• Journal of the Korean Statistical Society
• /
• 제31권2호
• /
• pp.213-228
• /
• 2002

Asymptotic properties of minimum distance estimators for the parameter involved for a class of stochastic partial differential equations are investigated following the techniques in Kutoyants and Pilibossian (1994).

• 한국물환경학회지
• /
• 제23권6호
• /
• pp.897-905
• /
• 2007

Approximately 70% of Korea is composed of forest areas. Especially 48% of agricultural field is practiced at highland areas over 400 m in elevation in Kangwon province. Over 90% of highland agricultural farming is located at Kangwon province. Runoff characteristics at the mountainous area such as Kangwon province are largely affected by steep slopes, thus runoff estimation considering field slopes needs to be utilized for accurate estimation of direct runoff. Although many methods for runoff estimation are available, the Soil Conservation Service (SCS), now Natural Resource Conservation Service (NRCS), Curve Number (CN)-based method is used in this study. The CN values were obtained from many plot-years dataset obtained from mid-west areas of the United States, where most of the areas have less than 5% in slopes. Thus, the CN method is not suitable for accurate runoff estimation where significant areas are over 5% in slopes. Therefore, the CN values were adjusted based on the average slopes (25.8% at Doam-dam watershed) depending on the 5-day Antecedent Moisture Condition (AMC). In this study, the CN-based Long-Term Hydrologic Impact Assessment (L-THIA) direct runoff estimation model used and the Web-based Hydrograph Analysis Tool (WHAT) was used for direct runoff separation from the stream flow data. The $R^2$ value was 0.65 and the Nash-Sutcliffe coefficient value was 0.60 when no slope adjustment was made in CN method. However, the $R^2$ value was 0.69 and the Nash-Sutcliffe value was 0.69 with slope adjustment. As shown in this study, it is strongly recommended the slope adjustment in the CN direct runoff estimation should be made for accurate direct runoff prediction using the CN-based L-THIA model when applied to steep mountainous areas.

• 대한기계학회논문집A
• /
• 제35권10호
• /
• pp.1291-1298
• /
• 2011

본 논문은 탄약, 미사일, 우주발사체 등과 같은 일회성(one-shot) 시스템의 가부반응데이터를 이용하여 신뢰도를 추정하는 새로운 방법을 제안한다. 제안한 방법은 모수 추정법을 기반으로 한다. 제안한 방법은 가부반응 데이터의 시간에 따른 고장 비율 감소를 고려하였으며 모수 추정법의 문제점을 극복할 수 있다. 기존 문헌에 공개된 7 가지 추정방법들과 제안한 방법과의 정확성을 비교하여 제안한 방법을 검증하였다. 정확성 비교 시, 다양한 샘플 수 변화를 고려하여 신뢰도 추정결과에 대한 SSE를 이용하였다. 정확성 비교 결과, 제안한 방법은 다른 방법에 비해 정확성이 높은 신뢰도 추정결과를 제공하였다.

• 한국농공학회논문집
• /
• 제53권2호
• /
• pp.19-26
• /
• 2011

SATEEC ArcView GIS system was developed using the Universal Soil Loss Equation (USLE) and sediment delivery ratio (SDR) modules. In addition, time-variant R and C modules and $R_5$ module were developed and integrated into the SATEEC system in recent years. The SATEEC ArcView GIS 2.1 system is a simple-to-use system which can estimate soil erosion and sediment yield spatially and temporarily using only USLE input data, DEM, and daily rainfall dataset. In this study, the SATEEC 2.1 system was used to evaluate the effects of USLE LS input data considering slope length segmentation on soil erosion and sediment yield estimation. Use of USLE LS with slope length segmentation due to roads in the watershed, soil erosion estimation decreased by 24.70 %. However, the estimated sediment yield using SATEEC GA-SDR matched measured sediment values in both scenarios (EI values of 0.650 and EI 0.651 w/o and w/flow segmentation). This is because the SATEEC GA-SDR module estimates lower SDR in case of greater soil erosion estimation (without flow length segmentation) and greater SDR in case of lower soil erosion estimation (with flow length segmentation). This indicates that the SATEEC soil erosion need to be estimated with care for accurate estimation of SDR at a watershed scale and for accurate evaluation of BMPs in the watershed.

• 한국농공학회지
• /
• 제38권1호
• /
• pp.90-97
• /
• 1996

In Korea, total sediment discharge of a river has been estimated simply by using certain sediment transport formulas including, among others, Einstein's formula. Those formular, however, are known not to be reliable enough for the result calculated by them to be used directly to river planning and management. Therefore, the study used the Modified Einstein Procedure to the estimation of total sediment discharge, because this method is reliable estimated by measurement. Here, measurement of sediment discharge used depth integrating method. The major results obtained from the study for estimation by depth integrating method of sediment discharge in Naeseong stream are as follow; 1 The sedeiment characteristics of Naeseong stream are; The distribution of sediment grain size shows that silt and clay are 55% and sand is 45%. and the bed load sediment grain size is constituted that sand contained with the grain size from O.062mm to 2.0mm is 80% 2. The sediment rating formulas derived from the regression analysis between the sediment discharge and flow discharge are; Seogpo-Gyo : Qs=$0.017 \times 10^{-4} Q^{2.352}$, where discharge is l0cms $0.074 \times 10^{-4} Q^{2.066}$, where discharge is l0cms

• 전자공학회논문지S
• /
• 제35S권6호
• /
• pp.119-126
• /
• 1998

본 논문에서는 인접블럭의 화소단위 움직임벡터와 반화소단위 움직임벡터 사이의 통계적인 특성과 반화소단위 움직임벡터의 공간적 상관성을 이용하여 새로운 반화소단위 움직임벡터 추정 기법들을 제안하였다. 즉, 화소단위 움직임벡터가 같은 인접블럭과는 반화소단위 움직임벡터도 같을 확률이 높다는 사실과 반화소위치들 간에도 서로 인접된 반화소위치간에는 높은 상관성을 지니고 있음을 실험을 통해 확인할 수 있었다. 이러한 성질을 이용한 제안한 방법들은 모의실험 결과 기존의 방법에 비해 아주 미약한 PSNR감소를 보이는 대신 비트 율 및 계산량을 효과적으로 줄일 수 있음을 보여주었다.

• Water Engineering Research
• /
• 제4권3호
• /
• pp.155-173
• /
• 2003

Parameters and quantiles of the 2-parameter generalized Pareto distribution were estimated using the methods of regular moments, modified moments, probability weighted moments, linear moments, maximum likelihood, and entropy for Monte Carlo-generated samples. The performance of these seven estimators was statistically compared, with the objective of identifying the most robust estimator. It was found that in general the methods of probability-weighted moments and L-moments performed better than the methods of maximum likelihood estimation, moments and entropy, especially for smaller values of the coefficient of variation and probability of exceedance.

• Communications for Statistical Applications and Methods
• /
• 제5권3호
• /
• pp.581-589
• /
• 1998

An algorithm is proposed for the $L_1$-estimation with linear equality and inequality constraints in linear regression model. The algorithm employs a linear scaling transformation to obtain the optimal solution of linear programming type problem. And a special scheme is used to maintain the feasibility of the updated solution at each iteration. The convergence of the proposed algorithm is proved. In addition, the updating and orthogonal decomposition techniques are employed to improve the computational efficiency and numerical stability.

• Communications for Statistical Applications and Methods
• /
• 제7권1호
• /
• pp.119-128
• /
• 2000

This paper proposes a method for detecting interactions in a two-way layout with one observation per cell. The identification of interactions in the model is not clear for they are confounding with error terms. The $L_1$-Estimation is robust with respect to a y-direction outlier in linear model so we are able to estimate main effects without affection of interactions, If an observation is classified as an outlier we conclude it contains an interaction. An empirical study compared with a classical method is performed.

• 대한기계학회논문집A
• /
• 제41권8호
• /
• pp.783-789
• /
• 2017

9축 IMMU기반의 3차원 자세추정에 있어 대표적인 정확성 저하요인은 가속도계 신호를 교란시키는 외부가속도와 지자기센서 신호와 관련된 자기교란이라는 두 가지 교란성분이다. 교란성분에 의한 영향을 최소화하기 위해 모델링기반 기법과 스위칭 기법이 제안되어 왔고, 이를 비교한 연구도 진행된 바 있다. 그러나 모델링기반 기법에서 모델링의 차이가 자세추정 성능에 미치는 영향에 대한 연구는 현재까지 발표된 바 없다. 본 논문은 교란성분 모델링이 IMMU기반 자세추정 정확성에 미치는 영향을 확인하기 위해, 모델링에 차이가 있는 최근 발표된 두 알고리즘을 다양한 시험조건에서 비교하였다. 이를 통해 교란성분 모델링의 차이는 진행잡음 공분산 행렬에 차이를 발생시키며, 이로 인해 자세추정 성능에 영향을 끼칠 수 있음을 확인할 수 있었다. 시험결과 두 알고리즘은 평균제곱근오차에서 롤 피치 요평균 $1.35^{\circ}$ 및 요성분 $3.63^{\circ}$의 차이를 발생시켰다.