• 한국방재학회:학술대회논문집
• /
• 한국방재학회 2007년도 정기총회 및 학술발표대회
• /
• pp.315-318
• /
• 2007

In order to reduce the amount of damage from natural disasters, we needs prevention meteorological database classified into the cause of disaster, damage elements etc. For this, we have analyzed four data, such as Statistical yearbook of calamities issued by the National Emergency Management Agency and Annual Climatological Report issued by the Korea Meteorological Administration and Recently 10 years for natural disaster damage and Statistics Yearbook from the Ministry of Government Administration and Human affairs. Through the analysis of disaster data, we have selected input variables, such as causes and elements, occurrence frequencies, vulnerable areas of natural disaster, etc. In order to reduce damage from natural disaster, the prevention activities and forecasting based on meteorological parameters and damage datas are required. In addition, it is necessary to process meteorological information for disaster prevention activities. Through these procedure, we have established the foundation of database about natural disasters. This database will be used to assess the natural disasters and build risk model and natural disasters mitigation plan.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2009년도 학술발표회 초록집
• /
• pp.1524-1527
• /
• 2009

본 연구는 주요지천 홍수예측에 적용된 통계적 모형을 개선하여 예측 결과의 정확성 향상을 도모하는 데 목적이 있다. 중랑천, 탄천, 왕숙천 등 한강수계 주요 지천은 홍수예보 지점으로 유역면적이 작고 도달 시간이 짧아 기존의 대하천 홍수예보에 이용되고 있는 수문학적 홍수예측 모형을 적용하기에는 한계가 있다. 이러한 문제점을 해결하기 위해 주요 지천 홍수예측에 통계적 모형인 다중선형 회귀모형을 이용하는 방법이 제안되어 활용되었다. 본 연구에서는 지천홍수예측에 기 적용된 다중선형 회귀 모형의 다중공선성 문제를 해결하기 위해 독립변수를 조정하고, 10분 단위 관측 자료를 활용한 예측 결과를 얻기 위해 매개변수를 재산정하였다. 그 결과 기존 모형에 비해 적은 수의 독립변수와 재 산정된 매개변수를 이용한 통계적 모형으로 예측 수위의 오차를 줄일 수 있었다.

• 응용통계연구
• /
• 제24권2호
• /
• pp.307-313
• /
• 2011

본 연구에서는 인터넷 트래픽 자료를 예측하는데 사용되는 Holt-Winters, FARIMA, AR-GARCH 모형을 트래픽 예측에 적용하여 각 모형을 성능을 비교하고자 한다. 각 시계열 모형에 대해 소개하고, 트래픽 자료의 특성인 장기기억 특성을 설명하는데 적합한 모형을 알아보기 위해 실제 트래픽 자료에 적용하여 예측 성능을 비교하였다.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2009년도 추계학술대회 논문집
• /
• pp.383-386
• /
• 2009

Contract power conversion factor which is applied to estimate contract power of industrial customers is an important standard to calculate transformer capacity. This paper shows a reasonable contract power conversion factor, that was made by the systematic and statistical way considering actual conditions, such as investigated contract power and peak power for the last 5 years of each customer for industrial customers as to AMR system. In this dissertation, it is necessary to analyze the key features and general trend from the investigated data. It made an analysis of the feature parameters, such as average, standard deviation, median, maximum. minimum and thus it was carried the linear and nonlinear regression analysis. Therefore, this paper compared characteristics for a contract power conversion factor which is applied to calculate contract power with characteristics for a regression model for customers which maximum utilization factor of transformer is more than 60%.

• 응용통계연구
• /
• 제15권2호
• /
• pp.213-222
• /
• 2002

이 논문에서는 서울지역 기온에 대한 향후 48시간까지 3시간 간격 예보 모델 개발 결과이 다. 동적 변화패턴과 수치모델의 체계적 오차를 제거하기 위하여 동적 선형모형으로 적합하였으며 , 수치모델 예측치와 관측치를 입력 변수로 사용하였다. 동적 선형모형에 의한 예측모델은 수치모델의 체계적 오차를 성공적으로 제거하였으며, 예측 정확도를 향상시키고 있다.

• 유통과학연구
• /
• 제13권2호
• /
• pp.15-24
• /
• 2015

Purpose - Foreign exchange risk control is in an important component in the international supply chain management. This study shows the importance of the reference period in forecasting future exchange rates with a specific illustration of KIKO currency option contracts, and suggests feasible preventive measures. Research design, data, and methodology - Using monthly Won-Dollar exchange rate data for January 1995~July 2007, I evaluate the statistical characteristics of the exchange rate for two sub-periods; 1) a shorter period after the East Asian financial crisis and 2) a longer period including the financial crisis. The key instrument of analysis is the basic normal distribution theory. Results - The difference in the reference period could lead to an unexpected development in contract implementation and a consequent financial loss. We may avoid foreign exchange loss by using derivatives such as forwards or currency options. Conclusions - We should consider not only level values but also the volatilities of financial variables in making a binding financial contract. Appropriate measures may differ depending on the specific supply chain pattern. We may extend the study with surveys on actual risk measures.

• 한국농공학회논문집
• /
• 제48권2호
• /
• pp.27-35
• /
• 2006

Large dams are managed with operation standard and flood forecasting systems, while small dams do not have management method generally. Shortage of water resources and natural disasters due to drought and flood raised public concerns for management of small dams. Most of small dams are irrigation dams, which need diversified water uses. However, the lack of systematic management of small dams have caused serious water wastage and increased natural disasters. Storage management method and system were developed to solve these problems in small dams. The system was applied to Seongju dam for effective management. The storage management method was established considering hydrology simulation and statistical analysis using the system. This method can bring additional available water, even in the same conditions of the water demand and the supply conditions of watershed. It can improve the flood control capacity and water utilization efficiency by' the flexible operation of storage space.

• Ocean and Polar Research
• /
• 제37권1호
• /
• pp.1-9
• /
• 2015

An approach based on the combined use of a 2D shallow water model and analytical 1D long wave run-up theory is proposed which facilitates the forecasting of tsunami run-up heights in a more rapid way, compared with the statistical or empirical run-up ratio method or resorting to complicated coastal inundation models. Its application is advantageous for long-term tsunami predictions based on the modeling of many prognostic tsunami scenarios. The modeling of the Chilean tsunami on February 27, 2010 has been performed, and the estimations of run-up heights are found to be in good agreement with available observations.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 추계학술대회 논문집 전력기술부문
• /
• pp.35-38
• /
• 2005

This paper suggests the method that forecast Dynamic Line Rating (DLR). Thermal Overload Risk (TOR) of next time is forecasted based on current weather condition and DLR value by Monte Carlo Simulation (MCS). To model weather element of transmission line for MCS, we will propose the use of weather forecast system and statistical models that time series law is applied. Also, through case study, forecasted TOR probability confirmed can utilize by standard that decide DLR of next time. In short, proposed method may be used usefully to keep safety of transmission line and reliability of supply of electric Power by forecasting transmission capacity of next time.

• 응용통계연구
• /
• 제13권2호
• /
• pp.307-320
• /
• 2000

송이버섯 생산량과 기후인자와의 관계를 통계적으로 규명하기 위한 노력이 꾸준이 진행되어 왔다. 최근 박현 등(1998)은 송이버섯 생산량과 기후인자의 관계를 자기회귀모형을 이용하여 분석하였으나 예측력이 떨어지는 것으로 나타났다. 본 논문에서는 예측의 정확성을 높이기 위한 방법으로 송이버섯 생산이 있다는 조건을 이용한 조건부 자기 회귀모형을 제안하였다. 두 모형의 예측력을 비교한 결과 조건부 자기회귀모형이 더 우수한 것으로 나타났다.