• 무역학회지
• /
• 제48권2호
• /
• pp.27-43
• /
• 2023

해양 산업은 글로벌 경제 성장에 매우 중요한 역할을 하고 있다. 특히 벌크운임지수인 BDI는 글로벌 상품 가격과 매우 밀접한 상관 관계를 지니고 있기 때문에 BDI 예측 연구의 중요성이 증가하고 있다. 본연구에서는 글로벌 시장 상황 불안정성으로 인한 정확한 BDI 예측 어려움을 해결하고자 머신러닝 전략을 도입하였다. CNN과 LSTM의 이점을 결합한 예측 모델을 설정하였고, 모델 적합도를 위해 27년간의 일일 BDI 데이터를 수집하였다. 연구 결과, CNN을 통해 추출된 BDI 특징을 기반으로 LSTM이 BDI를 R² 값 94.7%로 정확하게 예측할 수 있었다. 본 연구는 해운 경제지표 연구 분야에서 새로운 머신 러닝 통합 접근법을 적용했을 뿐만 아니라 해운 관련기관과 금융 투자 분야의 위험 관리 의사결정에 대한 시사점을 제공한다는 점에서 그 의의가 있다.

• 정보보호학회논문지
• /
• 제27권6호
• /
• pp.1317-1330
• /
• 2017

서버 정보를 수집해 네트워크 지도를 구축하는 작업은 쉽게 발생하는 보안 사고들을 예방할 뿐만 아니라, 사이버전에 대비하고 적절한 정책을 제안하는데 방향을 제시해준다. 본 논문에서는 기존의 네트워크 스캐너인 Nmap과 ZMap을 분석하고, 네트워크 지도를 만들기 위해 서버 정보를 수집하는 기술로 배너 그래빙(banner grabbing)을 사용했다. 실시간으로 서버 정보를 수집하는 크롤링 도구를 구현하면서 정보 수집 대상이 받는 부하를 줄이기 위해 주소 생성 방식을 고안하고, 속도 향상을 위해 스레드를 나눴다. 구현한 크롤링 도구를 자체적으로 제시한 성능 평가 기준에 따라 기존 네트워크 스캐너를 사용하는 경우와 비교했다. 마지막으로, 크롤링 도구를 활용해 국내외 서버에서 정보를 수집한 DB를 바탕으로 국가별 위험 지표를 도출했으며 국가마다 차이는 있으나 수많은 사용자들이 위험한 공격에 노출되어 있는 실태를 확인했다.

• Journal of Korea Trade
• /
• 제25권3호
• /
• pp.21-47
• /
• 2021

Purpose - Offshoring has emerged as one of the major trends in international trade and has become one of the strategies for achieving competitiveness in the global market. In spite of this, the expected gains of offshoring can be offset by hidden costs and risks, such as those associated with the COVID-19 pandemic, the trade war between the USA and China, and the ongoing trade dispute between Korea and Japan. To obviate such business failure and prevent critical business blunders, offshoring strategies that efficiently consider both risk elements and potential wealth creation are urgently need. The first purpose of this study is to contribute to the development of more advanced offshoring strategies to help host countries select the best locations to manage supply chain risks and create unique value. The second purpose is to specifically analyze the current status of Korea and provide Korean companies with implications to be considered when deciding whether to offshore or re-shore. Design/methodology - A Network DEA model was applied to measure the comparative location efficiency of national competencies for offshoring strategy from perspectives of wealth creation opportunities (profitability and marketability) and supply chain risk management. The location efficiencies are compared among a total 70 countries selected from the Global Competitiveness Index (GCI) and globally attractive locations outlined by Kearney (2017). For the secondary analysis of efficiency, a t-test examining the nature of competitive advantage and the level of sophistication in production processes was implemented in three divisions. We then analyzed differences in offshoring performance in terms of the identified national traits. Moreover, Tobit regression analysis is conducted to investigate the correlation between value-added business activities and each divisional efficiency, seeking to determine how each degree of value-added business activity influences the increase in offshoring productivity. Findings - Regarding overall location efficiency for offshoring performance, only the USA and Italy were identified as being efficient as host countries for offshoring, under circumstances of advanced development, such as productivity and risk management. Korea ranks 13th among 70 countries. The determinants of national competitiveness depend on national traits (the nature of competitive advantage and business sophistication). Countries with labor/resource advantages and labor-intensive industries are more competitive in terms of marketability than others. In contrast, countries with strong technology-intensive industries benefit offshoring companies, particularly in the technology sector, with the added advantage of supply chain risk management. As the perception of a value chain is broader in a country, it can achieve both production sophistication and competitive advantages such as marketability and SCRM. Originality/value - Existing studies focus on offshoring effectiveness from a company perspective. This paper contributes to comparing country efficiency in producing core competencies related to an offshoring strategy and also segments countries into three performance-based considerations associated with the global offshoring market. It also details Korea's position as an offshoring location according to national efficiency and competency.

• International Journal of Computer Science & Network Security
• /
• 제22권1호
• /
• pp.69-76
• /
• 2022

At the current stage of globalization and European integration of Ukraine, the aspects related to the effective fight against corruption in the system of economic security of our country are receiving more and more attention, as they become a prerequisite for continuing reforms based on international funding. In order to consider this issue and solve this problem, the necessary step is to develop and implement real mechanisms of the system for detecting and preventing corrupt behavior, which are based on international anti-corruption standards. The leading component of this system is the management of corruption risks in the system of economic security in order to identify them and implement measures to reduce them. This study analyzes the corruption perception index in Ukraine in recent years, which showed a positive, albeit somewhat slow dynamics of its growth, indicating a gradual increase in overcoming corruption through the introduction of a number of anti-corruption measures and changes. It is proved that the current stage of socio-economic development of the country contributes to strengthening the processes of combating corruption and preventing corruption risks, creating an effective and efficient anti-corruption system of the state. The concept of "corruption" was studied, it was found that in the field of public administration it is considered from different positions and is closely related to the concept of "corruption risks". The essence and features of corruption risks are studied, the preconditions of their occurrence are formulated, the relationship between the causes of corruption risks and economic security in the field of public authority has been established. The system of corruption risk management is considered and its components are characterized. It is proposed to increase the effectiveness of anticorruption policy through the implementation of measures aimed at investigating the causes of corruption risks, as well as developed effective and effective means of reducing corruption risks within the system of economic security

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 추계학술대회 논문집 전력기술부문
• /
• pp.227-229
• /
• 2004

In a new competitive market environment, it is very important to determines how much power can be transferred through the network. It's known as Available Transfer Capability(ATC). This paper presents a technique to evaluate Reliability Assesment and the Available Transfer Capability of Haenam-Cheju HVDC transmission system using Well-being Method which is based on the probabilistic method. The system Well-being is categorized in terms of the system Healthy and Marginal in addition to the conventional Risk index. Haenam-Cheju HVDC system has been studied for the optimal ATC based in well-being categories.

• 문화기술의 융합
• /
• 제8권5호
• /
• pp.697-703
• /
• 2022

최근 Covid-19 및 불안한 국제정세로 인한 경기 침체로 많은 투자자들이 투자의 한 수단으로써 파생상품시장을 선택하고 있다. 하지만 파생상품시장은 주식시장에 비해 큰 위험성을 가지고 있으며, 시장 참여자들의 시장에 대한 연구 역시 부족한 실정이다. 최근 인공지능 분야의 발달로 파생상품시장에서도 기계학습이 많이 활용되고 있다. 본 논문은 해외선물에 분 단위로 거래하는 스캘핑 거래의 분석을 위해 기계학습 기법 중 하나인 강화학습을 적용하였다. 데이터 세트는 증권사에서 거래되는 해외선물 상품들 중 4개 상품을 선정해, 6개월간 1분봉 및 3분봉 데이터의 종가, 이동평균선 및 볼린저 밴드 지표들을 이용한 21개의 속성으로 구성하였다. 실험에는 DNN 인공신경망 모델과 강화학습 알고리즘인 DQN(Deep Q-Network), A2C(Advantage Actor Critic), A3C(Asynchronous A2C)를 사용하고, 학습 데이터 세트와 테스트 데이터 세트를 통해 학습 및 검증 하였다. 에이전트는 스캘핑을 위해 매수, 매도 중 하나의 행동을 선택하며, 행동 결과에 따른 포트폴리오 가치의 비율을 보상으로 한다. 실험 결과 에너지 섹터 상품(Heating Oil 및 Crude Oil)이 지수 섹터 상품(Mini Russell 2000 및 Hang Seng Index)에 비해 상대적으로 높은 누적 수익을 보여 주었다.

• 정보처리학회논문지D
• /
• 제14D권6호
• /
• pp.689-700
• /
• 2007

정보시스템 운영리스크를 최소화하고, 장애시간 동안의 영업기회 손실비용 규모를 줄이기 위해서는 장애의 예방과 사전준비가 필요하다. 그런데 장애가 발생할 경우, 대부분의 기업에서는 장애발생 직후에 대응과 복구 조치를 취하고 있다. 프로그램 개발자나 시스템운영자들은 과거의 경험과 직관에 의존하여 장애를 관리하고 있을 뿐, 장애를 체계적으로 관리하고 사전에 예방하는 사례를 찾아보기가 힘든 실정이다. 본 논문은 정보시스템 운영리스크의 관점에서, 디스크 장애예방을 위한 피해저감모델의 개발에 초점을 맞추었다. 연구모델은 디스크장치에서 정보시스템 운영리스크가 발생하는 위험원인, 그리고 이러한 원인들을 사전에 점검하는 점검주기, 점검에 필요한 운영규정으로 구성된다. 또한 정보시스템 부문의 하드웨어 장애요인 중에서 가장 크게 나타나고 있는 디스크 장애에 대하여 피해저감모델을 적용함으로써 활용 가능성을 보여 준다.

• IMMUNE NETWORK
• /
• 제22권2호
• /
• pp.17.1-17.14
• /
• 2022

We aimed to investigate associations of dietary diversity (DD) with gut microbial diversity and the development of hen's egg allergy (HEA) in infants. We enrolled 68 infants in a high-risk group and 32 infants in a control group based on a family history of allergic diseases. All infants were followed from birth until 12 months of age. We collected infant feeding data, and DD was defined using 3 measures: the World Health Organization definition of minimum DD, food group diversity, and food allergen diversity. Gut microbiome profiles and expression of cytokines were evaluated by bacterial 16S rRNA sequencing and real-time reverse transcriptase-polymerase chain reaction. High DD scores at 3 and 4 months were associated with a lower risk of developing HEA in the high-risk group, but not in the control group. In the high-risk group, high DD scores at 3, 4, and 5 months of age were associated with an increase in Chao1 index at 6 months. We found that the gene expression of IL-4, IL-5, IL-6, and IL-8 were higher among infants who had lower DD scores compared to those who had higher DD scores in high-risk infants. Additionally, high-risk infants with a higher FAD score at 5 months of age showed a reduced gene expression of IL-13. Increasing DD within 6 months of life may increase gut microbial diversity, and thus reduce the development of HEA in infants with a family history of allergic diseases.

• Korean Journal of Radiology
• /
• 제22권3호
• /
• pp.344-353
• /
• 2021

Objective: The mitotic count of gastrointestinal stromal tumors (GIST) is closely associated with the risk of planting and metastasis. The purpose of this study was to develop a predictive model for the mitotic index of local primary GIST, based on deep learning algorithm. Materials and Methods: Abdominal contrast-enhanced CT images of 148 pathologically confirmed GIST cases were retrospectively collected for the development of a deep learning classification algorithm. The areas of GIST masses on the CT images were retrospectively labelled by an experienced radiologist. The postoperative pathological mitotic count was considered as the gold standard (high mitotic count, > 5/50 high-power fields [HPFs]; low mitotic count, ≤ 5/50 HPFs). A binary classification model was trained on the basis of the VGG16 convolutional neural network, using the CT images with the training set (n = 108), validation set (n = 20), and the test set (n = 20). The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated at both, the image level and the patient level. The receiver operating characteristic curves were generated on the basis of the model prediction results and the area under curves (AUCs) were calculated. The risk categories of the tumors were predicted according to the Armed Forces Institute of Pathology criteria. Results: At the image level, the classification prediction results of the mitotic counts in the test cohort were as follows: sensitivity 85.7% (95% confidence interval [CI]: 0.834-0.877), specificity 67.5% (95% CI: 0.636-0.712), PPV 82.1% (95% CI: 0.797-0.843), NPV 73.0% (95% CI: 0.691-0.766), and AUC 0.771 (95% CI: 0.750-0.791). At the patient level, the classification prediction results in the test cohort were as follows: sensitivity 90.0% (95% CI: 0.541-0.995), specificity 70.0% (95% CI: 0.354-0.919), PPV 75.0% (95% CI: 0.428-0.933), NPV 87.5% (95% CI: 0.467-0.993), and AUC 0.800 (95% CI: 0.563-0.943). Conclusion: We developed and preliminarily verified the GIST mitotic count binary prediction model, based on the VGG convolutional neural network. The model displayed a good predictive performance.

• 한국수자원학회논문집
• /
• 제53권4호
• /
• pp.313-322
• /
• 2020

국토의 70% 이상이 산지인 우리나라의 경우 산지지역의 돌발호우로 인한 수재해의 위험이 상시 존재한다. 본 연구에서는 환경부 비슬산 강우레이더 관측 영역의 산지지역에 발생한 돌발성 호우 사례를 대상으로 레이더 기반 돌발성 호우 사전 예측 방법을 적용하여, 그 활용성을 살펴보았다. 비슬산 강우레이더의 3차원 레이더 반사도, 강우강도, 도플러 풍속을 이용하여, 산지지역에서 발생한 8개의 국지적 호우 사례를 선정한 후 적란운 대류세포의 조기탐지, 탐지된 대류세포의 자동 추적, 해당 대류세포가 발달하여 돌발성 호우를 유발할 수 있는 가능성을 판단하는 위험도 정보를 산출하였다. 사례적용 결과, 대기 중에 돌발호우로 발달할 수 있는 대류세포의 최초 탐지시점 및 위치, 소용돌이도 발생여부에 따라 판정된 위험도 수준 및 발생시점, 위치를 확인할 수 있었다. 특히, 지상강우관측망으로는 좁은 영역에 국지적으로 발달하는 호우를 탐지하는데 한계가 있음을 확인하였다. 또한, 위험도 정보를 획득한 시점에서 최대 강우강도가 발생할 때까지 최소 10분에서 최대 65분 정도의 시간을 확보함으로써 레이더 기반의 돌발성 호우 사전 예측기법은 산지지역에서 호우로 인한 산지홍수, 고립사고 방지를 위한 사전정보로 활용성이 있을 것으로 판단되었다.