing the platform will help manufacturers: 1) acquire an advanced technology towards manufacturing intelligence, 2) implement a cost-effective analytics environment through the use of standardized data interfaces and open-source solutions, 3) obtain a technical reference for time-efficiently implementing an analytics modeling environment, and 4) eventually improve productivity performance in manufacturing systems. This paper also presents a technical architecture for big data infrastructure, which we are implementing, and a case study to demonstrate energy-predictive analytics in a machine tool system.

• 대한지역사회영양학회지
• /
• 제26권3호
• /
• pp.155-166
• /
• 2021

Objectives: Driven by a growth of single-person households and individualized lifestyles, solo dining in restaurants is an increasingly recognizable trend. However, a research gap exists in the comparison of solo and group diners' menu-decision making processes. Based on the self-control dilemma and the temporal construal theory as a theoretical framework, this study compared the ordering intentions of solo vs. group diners with healthy vs. indulgent (less healthy) entrées. The mediating role of consumption orientation and the moderating role of amount of menu nutrition information were further explored to understand the mechanism and a boundary condition. Methods: A scenario-based online survey was developed using a 2 (dining social context: solo vs. with others) × 3 (amount of menu nutrition information: no nutrition information vs. calories vs. calories/fat/sodium), between-subjects, experimental design. Consumers' level of nutrition involvement was controlled. A nationwide survey data (n = 224) were collected from a crowdsourcing platform in the U.S. Data were analyzed using multivariate analysis of covariance, independent t-test, univariate analysis of covariance, and moderated mediation analyses. Results: Findings reveal that solo (vs. group) diners have less (vs. more) intentions to order indulgent menu items due to a more utilitarian (vs. more hedonic) consumption orientation in restaurant dining. Findings also show that solo (vs. group) diners have more (vs. less) intentions to order healthy menu items when the restaurant menu presented nutrition information including calories, fat, and sodium. Conclusions: The findings contribute to the literature of foodservice management, healthy eating, and consumer behavior by revealing a mechanism and an external stimuli of solo vs. group diners' healthy menu-decision making process in restaurants. Furthermore, the findings provide restauranteurs and health professionals with insights into the positive and negative impacts of menu nutrition labelling on consumers' menu-decisions.

• 디지털콘텐츠학회 논문지
• /
• 제5권1호
• /
• pp.54-60
• /
• 2004

본 논문에서 이러한 인터넷 환경에서 자신에게 필요한 정보를 빠르게 확보하기 위한 방법으로 설문조사와 원서 접수를 이용하였으며, 이는 인터넷이 급격하게 보급됨으로 환경 변화에 신속 정확하게 대처하기 위한 질 높은 정보들이 기업이나 개인에게 필요하게 되었다. 웹 GUI 환경을 기반으로 하여 사용자의 편의성을 제공하였고 Agent 개념을 도입하여 설문조사와 원서 접수가 등록되면 자동으로 적합한 정보를 검색하여 사용자에게 제공하여 줌으로 흥미 유발과 참여도를 높일 수 있다. 또한 정보의 빠른 수집이 가능하여 짐에 따라 사용자의 의사결정에 도움을 준다.

• 대한감각통합치료학회지
• /
• 제17권3호
• /
• pp.26-45
• /
• 2019

목적 : 본 연구의 목적은 작업치료사가 감각통합 중재를 실행하는데 필요한 역량을 기반으로 중재 과정 교육 커리큘럼 개발하고, 중재과정 실시 및 교육만족도 확인을 통하여 대한감각통합치료학회의 역량기반 중재 교육과정을 제시하는데 있다. 연구방법 : 본 연구는 대한감각통합치료학회의 2019년 중재과정에 참여한 작업치료사 9명과 강사 3명을 대상으로 하였다. 중재과정의 교육목표 설정은 참여자 설문조사 방법을 통하여 교육요구 분석방법을 사용하였다. 중재과정의 역량기반 교육 프로그램 초안 및 교육 방법은 강사회의를 통하여 결정하였다. 중재교육과정은 실행계획에 따라 5일간 실시하였으며, 교육 만족도와 각 역량지표에 대한 중재과정 전후의 수행도 변화를 조사하였다. 결과 : 교육목표는 교육요구 분석 결과를 반영하여 '감각통합중재의 임상추론 과정을 학습 하고 적용한다'와 '감각통합중재 원칙을 적용하여 중재한다'로 하였다. 역량기반 중재과정 교육커리큘럼은 교육목표에 따라 Data driven decision making process 및 Ayres Sensory Integration에 관한 강의, 워크샵, 토의, 그리고 사례 중재 등으로 구성하여 총 42시간 교육을 실시하였다. 중재과정 참여자의 교육 만족도는 평균 4.48±0.73이었고, 수퍼바이저의 교육 만족도는 평균 3.92±0.71이었다. 두 집단 모두에서 Data driven decision making process 강의와 중재 목표 수립 강의의 만족도가 가장 높았고, 그룹 활동 및 토의에 대한 만족도가 가장 낮았다. 중재과정 전후, 역량모델의 전문가 역량군에 포함된 분석기술 역량의 두 가지 행동지표가 수행도에서 유의미한 변화를 보였다. 결론 : 본 연구는 교육 개발에 필요한 체계적 과정을 거쳐 교육요구 조사, 교육 커리큘럼 개발과 실시, 교육 만족도 조사를 실행하였다는 점에서 의의가 있다. 대한감각통합치료학회 내의 다른 교육커리큘럼 개발 시 기초자료로 사용될 수 있을 것으로 생각된다.

• 대한토목학회논문집
• /
• 제38권4호
• /
• pp.505-516
• /
• 2018

교량 유지관리 전략 수립 시 현재 상태를 기반으로 미래 상태를 예측할 수 있어야 하며, 상태예측모델의 신뢰도가 높아질수록 효과적인 유지관리 의사결정이 가능하다. 그러나 인력기반 반복 주기적인 현행유지관리는 관리자가 목표하는 관리(등급)수준의 교량 상태를 정확히 예측하지 못해서 막대한 보수 보강비용이 발생될 가능성이 있고, 합리적인 유지관리 의사결정을 도모하는데 어려움을 겪는다. 이에 따라 본 논문에서는 국내 교량 점검 이력 데이터를 이용하여 불확실성을 고려한 교량 부재별 대표 상태예측모델을 개발하고, 개발된 상태예측모델을 실제 유지관리 대상 교량에 보다 높은 정확도로 적용 가능한 베이지안 업데이트 기법을 제안하였다. 또한, 모니터링 업데이트 상태예측모델 기반 예방적 유지관리가 기존 현행유지관리 대비 비용 효율성 측면에서 유리함을 제안하기 위해 각각의 유지관리비용 산출에 따른 교량 점검 타당성 분석을 수행하였다.

• Smart Structures and Systems
• /
• 제26권4호
• /
• pp.495-506
• /
• 2020

Monitoring of complex processes faces several challenges mainly due to the lack of relevant sensory information or insufficient elaborated decision-making strategies. These challenges motivate researchers to adopt complex data processing and analysis in order to improve the process representation. This paper presents the development and implementation of quality monitoring framework based on a model-driven approach using embedded artificial intelligence strategies. In this work, the strategies are applied to the supervision of a microfabrication process aiming at showing the great performance of the framework in a very complex system in the manufacturing sector. The procedure involves two methods for modelling a representative quality variable, such as surface roughness. Firstly, the hybrid incremental modelling strategy is applied. Secondly, a generalized fuzzy clustering c-means method is developed. Finally, a comparative study of the behavior of the two models for predicting a quality indicator, represented by surface roughness of manufactured components, is presented for specific manufacturing process. The manufactured part used in this study is a critical structural aerospace component. In addition, the validation and testing are performed at laboratory and industrial levels, demonstrating proper real-time operation for non-linear processes with relatively fast dynamics. The results of this study are very promising in terms of computational efficiency and transfer of knowledge to manufacturing industry.

• 아태비즈니스연구
• /
• 제13권1호
• /
• pp.37-52
• /
• 2022

Purpose - The objective of this study is to investigate what motivates global FDI inflows in the different economic development level and to clarify the FDI motivation type in the level of qualitative economic growth. Design/methodology/approach - Major macroscopic social·economic factors induced FDI inflows were analyzed using fixed-effect panel regression with 30-year panel data of 28 countries from 1985 to 2014. For analysis in the stage of economic growth, two category of developed and developing countries was used. And to analyze FDI motivation type in the level of qualitative economic growth, 4 shares of GDP; consumption·government·investment expenditure and export, was used as explanatory variable. Findings - In developed country, TFP(total factor productivity) and GDP have a great influence on FDI inflows, and consumption and labor compensation have a slight effect. This result indicates that the market seeking-driven, horizontal type investment is shown along with efficiency seeking investment. In developing country, human capital and TFP is shown to have greater impact on FDI inflows and labor compensation, exports, investment and government expenditures also have impacts. Thus it has confirmed that not only efficiency-seeking vertical investment for using low cost well educated laborer, but also government-driven economic growth and export policies could affect the FDI inflows. Research implications or Originality - The FDI investment decision making of multinational companies is decided by their own purpose. But, in the concept of as follows; 1) FDI is a long-term capital flowing for maximization of economic utility with limited global resource, 2) Thus FDI could be affected by macro socio·economic factors of host country. 3) Also such macro factors is different by each economic growth qualitative level. Therefore macro socio·economic factors of each country could be affected by the qualitative level of their own economic growth. To attract FDI inflows, it is desirable to implement differentiated incentive policies in the qualitative level of economic growth. Furthermore in developing countries it is recommended to implement government driven economic growth policies as follows; fostering well educated human resources, improving technology productivity in the relative lower cost labor market compared to developed countries and boosting international export volume.

• Nuclear Engineering and Technology
• /
• 제54권8호
• /
• pp.2859-2870
• /
• 2022

Because nuclear power plants (NPPs) are safety-critical infrastructure, it is essential to increase their safety and minimize risk. To reduce human error and support decision-making by operators, several artificial-intelligence-based diagnosis methods have been proposed. However, because of the nature of data-driven methods, conventional artificial intelligence requires large amount of measurement values to train and achieve enough diagnosis resolution. We propose a graph neural network (GNN) based accident diagnosis algorithm to achieve high diagnosis resolution with limited measurements. The proposed algorithm is trained with both the knowledge about physical correlation between components and measurement values. To validate the proposed methodology has a sufficiently high diagnostic resolution with limited measurement values, the diagnosis of multiple accidents was performed with limited measurement values and also, the performance was compared with convolution neural network (CNN). In case of the experiment that requires low diagnostic resolution, both CNN and GNN showed good results. However, for the tests that requires high diagnostic resolution, GNN greatly outperformed the CNN.