• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.367-367
• /
• 2021

최근 기후변화로 인해 극한 강우 사상의 빈도가 잦아짐에 따라 수공 구조물의 안전성이 저해되거나 인명 및 재산 피해가 발생할 가능성이 커지고 있다. 기후변화에 따른 기상현상의 변화 추세를 파악하고 대비하기 위해 CMIP (Coupled Model Intercomparison Project Phase)의 GCM(General Circulation Model) 기상자료 산출물이 활발하게 이용되고 있다. 기후변화 시나리오는 홍수기 방재 대책 수립 등의 연구에도 적용되고 있으나, GCM에서 산출된 기상자료의 시간 간격은 24시간 혹은 3시간 정도로 시간적 해상도가 낮아 홍수 모형의 입력자료로 사용되기 어려운 형태를 가지고 있다. 따라서 기후변화 시나리오를 홍수 모의 등의 분야에 접목하기 위해서는 GCM 자료의 시간적 해상도를 1시간 이하로 낮춤으로써 시나리오 산출물이 홍수모형과 적절하게 연결될 수 있도록 해야 한다. MRC (Multiplicative Random Cascade) 모형은 국내외에서 예보강우의 시간 분해 및 일강우 데이터 분해 연구에 활용된 바 있으며 관측 강우에 대하여 분해 성능이 준수함이 확인되었다. 이에 본 연구에서는 MRC 모형을 활용하여 미래 기후변화 시나리오 산출물에 적용함으로써 MRC 모형이 일단위 및 3시간 단위 기후변화 자료의 시간 분해에 대해 적절한 성능을 수행하는지 여부를 분석하고, 기후변화 자료의 최소 시간 간격별 강우 분해 결과를 비교·분석하고자 하였다. 본 연구의 결과는 향후 기후변화 시나리오 기반 기상자료 시간 분해에 대한 MRC 모형의 적용성을 평가하는 기초 자료로 활용될 수 있을 것으로 사료된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.108-108
• /
• 2021

최근 국내에서는 기후변화로 인해 지역별·계절별 강수편차가 커지고 있으며, 이로 인해 상습가뭄지역(충남 서부, 경기 남부, 전라 등)의 가뭄 피해가 확대되는 등 수자원의 안정적인 공급을 위협하고 있다. 실제로 지난 2014-2015년 발생한 가뭄으로 인해 충남·경기지역 일부에서 수 개월간 생·공용수 공급이 제한된 바 있다. 기후변화에 대비한 국내 수자원의 추가 확보 및 효율적인 활용 방안의 필요성이 증가하고 있으나, 신규 수공시설물(댐, 저수지 등)을 건설하기 힘든 국내 개발 여건상 기존 수공시설물을 최대한 활용하기 위한 다양한 방안이 추진되고 있다. 기존 댐의 용수공급 능력을 재평가하거나, 댐·보 시설물의 연계운영을 통한 용수공급능력의 분석은 대부분 다목적댐 및 용수공급댐을 대상으로 수행되어 왔으며, 발전용댐을 활용한 용수공급능력 평가는 상대적으로 미흡한 실정이다. 따라서 최신화된 데이터 및 발전용댐 특성을 고려한 객관적인 평가방법을 통해 발전용댐의 용수공급능력을 새롭게 평가할 필요가 있다. 당초 수력발전이라는 단일목적으로 건설된 발전용댐은 다목적댐 대비 구조적 특성과 운영 측면에서 상이한 부분이 많아, 용수공급능력 평가 시 발전용댐의 특성을 고려할 필요가 있다. 따라서 본 연구에는 발전용댐의 구조 및 운영특성을 고려하여 발전용댐 별 유형(저류형 및 비저류형)을 구분하는 방안을 제안하고, 발전용댐 유형별 용수공급능력 산정 방안을 제시하였다. 제안한 기법은 북한강수계에 위치한 발전용댐에 적용하여 정량적인 용수공급능력을 평가하였다. 본 연구는 국내에서 연구가 미흡하였던 발전용댐을 대상으로 댐 이수능력을 검토하였으며, 향후 국가 수자원 계획 수립에 활용될 수 있을 것으로 기대된다.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.1
• /
• pp.93-102
• /
• 2023

Building supervision can be defined as a major task that involves managing and supervising the construction process to support the creation of high-quality results. To successfully perform supervision work, it is necessary to collect various information generated in uncertain field conditions, but today, supervision is performed based on documents such as reports, so there are limitations in collecting information. In fact, it has also been reported that the recent collapse of an apartment building in Korea was caused by limitations of information communication in th supervision work. Accordingly, this study analyzed the types of digital technologies that can be used to improve the efficiency of building supervision work, and presented the prioritized application of them. Priority application was quantitatively evaluated using analytic hierarchy process on data through a survey. It is expected that the results of this study can be used as basic data to set the roadmap of digital technology for building supervision in the future.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.378-378
• /
• 2022

상수도시스템의 과정 중 최종 단계인 급수단계에서 지역전반에 수질문제가 발생할 경우, 직간접적인 피해의 해결은 장기간 지속될 수 있다. 본 연구에서는 실시간 비정형정보의 빅데이터 분석을 통해 상수도시스템에서 수질사고 문제의 파급력과 2차 피해 등의 연결 관계 변화 추적을 위한 기초적 분석을 수행하였다. 과거 대규모 수질사고가 발생된 바 있는 인천광역시 유충발생 사고를 대상으로 뉴스 기사 웹크롤링 절차를 정립하고, 그 결과를 분석하였다. '인천 유충'이 최초 보도되었던 2020년 7월 13일 부터 이후 1년을 대상으로 네이버 통합검색에 의해 표출되는 뉴스기사를 웹크롤링하였으며, 프로그래밍을 통한 불용어 제거 및 관련성 검토를 통해 총 920건의 기사를 분석하였다. 수질사고의 전개양상에 따라 사고발생, 확산, 수습, 그리고 보상의 4단계로 임의 구분하여 분석하였다. 의미분석을 위한 토픽모델링 기법은 잠재 디리클레 할당(Latent Dirichlet Allocation, LDA) 방법을 적용하였으며, 긍부정 감정분석은 KNU 한국어 감성사전(KNU sentiment lexicon)을 활용하여 수행하였다. 토픽 모델링 결과, 사고 발생에서부터 확산, 수습, 보상의 단계에 맞춰 적절한 주제어의 조합에 따른 기사들이 도출되었으며, 단계별 긍부정 기사 비율역시 사고의 전개단계에 따라 적절히 나타남을 확인하였다. 제시된 수질사고 관련 비정형정보 분석 방법론과 결과는 과거 사고 사례 분석을 통한 검색 및 긍부정 키워드 확정, 키워드 발생 비율 변동(사고전과 후)에 따른 상황판단 기준설정 등에 활용이 가능하다.

• Journal of Korea Entertainment Industry Association
• /
• v.4 no.4
• /
• pp.72-76
• /
• 2010

Clinical nomogram is a graphical representation of numeric formula, constructed from clinical cases database of followed patients' treatment, which is used for medical predication. For a clinical nomogram to contribute patient care, it is required to accumulate as many as clinical cases and to extract medical prediction knowledge. It needs to be equipped with an effective method to build medical nomogram with high predication accuracy. It is desirable for medical nomogram to be accessible at patient care point. This paper proposes a medical nomogram service system architecture which takes into account the above-mentioned issues. The proposed system architecture includes a web-based database subsystem to maintain and keep track of clinical cases. On the periodic basis, a new clinical nomogram is reconstructed for the updated clinical database. For the convenient use of patient care practice environment, an app-based program is provided which makes prediction based on the most recent clinical nomogram constructed in the service system. The proposed method has been applied to a clinical nomogram service system development for recurrence and survival prediction in bladder cancer patients.

• Journal of Korea Entertainment Industry Association
• /
• v.5 no.1
• /
• pp.149-153
• /
• 2011

In this study, a configuration method for a cloud technology based VoD system through two different scenarios is proposed. The first scenario virtualizes DMC, content storages for each SO, and stream servers in the conventional VoD system in order to efficiently use the additionally required storage capacity and stream server. In the second scenario, it is proposed that cable broadcasting systems including VoD systems are to be changed as cloud in which the subscriber STB should have minimum programs and storage regions to connect networks, and the operating system and middle ware presented in the existing subscriber STB is moved to the cloud data center. In addition, the comparison of the application of the cloud technology for the cost of changing the existing system to STB and the cost of establishing a cloud VoD system is performed in order to analyze the cost reduction in broadcasting businesses based on the establishment of VoD systems.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.137-147
• /
• 2023

LiDAR is used in autonomous driving and various industrial fields to measure the size and distance of an object. In addition, the sensor also provides intensity images based on the amount of reflected light. This has a positive effect on sensor data processing by providing information on the shape of the object. LiDAR guarantees higher performance as the resolution increases but at an increased cost. These conditions also apply to LiDAR intensity images. Expensive equipment is essential to acquire high-resolution LiDAR intensity images. This study developed artificial intelligence to improve low-resolution LiDAR intensity images into high-resolution ones. Therefore, this study performed parameter analysis for the optimal super-resolution neural network model. The super-resolution algorithm was trained and verified using 2,500 LiDAR intensity images. As a result, the resolution of the intensity images were improved. These results can be applied to the autonomous driving field and help improve driving environment recognition and obstacle detection performance

• Journal of the Economic Geographical Society of Korea
• /
• v.26 no.3
• /
• pp.274-288
• /
• 2023

While the integration into global value chains has garnered attention as a rural development strategy, less is known about why some integrations are successful while others are not. This study draws on rent theory and on empirical examples from Jinju and Nonsan, the two biggest strawberry production regions in South Korea, to explore the mechanisms of Jinju creating and exclusively retaining monopoly rents from the exports. Based on five months of fieldwork and in-depth interviews with stakeholders, the findings show that a producer-driven chain integration into the overseas markets was possible in Jinju due to the natural barriers to entry based on an exportable variety, as well as the region's climate conditions being suitable to the variety. Moreover, the farmers have attempted to retain the monopoly rents and extra profits from public supports by associating producers. The horizontally associated farmers stabilized their positions by enhancing their bargaining power against exporters, as well as by managing access to the public supports by controlling memberships.

• Journal of the Korean Society of Radiology
• /
• v.81 no.6
• /
• pp.1305-1333
• /
• 2020

Deep learning has recently achieved remarkable results in the field of medical imaging. However, as a deep learning network becomes deeper to improve its performance, it becomes more difficult to interpret the processes within. This can especially be a critical problem in medical fields where diagnostic decisions are directly related to a patient's survival. In order to solve this, explainable artificial intelligence techniques are being widely studied, and an attention mechanism was developed as part of this approach. In this paper, attention techniques are divided into two types: post hoc attention, which aims to analyze a network that has already been trained, and trainable attention, which further improves network performance. Detailed comparisons of each method, examples of applications in medical imaging, and future perspectives will be covered.

• Journal of Korean Academy of Nursing
• /
• v.54 no.2
• /
• pp.193-210
• /
• 2024

Purpose: The objective of this study was to develop a predictive model for the sexual experiences of adolescents using the random forest method and to identify the "variable importance." Methods: The study utilized data from the 2019 to 2021 Korea Youth Risk Behavior Web-based Survey, which included 86,595 man and 80,504 woman participants. The number of independent variables stood at 44. SPSS was used to conduct Rao-Scott χ² tests and complex sample t-tests. Modeling was performed using the random forest algorithm in Python. Performance evaluation of each model included assessments of precision, recall, F1-score, receiver operating characteristics curve, and area under the curve calculations derived from the confusion matrix. Results: The prevalence of sexual experiences initially decreased during the COVID-19 pandemic, but later increased. "Variable importance" for predicting sexual experiences, ranked in the top six, included week and weekday sedentary time and internet usage time, followed by ease of cigarette purchase, age at first alcohol consumption, smoking initiation, breakfast consumption, and difficulty purchasing alcohol. Conclusion: Education and support programs for promoting adolescent sexual health, based on the top-ranking important variables, should be integrated with health behavior intervention programs addressing internet usage, smoking, and alcohol consumption. We recommend active utilization of the random forest analysis method to develop high-performance predictive models for effective disease prevention, treatment, and nursing care.