• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.261-267
• /
• 2021

The mission of the reserve forces unit is to prepare good training for reserve forces during peacetime. For good training, units require proper organization support agents, but they have difficulties due to a lack of unit members. For that reason, the units forecast the monthly attendance rate of reserve forces (using the x-1 year's result) to organize support agents and unit schedule. On the other hand, the existing planning method can have more errors compared to the actual result of the attendance rate. This problem has a negative effect on the training performance. Therefore, it requires more accurate forecast models to reduce attendance rate errors. This paper proposes an attendance rate forecast model using data mining. To verify the proposed data mining based model, the existing planning method was compared with the proposed model using real data. The results showed that the proposed model outperforms the existing planning method.

• The Journal of the Korea Contents Association
• /
• v.20 no.2
• /
• pp.1-14
• /
• 2020

Leading the fourth industrial revolution era requires science and technology strategies that establish original research directions at the national level. To this end, it is necessary to look at the research and development activities for the fourth industrial revolution of technology-leading countries. In this study, the research programs of the U.S. Intelligence Advanced Research Projects Activity(IARPA), an organization focusing on cutting edge research on science and technology information such as artificial intelligence, are investigated by using network analysis. The findings show that, resolving around the information identification and forecasting, decision making and cybersecurity clusters, IARPA's research programs largely focus on finding hidden information and predicting specific events, supporting decision making by considering changes in and outside organizations or establishing cybersecurity. Also, this study finds that China and Japan, representative technology-leading Asian countries, refer to the research programs of IARPA to establish their science and technology policies. The results of this study suggest implications for Korea's science and technology policies in response to the fourth industrial revolution era.

• Journal of Technology Innovation
• /
• v.31 no.2
• /
• pp.173-214
• /
• 2023

Investments in new technologies have grown significantly in size, and science and technology have a large and complex impact on society at large. With people's great interest in technology, the government has the duty to accurately assess the influence of new technologies on society to facilitate their acceptance in society. For this purpose, technology impact assessment should be performed to facilitate a social consensus. There has been research on the initial methods of technology assessment for 50 years. Following various academic studies and discussions based on numerous new technology response policies, coupled with the examination of trends and changes over time, academia and policymakers around the world have paid attention to the multilateral analysis of the impact of new technologies on future society. This study focuses on research changes such as the stage of forecasting factors that should consider the technology assessment of new technologies, despite differences between the development methods for the assessment between developed countries and South Korea. The analysis yielded three factors of technological understanding of awareness, professionalism, and gender characteristics, in addition to a previously identified factor. The three factors are then suggested as forecasting factors for new technology. The findings of this study provide both academic and policy evidence for technology assessment based on the country's Framework Act on Science and Technology.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2004.05b
• /
• pp.1408-1412
• /
• 2004

인구의 폭발적 증가, 산업화, 도시화의 급진적, 과학기숙의 발달 등으로 물 소비는 급증하는 반면, 이상기후현상으로 수자원의 절대량이 줄어 수자원의 양적인 문제와 하천 및 저수지의 수질오염에 대한 질적인 문제가 ,대두되고 있다. 하천의 수질현상 및 이송은 상당히 비선형적이고, 시간에 따라 변화하려, 실제로 수질의 예측은 유량의 변동, 오염물질의 이송 및 확산, 하천 구조물 등의 여러 요인에 의하여 상당히 어렵다고 알려져 왔다. 또한 한정된 수자원으로 하천의 수량과 수질목표를 동시에 달성하기 위해서는 물의 수요와 공급을 실시간으로 감시하면서 기상과 유출예측기술을 활용하여 용수의 수요와 공급을 예측하고 이를 토대로 수량과 수질을 고려한 물관리 운영시스템이 구축되어야 한다. 이를 위해 본 연구에서는 모형의 입${\cdot}$출력 구성을 자유롭게 변형할 수 있는 상태공간 모형과 신경망 모형을 이용하여 금강수계 주요 지점의 수질예측 모형을 구성하고 모형의 적용성을 파악한 후 예측력이 우수한 모형을 Web기반 모형의 수질예측 모듈의 기본모형으로 선정하고 Web 상에서 수질예측이 가능하도록 시스템을 개발하였다.

• Nuclear industry
• /
• v.16 no.8 s.162
• /
• pp.45-52
• /
• 1996

원전의 방사능 누출은 물론, 전국의 환경 방사선이나 기상 등을 수시로 종합 감시하여 즉각적으로 대응하는 방사능 방재 전산망이 본격 가동되었다. 과학기술처는 7월 31일 과천 청사 방사선 비상대책실에서 원전 사고 등 비상시에 방사능 누출 현황 등을 컴퓨터 화면으로 한눈에 보고 대응책을 마련할 수 있는 방사능방재대책 기술지원전산망 가동식을 가졌다. 이 전산망은 $\ulcorner$방사선 영향 평가 및 예측 전산화 시스템(CARE)$\lrcorner$을 중심으로 서울 등 전국 20개 지역의 환경방사선량을 표시해주는 환경방사능 감시망과 기상자료 수집망이 하나로 연결된 컴퓨터 통신망이다. 이의 운영 현황을 들어본다.

• Proceedings of the Korea Technical Association of the Pulp and Paper Industry Conference
• /
• 2007.11a
• /
• pp.13-19
• /
• 2007

In this research, what megatrends will be derived for the future society and what new packaging technology will be required in the future were researched. Megatrends were researched in the five major categories, demographical, social, consumer, packaging related science and technology, governmental regulations and law trend. The six new packaging technologies were predicted, Active/Passive packaging technology, Intelligent Communication packaging technology, Nanotechnology packaging technology, Universal Convenience packaging technology, Environmental Friendly packaging technology, and Package Design technology.

• Proceedings of the Korean Society of Community Living Science Conference
• /
• 2003.11a
• /
• pp.160-161
• /
• 2003

농촌생활 전반에 대한 생활수준 진단과 농촌주민들의 의식과 욕구를 정확하게 파악하여 미래 농촌생활의 모습을 예측하는데 있어서 종합적인 지표 및 표준화된 실태에 관한 통계자료는 필수적이라 할 수 있다 그러나 우리 나라에서 생산되고 있는 공식통계 중 농촌생활을 종합적으로 다루고 있는 자료는 미흡한 실정이다. 이러한 필요성에 의해 농촌생활연구소에서는 1994년 농촌생활지표를 인구 및 사회, 식생활, 건강생활, 주거 및 환경, 가정경제, 교육 및 교양, 여가생활, 가족생활 등 8개 부문을 기본틀로 하여 1994년, 1999년 두 차례에 걸쳐 $\boxDr$농촌생활지표$\boxUl$ 집을 발간한 바 있고, 2000년부터는 이들 지표 중 기존 통계자료 이용이 불가능한 82종의 지표항목에 대해 3년 주기로 직접조사를 통해서 자료를 생산하게 되었다. 여기서는 2002년에 조사한 주거 및 환경. 가정경제, 교육 및 교양부문 중, 교육 및 교양부문의 조사결과를 제시 하고자 한다.

• Journal of Korean Society of Disaster and Security
• /
• v.14 no.4
• /
• pp.17-27
• /
• 2021

Streamflow prediction is a very vital disaster mitigation approach for effective flood management and water resources planning. Lately, torrential rainfall caused by climate change has been reported to have increased globally, thereby causing enormous infrastructural loss, properties and lives. This study evaluates the contribution of rainfall to streamflow prediction in normal and peak rainfall scenarios, typical of the recent flood at Piney Resort in Vernon, Hickman County, Tennessee, United States. Daily streamflow, water level, and rainfall data for 20 years (2000-2019) from two USGS gage stations (03602500 upstream and 03599500 downstream) of the Piney River watershed were obtained, preprocesssed and fitted with Long short term memory (LSTM) model. Tensorflow and Keras machine learning frameworks were used with Python to predict streamflow values with a sequence size of 14 days, to determine whether the model could have predicted the flooding event in August 21, 2021. Model skill analysis showed that LSTM model with full data (water level, streamflow and rainfall) performed better than the Naive Model except some rainfall models, indicating that only rainfall is insufficient for streamflow prediction. The final LSTM model recorded optimal NSE and RMSE values of 0.68 and 13.84 m³/s and predicted peak flow with the lowest prediction error of 11.6%, indicating that the final model could have predicted the flood on August 24, 2021 given a peak rainfall scenario. Adequate knowledge of rainfall patterns will guide hydrologists and disaster prevention managers in designing efficient early warning systems and policies aimed at mitigating flood risks.

• Proceeding of EDISON Challenge
• /
• 2015.03a
• /
• pp.124-131
• /
• 2015

단백질의 구조를 예측하기 위해서 구조가 알려져 있는 단백질 중 진화적으로 유사한 단백질의 구조 정보를 이용하는 Template Based Modeling (TBM) 방법이 현재까지 가장 효과적으로 많이 사용되고 있다. 단백질의 삼차 구조를 이루는 단위 중에서도 고리 부분은 효소 활성 부위 또는 리간드 결합 부위 등으로 작용하여 단백질의 생물학적 기능에 연관되어 있다. 하지만 진화적으로 가까운 단백질이어도 고리 부분은 서열이 잘 보존되지 않아 충분한 구조 정보를 주지 못하고 TBM 방법으로 고리 구조까지 정확히 예측을 할 수 없다. 따라서 TBM 방법으로 예측한 구조의 고리 부분을 주형 정보에 의존하지 않고 다시 예측하여 전체 구조를 정밀화하는 과정이 중요하다. 이번 연구에서는 이를 위해 자유 에너지를 고려한 고리 구조 예측 방법을 적용하여 그 효과를 검증해보았다.

• Journal of Korea Technology Innovation Society
• /
• v.13 no.4
• /
• pp.617-637
• /
• 2010

As the impact of S&T on daily life increases, efforts to predict and anticipate the adverse effects of S&T development on human society and the natural environments are reinforced. In addition, public character of S&T demands wider participation of various stakeholders in R&D process. In response to these demands, Technology Assessment (TA) was introduced in the process of S&T policy formation. The Korean TA exercises were carried out 5 times since 2003 through 2008 by Korea Institute of S&T Evaluation and Planning (KISTEP), the necessity of which was incorporated in the S&T basic law. TA in Korea has been continuously upgraded in terms of organizational structure and procedure, but still in progress to take into account of problems exposed so far. In this paper, problems of TA in Korea are examined in terms of law, sponsor, management, and utilization. Suggestions for its improvement such as sophistication of methods and linking to national S&T planning are proposed.