• 제목/요약/키워드: national statistical system

검색결과 1,557건 처리시간 0.03초

설명 가능한 AI를 적용한 기계 예지 정비 방법 (Explainable AI Application for Machine Predictive Maintenance)

  • 천강민;양재경
    • 산업경영시스템학회지
    • /
    • 제44권4호
    • /
    • pp.227-233
    • /
    • 2021
  • Predictive maintenance has been one of important applications of data science technology that creates a predictive model by collecting numerous data related to management targeted equipment. It does not predict equipment failure with just one or two signs, but quantifies and models numerous symptoms and historical data of actual failure. Statistical methods were used a lot in the past as this predictive maintenance method, but recently, many machine learning-based methods have been proposed. Such proposed machine learning-based methods are preferable in that they show more accurate prediction performance. However, with the exception of some learning models such as decision tree-based models, it is very difficult to explicitly know the structure of learning models (Black-Box Model) and to explain to what extent certain attributes (features or variables) of the learning model affected the prediction results. To overcome this problem, a recently proposed study is an explainable artificial intelligence (AI). It is a methodology that makes it easy for users to understand and trust the results of machine learning-based learning models. In this paper, we propose an explainable AI method to further enhance the explanatory power of the existing learning model by targeting the previously proposedpredictive model [5] that learned data from a core facility (Hyper Compressor) of a domestic chemical plant that produces polyethylene. The ensemble prediction model, which is a black box model, wasconverted to a white box model using the Explainable AI. The proposed methodology explains the direction of control for the major features in the failure prediction results through the Explainable AI. Through this methodology, it is possible to flexibly replace the timing of maintenance of the machine and supply and demand of parts, and to improve the efficiency of the facility operation through proper pre-control.

학교도서관 북큐레이션 운영에 대한 사서의 인식조사 연구 - 부산지역 초등학교 도서관을 중심으로 - (A Study on the Perception of Librarians on the Operation of School Library Book Curation: Focused on Elementary School Libraries in Busan)

  • 김미나;강은영
    • 한국비블리아학회지
    • /
    • 제33권2호
    • /
    • pp.5-31
    • /
    • 2022
  • 이 연구는 부산지역 초등학교 도서관의 북큐레이션 운영에 대한 사서의 인식을 조사하여 분석한 다음, 학교도서관에서의 북큐레이션 활성화방안을 제안하고자 하였다. 2021년 기준 국가도서관통계시스템의 학교도서관 현황을 활용하여 부산지역 304개 학교도서관 목록을 확보하여 사서가 배치되어 있는 121개 학교도서관을 선정한 다음 설문조사에 참여하기로 한 83개관을 최종 연구대상으로 선정하였다. 북큐레이션 운영현황과 사서와 사서교사의 인식조사 결과를 바탕으로 학교도서관 북큐레이션을 활성화하기 위한 방안으로 1) 북큐레이션에 대한 전문화된 교육의 확대와 제공, 2) 학교도서관 북큐레이션 운영에 관한 자료의 개발과 보급, 3) 북큐레이션에 대한 역량강화를 위한 사서들의 지속적인 노력, 4) 학교도서관 사서 간의 협력과 정보 공유 등을 제안하였다.

사회재난 지표별 등급화 기법 비교: 가축질병을 중심으로 (Comparison of Rating Methods by Disaster Indicators)

  • 이효진;윤홍식;한학
    • 한국재난정보학회 논문집
    • /
    • 제17권2호
    • /
    • pp.319-328
    • /
    • 2021
  • 연구목적: 최근 대형 사회재난이 발생하면서 사회재난 안전도 진단에 대한 필요성이 요구되며 행정안전부에서 지역 안전지수, 국가안전대진단 등 지역의 안전도 등급을 계산하여 매년 공표하고 있다. 기존의 안전도 진단 시스템은 등간격 혹은 정규분포를 이용해서 획일화된 방법으로 등급화를 진행하여 위험지도를 작성하고 있다. 연구방법: 하지만 등간격 기법은 위험등급을 객관적으로 분석할 수 있지만 분포가 한쪽에 치우쳐있는 경우 위험등급을 분류하는데 한계가 있으며 z-score 기법은 모집단이 정규분포를 따르지 않으면 신뢰도가 떨어지는 문제가 있다. 지표별로 통계 데이터의 분포가 상이하기 때문에 데이터 분포별로 가장 적합한 등급화를 적용해야한다. 연구결과: 따라서 본 논문에서는 재난 지표의 데이터를 분석하여 각 지표마다 최적화된 등급화를 진행하고자 기존의 등간격 기법과 네츄럴브레이크 기법을 비교 및 적합한 방법을 제시하였다. 결론: 그 결과 기존의 등급화 기법과 다르게 적용된 것은 6새 지표 중 3개에 해당하였다.

SWOT Analysis and Expert Assessment of the Effectiveness of the Introduction of Healthcare Information Systems in Polyclinics in Aktobe, Kazakhstan

  • Lyudmila, Yermukhanova;Zhanar, Buribayeva;Indira, Abdikadirova;Anar, Tursynbekova;Meruyert, Kurganbekova
    • Journal of Preventive Medicine and Public Health
    • /
    • 제55권6호
    • /
    • pp.539-548
    • /
    • 2022
  • Objectives: The purpose of this study was to assess the organizational effectiveness of the introduction of a healthcare information system (electronic medical records and databases) in healthcare in Kazakhstan. Methods: The authors used a combination of 2 methods: expert assessment and strengths, weaknesses, opportunities, and threats (SWOT) analysis. SWOT analysis is a necessary element of research, constituting a mandatory preliminary stage both when drawing up strategic plans and for taking corrective measures in the future. The expert survey was conducted using 2 questionnaires. Results: The study involved 40 experts drawn from specialists in primary healthcare in Aktobe: 15 representatives of administrative and managerial personnel (chief doctors and their deputies, heads of medical statistics offices, organizational and methodological offices, and internal audit services) and 25 general practitioners. Conclusions: The following functional indicators of the medical and organizational effectiveness of the introduction of information systems in polyclinics were highlighted: first, improvement of administrative control, followed in descending order by registration and movement of medical documentation, statistical reporting and process results, and the cost of employees' working time. There has been no reduction in financial costs, namely in terms of the costs of copying, delivery of information in paper form, technical equipment, and paper.

A Study on the Effects That SMEs' Response to Non-Tariff Barriers Exerts on Export Performance: Focusing on Technical Barriers to Trade

  • Joo, Se-Hwan;Lee, Jae-Sung
    • Journal of Korea Trade
    • /
    • 제25권6호
    • /
    • pp.105-125
    • /
    • 2021
  • Purpose - This study analyzes the effects that the response to the technical barriers to trade (TBT), which are used by various countries as means to restrict imports, exerts on exports at a time when protectionism is emerging in the face of a global economic downturn. TBT has been widely used in developed countries for the safety and protection of their people. Recently, the use of TBT as a tool of protectionism has increased considerably in developing countries as well. Therefore, this study analyzes the South Korean SMEs' response and export performance. Design/methodology - To analyze SMEs' response to TBT and their export performance, this study conducted empirical analysis through statistical analysis. To this end, the research established a theory based on previous research and designed its hypothesis and research model. To verify the hypothesis and research model, factor analysis addressing validity and reliability was performed using SPSS 25 and AMOS 26, and the structural equation model was analyzed. Findings - This study found the causal relationship between the independent variable, the mediating variable, and the dependent variable adopted against the theoretical background to have little or no effect, in contrast with previous studies. In a break from previous studies, all hypotheses were rejected for innovation strategic competencies, one of the sub-factors of the independent variable, which is believed to be a result of the lack of practical research related to TBT. Originality/value - Previous studies performed analysis using trade statistics or macro data. A number of such studies analyzed the relationship between technical regulation and trade volume. This study differs from previous studies in some respects, because it analyzed the export performance of companies by establishing a hypothesis and implementing a research model with the factors analyzed in previous studies. In addition, a new attempt has been made by classifying the TBT response factors into technology competencies, human resource competencies, and innovation strategic competencies, and utilizing technology innovation and the export support system as mediating effects.

Assessment of public knowledge, perception, and acceptance of nuclear power in Bangladesh

  • Md Iqbal Hosan;Md Jafor Dewan;Md Hossain Sahadath;Debasish Roy;Drupada Roy
    • Nuclear Engineering and Technology
    • /
    • 제55권4호
    • /
    • pp.1410-1419
    • /
    • 2023
  • Public perception plays a crucial role in the successful completion of a nuclear power project. As a newcomer country to nuclear power, there are lots of misconceptions among the Bangladeshi people about nuclear energy. Consequently, it is crucial to minimize all the doubts among mass people and build up their positive outlook toward nuclear power. This demands a comprehensive survey to figure out the public opinion, concerns, false impressions, and knowledge gap regarding nuclear power. In the present study, these issues were addressed by a survey that was responded to by 661 persons for the 24 survey questions. The questions were categorized based on information, knowledge, faith, benefit, awareness, and technology. Feedback and responders' basic demographic and socioeconomic information were collected from various locations in Bangladesh through online and in-person surveys. The responses were analyzed in both statistical and descriptive ways. Some of the feedback was found to vary with age, sex, and education level while others were quite independent of these parameters. It is found that socioeconomic development and energy security can be achieved by the inclusion of nuclear energy in the power system master plan of the country. However, huge knowledge gaps and misconceptions were found among the public regarding nuclear energy. As per feedback, political instability and corruption may affect the national nuclear power project in Bangladesh. Low faith in the existing rules & regulations for nuclear power programs was also observed. The result of this study will be handy to develop the communication and public awareness strategy for a successful nuclear power project in Bangladesh.

국내 토양오염물질 분포 특성 및 중금속 오염도 평가 (Assessment of Soil Pollutant Distribution Characteristics and Heavy Metal Pollution in Korea)

  • 이종철;강민우;최규혁;오세진;김동진;이상수
    • 한국환경농학회지
    • /
    • 제41권1호
    • /
    • pp.9-15
    • /
    • 2022
  • BACKGROUND: Heavy metals discharged from various sources contaminate the soil and water and the residuals can persistently be accumulated. In this study, the concentration of soil heavy metals was assessed over the whole regions of Korea based on the contamination factor and the geoaccumulation index. METHODS AND RESULTS: The data of averaged concentrations of heavy metals and fluorine were collected from the Korean Statistical Information Service (KOSIS) and the research papers published. In order to classify the levels of heavy metal concentration, the contamination index, including the contamination factor and the geoaccumulation index, based on the relative ratio of the actual concentration of heavy metals in the soil to the background concentration was calculated. In addition, the distribution of heavy metals in soils was visualized by using the geographic information system (GIS). As a result, the Cd contamination in the soils was the most concerned. CONCLUSION(S): This study very roughly indicated the outline of heavy metal concentration over the whole regions of Korea. The change in heavy metals' concentration over the time should further be monitored and the larger data of heavy metal contamination are needed for better understanding in the future.

1D-CNN을 이용한 항만내 선박 이동시간 예측 (Prediction of Ship Travel Time in Harbour using 1D-Convolutional Neural Network)

  • 유상록;김광일;정초영
    • 한국항해항만학회:학술대회논문집
    • /
    • 한국항해항만학회 2022년도 춘계학술대회
    • /
    • pp.275-276
    • /
    • 2022
  • 해상교통관제사는 항로폭이 협소한 항만에서 선박 충돌사고 예방을 위해 one-way로 항해하도록 선박의 입·출항 대기 지시를 한다. 현재 해상교통관제사의 입·출항대기 지시는 과학적이고 통계적인 데이터를 기반으로 하지 않고 해상교통관제사의 개인 역량에 따라 편차가 크다. 이에 따라 본 연구에서는 항만에서의 선박 입·출항 대기 지시를 위한 정확한 이동 시간을 예측하기 위해 선박 및 기상 데이터를 수집하여 1d-합성곱신경망 모델을 구축하였다. 제안한 모델이 다른 앙상블 기계학습 모델보다 4.5% 이상 개선된 것을 확인하였다. 본 연구를 통해 다양한 상황에서도 선박 입·출항 소요시간 예측이 가능하여 해상교통관제사는 선박에게 정확한 정보 제공 및 대기지시 판단에 도움이 될 것으로 기대된다.

  • PDF

애널리스트 보고서 텍스트의 주가예측력에 대한 검증 (Verification on stock return predictability of text in analyst reports)

  • 이영선;야마다 아키히코;양철원;노호석
    • 응용통계연구
    • /
    • 제36권5호
    • /
    • pp.489-499
    • /
    • 2023
  • 온라인 플랫폼을 통한 애널리스트 보고서의 공유가 가능해짐에 따라 애널리스트들이 생성한 보고서는 시장 참여자들 간 금융 정보 격차를 줄일 수 있는 유용한 도구가 되었으며, 애널리스트 보고서의 정량적 정보가 주식수익률 예측에 다수 활용되었다. 하지만 상대적으로 애널리스트 보고서 내 텍스트 정보의 주식수익률 예측 정보력에 대한 국내 자료 기반 연구는 상대적으로 많이 부족하다. 본 연구는 애널리스트 보고서에서 추출 가능한 텍스트로부터 어조 변수를 생성하여 주식수익률 예측에 정보력이 있는지를 검증하되, 기존 연구들의 선형모형 가정 기반 검정의 한계를 해결하고자 랜덤 포레스트 기반의 F-test를 사용하여 기업수익률 예측력을 검증하였다.

이공계열 대학원생 핵심역량 진단도구 개발 및 타당화 연구: A연구중심대학 사례 (Development and Validation of Core Competency Scale For Graduate Students in the Field of Science and Engineering)

  • 배상훈;조은원;한송이;정유지;김경언
    • 공학교육연구
    • /
    • 제27권2호
    • /
    • pp.35-50
    • /
    • 2024
  • The purpose of this study is to identify the core competencies of graduate students at A research university in the context of graduate education in science and engineering, and to develop and validate a diagnostic tool to measure them. To achieve the research objectives, first, 6 factors and 18 sub-competencies of core competencies were derived based on a review of domestic and foreign studies, cases of excellent research-centered overseas universities, and interviews with members of A University. Second, a theoretical model was constructed by deriving behavioral indicators based on the core competencies and sub-competencies, and a preliminary survey was conducted on 188 graduate students of University A to verify the statistical validity of the theoretical model. Results of exploratory and confirmatory factor analysis, the core competencies of graduate students at A research university consisted of 6 factors, 16 sub-competencies, and 77 items. Specifically, it included "Independent research capability(13 items)", "Social Entrepreneurship(10 items)", "Academic agility(15 items)", "Ingenious Challenges(15 items)", "Collegial Collaboration(9 items)", and "Mueunjae leadership(15 items)". This study contributes to the development of theories related to core competencies of graduate students in science and engineering, and has practical significance as a basis for a data-driven competency-based graduate education system.