• 한국시뮬레이션학회논문지
• /
• 제10권2호
• /
• pp.33-46
• /
• 2001

Recently, the usage of containers in marine transportation is rapidly increasing. The problem of ship stability is important because of its direct influence to the loss of the human-life, ship, and merchandise. However, the assessment for ship stability during container loading/unloading in port is dependent on human experience only. On the other hand, the emerging information and communication technologies of shipbuilding industrial environments are rapidly changing. To respond to the situation, a new paradigm has been matured with new concepts such as the concrete method. Especially, all the efforts are shown to be concentrated to realize the concept of Simulation Based Design(SBD) based on three dimensional Computer Aided Design(CAD) model. In this paper, ship model-based simulation methodology for design and operation of ship is suggested, and for the verification of suggested methodology, the system for stability assessment of ship during container loading/unloading was developed using ENVISION, a general-purpose simulation system. The developed system consists of geometric modeling subsystem, basic calculation subsystem, and Computer Aided Engineering(CAE) subsystem. In addition, interface to CAE/CAD /simulation system such as SIKOB and ENVISION is provided.

• Nuclear Engineering and Technology
• /
• 제48권1호
• /
• pp.144-152
• /
• 2016

Human capabilities, such as technical/nontechnical skills, have begun to be recognized as crucial factors for nuclear safety. One of the most common ways to improve human capabilities in general is training. The nuclear industry has constantly developed and used training as a tool to increase plant efficiency and safety. An integrated training framework was suggested for one of those efforts, especially during simulation training sessions of nuclear power plant operation teams. The developed training evaluation methods are based on measuring the levels of situation awareness of teams in terms of the level of shared confidence and consensus as well as the accuracy of team situation awareness. Verification of the developed methods was conducted by analyzing the training data of real nuclear power plant operation teams. The teams that achieved higher level of shared confidence showed better performance in solving problem situations when coupled with high consensus index values. The accuracy of nuclear power plant operation teams' situation awareness was approximately the same or showed a similar trend as that of senior reactor operators' situation awareness calculated by a situation awareness accuracy index (SAAI). Teams that had higher SAAI values performed better and faster than those that had lower SAAI values.

• 대한한의진단학회지
• /
• 제11권2호
• /
• pp.45-58
• /
• 2007

Background and purpose: We previously developed questionnaire of Bojungikgitang systom on the Delphi method through the pathogenesis analysis. But developed a questionnaire was not verified in the clinical. So, to ensure objectivity, quantification and validity, verification is needed for questionnaire items before applying a clinical. On this study, we looked at whether questionnaire items had been validity in the clinical. Methods: Surveys conducted about 191 patients at 12 oriental medicine hospitals. Among them, patients with Bojungikgitang systom(group I) were 95, and patients with no Bojungikgitang systom(group II) were 96. We calculated that the sum of each item in the survey and then the sum was reviewed statistically significant difference through Independent samples T test between group I and II. Results: Between group I and II, the total sum survey of the percent difference is meaningful (P<0.05). Conclusions: Reliability analysis of the Bojungikgitang systom survey research is needed in the future. Also I think that research should proceed about a lot of people.

• 인터넷정보학회논문지
• /
• 제20권2호
• /
• pp.101-108
• /
• 2019

Workflow management systems (WfMSs) automate and manage workflows, which are implementations of organizational processes operated in process-centric organizations. In this paper, wepropose an algorithm to discover temporal work transference networks from workflow execution logs. The temporal work transference network is a special type of enterprise social networks that consists of workflow performers, and relationships among them that are formed by work transferences between performers who are responsible in performing precedent and succeeding activities in a workflow process. In terms of analysis, the temporal work transference network is an analytical property that has significant value to be analyzed to discover organizational knowledge for human resource management and related decision-making steps for process-centric organizations. Also, the beginning point of implementinga human-centered workflow intelligence framework dealing with work transference networks is to develop an algorithm for discovering temporal work transference cases on workflow execution logs. To this end, we first formalize a concept of temporal work transference network, and next, we present a discovery algorithm which is for the construction of temporal work transference network from workflow execution logs. Then, as a verification of the proposed algorithm, we apply the algorithm to an XES-formatted log dataset that was released by the process mining research group and finally summarize the discovery result.

• 로봇학회논문지
• /
• 제17권3호
• /
• pp.381-386
• /
• 2022

We develop a business model for facade cleaning service robot system that provides service by meeting the market needs and environments. The size of the facade cleaning market is growing rapidly in recent years due to the increasing importance of indoor space and the modern trend of building construction methods. Also, maintenance of exterior appearance of buildings has become an important factor in residential and commercial facilities. Though demand for facade cleaning services is rising, the current facade cleaning services are performed dangerously in a human labor-dependent way. It is desirable that the existing human resource service should be replaced with robot-based services. In addition, quantitative analysis of rental pricing model was conducted to propose effective launch of products to the market. The robot system is economically attractive from the consumer's point of view. When the actual facade cleaning robot service is released, it is expected that verification of the business models and more accurate analysis with specific figures can be performed.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2021년도 제33회 한글 및 한국어 정보처리 학술대회
• /
• pp.3-8
• /
• 2021

인공지능 기술이 발달함에 따라 기계번역 기술도 많은 진보를 이루었지만 여전히 기계번역을 통한 번역문 내에는 사람이 교정해야 하는 오류가 다수 포함되어있다. 이렇게 번역 모델에서 생성되는 오류를 교정하는 전문인력의 요구를 경감시키기 위하여 기계번역 사후교정 연구가 등장하였고, 해당 연구는 현재 WMT를 주축으로 활발하게 연구되고 있다. 이러한 사후교정 연구는 최근 도메인 특화 관점에서 주로 연구가 이루어지고 있으며 현재 많은 도메인에서 유의미한 성과를 내고 있다. 하지만 이런 연구들은 기존 번역문의 품질을 얼만큼 향상시켰는가에 초점을 맞출 뿐, 다른 도메인 특화 번역모델의 성능과 비교했을 때 얼마나 뛰어난지는 밝히지 않기 때문에 사후교정 연구가 도메인 특화에서 효과적으로 작용하는지 명확하게 알 수 없다. 이에 본 연구에서는 도메인 특화 번역 모델과 도메인 특화 사후교정 모델간의 성능을 비교함으로써, 도메인 특화에서 사후교정을 통해 얻을 수 있는 실제적인 성능을 검증한다. 이를 통해 사후교정이 도메인 특화 번역모델과 비교했을 때 미미한 수준의 성능을 보임을 실험적으로 확인하였고, 해당 실험 결과를 분석함으로써 향후 도메인특화 사후교정 연구의 방향을 제안하였다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2021년도 제33회 한글 및 한국어 정보처리 학술대회
• /
• pp.281-286
• /
• 2021

뉴스 헤드라인에 제3자의 발언을 직접 인용해 전언하는 이른바 '따옴표 저널리즘'이 언론 보도의 객관주의 원칙을 해치는지는 언론학 및 뉴스 구독자에게 중요한 문제이다. 이 연구는 온라인 포털사이트를 통해 실시간 유통되는 한국어 기사의 정확성을 판별하기 위한 기계학습(Machine Learning) 모델을 제안한다. 이 연구에서 제안하는 모델은 Edit Distance와 FastText 기법을 활용해 기사 제목과 본문 내 인용구의 유사성을 측정하고, XGBoost 모델을 활용해 최종 분류한다. 아울러 이 모델을 통해 229만 건의 뉴스 헤드라인에 대해 직접 인용구가 포함된 기사가 취재원의 발언을 주관적인 윤색없이 독자들에게 전하고 있는지를 판별했다. 이뿐만 아니라 딥러닝 기반의 KoELECTRA 모델을 활용해 기사의 제목 내 인용구에 대한 감성 분석을 진행했다. 분석 결과, 윤색이 가미되지 않은 직접 인용형 기사의 비율이 지난 20년 동안 10% 이상 증가했으며, 기사 제목의 인용구에 나타나는 감정은 부정 감성이 긍정 감성의 2.8배 정도로 우세했다. 이러한 시도는 앞으로 계산사회과학 방법론과 빅데이터에 기반한 언론 보도의 평가 및 개선에 도움을 주리라 기대한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2750-2767
• /
• 2023

Live Commerce is rapidly emerging as a new paradigm for the digital economy and consumption activities in the post-COVID era. Many prior studies have been conducted on Live Commerce, but studies focusing on the characteristics of sources of Live Commerce are insufficient. This study aimed to investigate the human factors of sources that affect consumers' intention to use Live Commerce. For this purpose, based on an expanded TAM (Technology Acceptance Model) through literature research, variables were set, and a survey was conducted targeting Korean consumers who have experienced purchasing products through Live Commerce. Excluding unreliable data, 201 responses were utilized in the analysis of this study. At first, the measurement tools were checked through validity and reliability verification, and correlation analysis was conducted to identify the relationships between variables. Then, the proposed hypotheses were verified through multiple regression analysis. As a result, firstly, the human factors of sources had a positive effect on PU (Perceived Usefulness). Secondly, the PEOU (perceived ease of use) had a positive effect on both PU and CS (Consumer Satisfaction). Thirdly, PU had a positive effect on CS and ITU (Intention to Use). Finally, CS with Live Commerce had a positive effect on the ITU. Through this study, we try to provide an understanding of consumer behavior in the Live Commerce environment and contribute to enhancing the service provider's ability to offer high-quality Live Commerce content.

• 산업경영시스템학회지
• /
• 제31권1호
• /
• pp.41-48
• /
• 2008

Enhanced machine reliability has dramatically reduced the rate and number of railway accidents but for further reduction human error should be considered together that accounts for about 20% of the accidents. Therefore, the objective of this study was to suggest a new taxonomy of performance shaping factors (PSFs) that could be utilized to identify the causes of a human error associated with railway accidents. Four categories of human factor, task factor, environment factor, and organization factor and 14 sub-categories of physical state, psychological state, knowledge/experience/ability, information/communication, regulation/procedure, specific character of task, infrastructure, device/MMI, working environment, external environment, education, direction/management, system/atmosphere, and welfare/opportunity along with 131 specific factors was suggested by carefully reviewing 8 representative published taxonomy of Casualty Analysis Methodology for Maritime Operations (CASMET), Cognitive Reliability and Error Analysis Method (CREAM), Human Factors Analysis and Classification System (HFACS), Integrated Safety Investigation Methodology (ISIM), Korea-Human Performance Enhancement System (K-HPES), Rail safety and Standards Board (RSSB), $TapRoot^{(R)}$, and Technique for Retrospective and Predictive Analysis of Cognitive Errors (TRACEr). Then these were applied to the case of the railway accident occurred between Komo and Kyungsan stations in 2003 for verification. Both cause decision chart and why-because tree were developed and modified to aid the analyst to find causal factors from the suggested taxonomy. The taxonomy was well suited so that eight causes were found to explain the driver's error in the accident. The taxonomy of PSFs suggested in this study could cover from latent factors to direct causes of human errors related with railway accidents with systematic categorization.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2000년도 추계학술대회 학술발표 논문집
• /
• pp.297-300
• /
• 2000

현재 연구되어지고 있는 홍채인식 시스템의 일반적인 구성을 보면 영상획득, 전처리, 특징추출, 인식/검증의 네 단계를 거치게 된다. 이 과정에서 최후 본인여부의 판단이 내려지는 것은 인식/검증의 마지막 단계인데, 전체 등록된 사용자의 수가 적을 경우 인식 방법을 통해 사용자를 확인할 수 있게 되어 그 정확도가 상당히 높을 수 있다. 하지만 등록된 사용자의 수가 많은 경우 인식방법에는 무리가 따르게 된다. 이에 따라 전자상거래와 같은 다수의 사용자를 보유하게 되는 시스템에서는 사용자 아이디를 함께 입력받아 본인 여부를 판단하는 검증 방법을 사용하는 것이 빠르고 효과적이라 할 수 있다. 본 논문에서는 기존에 사용되어지던 특징벡터의 일치율 또는 해밍 거리를 통한 검증방법에서 나아가 저용량 특징벡터에 적합하도록, 홍채영상으로부터 추출된 특징에 대해 적절한 양자화와 가중치를 두어 각 특징벡터 간의 내적을 통해 유사도를 측정함으로써 본인의 데이터와 타인의 데이터간의 차이를 크게 하여 향상된 성능의 홍채인식 시스템을 구현하는 방법을 제안한다.