• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.366-366
• /
• 2022

유역의 하천유량과 같은 수문 시계열을 모의 또는 예측하기 위한 수문 모델링에서 최근 기계 학습 방법을 활용한 연구가 활발하게 적용되고 있는 추세이다. 이러한 데이터 기반 모델링 접근법은 입출력 자료에서 관찰된 패턴을 학습하며, 특히, 장단기기억(Long Short-Term Memory, LSTM) 네트워크는 많은 연구에서 수문 시계열 예측에 대한 적용성이 검증되었으나, 장기간의 고품질 관측자료를 활용할 때 더 나은 예측성능을 보인다. 그러나 우리나라의 경우 장기간 관측된 고품질의 하천유량 자료를 확보하기 어려운 실정이다. 따라서 본 연구에서는 LSTM 네트워크의 학습 시 가용한 모든 유역의 자료를 통합하여 학습시켰을 때 하천유량 예측성능을 개선할 수 있는지 판단해보고자 하였다. 이를 위해, 우리나라 13개 댐 유역을 대상으로 대상 유역의 자료만을 학습한 모델의 예측성능과 모든 유역의 자료를 학습한 모델의 예측성능을 비교해 보았다. 학습은 2001년부터 2010년까지 기상자료(강우, 최저·최고·평균기온, 상대습도, 이슬점, 풍속, 잠재증발산)를 이용하였으며, 2011년부터 2020년에 대해 테스트 되었다. 다지점 통합학습을 통해 테스트 기간에 대해 예측된 각 유역의 일 하천유량의 KGE 중앙값이 0.74로 단일지점 학습을 통해 예측된 KGE(0.72)보다 다소 개선된 결과를 보여주었다. 다지점 통합학습이 하천유량 예측에 큰 개선을 달성하지는 못하였으며, 추가적인 가용 자료 확보와 LSTM 구성의 개선을 통해 추가적인 연구가 필요할 것으로 판단된다.

• Journal of Internet Computing and Services
• /
• v.14 no.3
• /
• pp.67-79
• /
• 2013

In wireless networks, efficient mobility management to support of mobile users is very important. Several mobility management schemeshave been proposed with the aim of reducing the signaling traffic of MN(Mobile Node). Among them, PMIPv6 (Proxy Mobile IPv6) is similar with host-based mobility management protocols but MN does not require any process for mobility. By introducing new mobile agent like MAG (Mobile Access Gateway) and LMA (Local Mobility Anchor), it provides IP mobility to MN. In this paper, we propose the analytical model to evaluate the mean signalingdelay and the mean bandwidth according to the type of MN mobility. As a result of mathematical analysis, MF-PMIP (Multicasting-based FastPMIP) outperforms compared to F-PMIP and PMIP in terms of parameters for the performance evaluation.

• Journal of the Korean Geographical Society
• /
• v.46 no.3
• /
• pp.319-330
• /
• 2011

In this study, a soil moisture estimation model was proposed using the ground observation data of soil moisture, precipitation, surface temperature, MODIS NDVI and artificial neural networks. The model was calibrated and verified on the Yongdam dam watershed which has reliable ground soil moisture networks. The test statistics of calibration sites, Jucheon, Bugui, Sangjeon, showed that the correlation coefficients between observations and estimations are about 0.9353 and RMSE is about 1.4957%. Also that of the verification site, Cheoncheon2, showed that the correlation coefficient is about 0.8215 and RMSE is about 4.2077%. The soil moisture estimation model was applied to estimate the spatial distribution of soil moisture in the Yongdam dam watershed and results showed improved spatial soil moisture distribution since the model used satellite information of NDVI and artificial neural networks which can represent the nonlinear relationships between data well. The model should be useful to estimate wide range soil moisture information.

• Journal of KIISE:Software and Applications
• /
• v.32 no.7
• /
• pp.625-635
• /
• 2005

In this paper, we propose a hybrid approach for segmenting the lungs efficiently and automatically in chest CT images. The proposed method consists of the following three steps. first, lungs and airways are extracted by two- and three-dimensional automatic seeded region growing and connected component labeling in low-resolution. Second, trachea and large airways are delineated from the lungs by two-dimensional morphological operations, and the left and right lungs are identified by connected component labeling in low-resolution. Third, smooth and accurate lung region borders are obtained by refinement based on image subtraction. In experiments, we evaluate our method in aspects of accuracy and efficiency using 10 chest CT images obtained from 5 patients. To evaluate the accuracy, we Present results comparing our automatic method to manually traced borders from radiologists. Experimental results show that proposed method which use connected component labeling in low-resolution reduce processing time by 31.4 seconds and maximum memory usage by 196.75 MB on average. Our method extracts lung surfaces efficiently and automatically without additional processing like hole-filling.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.12
• /
• pp.2343-2348
• /
• 2008

Ant algorithm is new meta heuristic for hard combinatorial optimization problem. It is a population based approach that uses exploitation of positive feedback as well as greedy search. It was first proposed for tackling the well known Traveling Salesman Problem. In this paper, we propose the improved $AS_{rank}$ algorithms. The original $AS_{rank}$ algorithm accomplishes a pheromone updating about only the paths which will be composed of the optimal path is higher, but, the paths which will be composed the optimal path is lower does not considered. In this paper, The proposed method evaporate the pheromone of the paths which will be composed of the optimal path is lowest(worst tour path), it is reducing the probability of the edges selection during next search cycle. Simulation results of proposed method show lower average search time and average iteration than original ACS.

• Economic Analysis
• /
• v.26 no.3
• /
• pp.48-70
• /
• 2020

Using data from the Household Income and Expenditure Survey over the period 1994-2016, we estimate the coefficient of relative prudence in order to capture precautionary saving motive. To do this, we adopt a cohort approach, where we transform such microdata into sample cohort means. Together with initial income involving liquidity constraint, we estimate the relative prudence derived from the Euler equation. The two-stage least-squares (2SLS) between estimate of it obtained from the cohort panel data analysis is too small for the existence of precautionary saving motive, as in previous studies, while the 2SLS random effects estimate is so reasonable. Moreover, the liquidity-constrained cohorts tend to be more sensitive to uncertainty, relative to the unconstrained ones.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.256-256
• /
• 2020

하천의 유출률은 하천의 경사, 연장, 강우특성 및 규모 등에 따라 크게 영향을 받으므로, 제주도의 지역별 고도별 토양 및 강우 특성과 독특한 지형에 따른 간헐하천의 유출특성을 고려할 때 관측에 의해 유출특성을 파악하는 것은 현실적으로 어렵다. 특히나 홍수시 관측되는 유량의 불확실성과 지역별·고도별 강우량의 편차를 고려한다면 강수대비 정확한 관측유출률의 산정 자체가 쉽지 않다. 이는 기존 관측된 유출률이 하천유역별로 대상기간별로 차이가 크게 나타나는 것을 통해서도 알 수 있다. 따라서 특정 지점에서의 몇 개의 강우사상에 대한 유출률이 아닌 다양한 사상과 지역적 특성을 고려한 유출특성을 파악하기 위해서는 모델링에 의한 접근법이 필요하다. 본 연구에서는 제주도 하천유역에서의 건천화 현상과 간헐적 유출특성을 모의하는데 최적화된 제주형 SWAT-K 모형을 기반으로 제주도 11개 하천유역(유역면적 30 ㎢ 이상)에 대한 유출특성을 분석하였다. 유출률을 중심으로 계절별, 지역별, 하천유역별 차이를 비교 분석함으로써 강우규모에 따른 유출 특성과 시·공간적 유출률 변화를 평가하였다. 1992~2013년 기간에 대해 분석한 결과 제주도 전역에 대한 연간 유출률은 13.3%~30.5% (평균 21.8%)로 나타났다. 하천유역별로는 천미천(31.6%), 가시천(31.1%), 화북천(29.3%), 창고천(27.4%), 의귀천(27.1%)의 유출률이 상대적으로 크게 나타났으며, 효돈천(18.9%)와 도순천(19.0%)은 상대적으로 낮은 것으로 분석되었다. 11개 하천유역에 대한 월별 평균 유출률은 강수량이 많은 8월에 가장 높은 유출률(26.1%)을 보였다.

• The Korean Journal of Applied Statistics
• /
• v.32 no.2
• /
• pp.173-185
• /
• 2019

Causal questions are prevalent in scientific research, for example, how effective a treatment was for preventing an infectious disease, how much a policy increased utility, or which advertisement would give the highest click rate for a given customer. Causal inference theory in statistics interprets those questions as inferring the effect of a given intervention (treatment or policy) in the data generating process. Causal inference has been used in medicine, public health, and economics; in addition, it has received recent attention as a tool for data-driven decision making processes. Many recent datasets are observational, rather than experimental, which makes the causal inference theory more complex. This review introduces key concepts and recent trends of statistical causal inference in observational studies. We first introduce the Neyman-Rubin's potential outcome framework to formularize from causal questions to average treatment effects as well as discuss popular methods to estimate treatment effects such as propensity score approaches and regression approaches. For recent trends, we briefly discuss (1) conditional (heterogeneous) treatment effects and machine learning-based approaches, (2) curse of dimensionality on the estimation of treatment effect and its remedies, and (3) Pearl's structural causal model to deal with more complex causal relationships and its connection to the Neyman-Rubin's potential outcome model.

• The Korean Journal of Pesticide Science
• /
• v.17 no.4
• /
• pp.249-255
• /
• 2013

The objective of this study was to investigate the exposure assessment of Korean consumers to edifenphos and tricyclazole in cattle product fed the rice straw, using a probabilistic approach. We used tricyclazole and edifenphos residue data in rice straw reported by National Academy of Agricultural Science (NAAS) for the 1998, 1999, 2001 and 2010 monitoring study and National Agricultural Products Quality Management Service (NAQS) for 2009 monitoring study. The mean exposures of edifenphos and tricyclazole for all of Korean consumers were 0.027% and 0.0006% of ADI and $99%^{th}$ percentile exposures were 0.034% and 0.0007% of ADI respectively. The group of 1~6 years old consumers has the lowest exposure of edifenphos and tricyclazole. The group of 19~29 years old consumers has the highest exposure of edifenphos and tricyclazole.

• Tuberculosis and Respiratory Diseases
• /
• v.61 no.4
• /
• pp.347-355
• /
• 2006

Background: Pneumonia is the most common cause of death among infectious diseases with community-acquired pneumonia being the sixth leading cause of death in the USA. In Korea, several studies have evaluated the prognosis of community-acquired pneumonia with a limited number of patients and risk factors. This study, evaluated all the possible risk factors (including the pneumonia severity index; PSI) in for the community-acquired pneumonia patients admitted to a referral hospital. Methods: The medical records of patients admitted to the Chung-Aug University Yongsan Hospital between January 2002 and January 2005 for community-acquired pneumonia were reviewed retrospectively. The demographic data, comorbidity, radiographic findings and laboratory results which might influence the prognosis of pneumonia were analyzed. Results: Among 179 patients admitted for community-acquired pneumonia, 29 patients died (mortality 16%). The risk factors for mortality in the comorbidity category were congestive heart failure and a myocardial infarction. The laboratory data, showed that albumin, LDH, total cholesterol, HDL, PT, aPTT, hemoglobin and blood urea nitrogen (BUN) were related to the prognosis. For the pneumonia severity index, the mortality rate increased in a step-wise manner from class I through class V. Conclusions: Comorbidities such as congestive heart failure and myocardial infarction as well as the albumin, LDH, total cholesterol, HDL cholestreol, prothrombin time, activated partial thrombotin time, hemoglobin and blood urea nitrogen(BUN) are important risk factors for mortality in patients with community-acquired pneumonia. PSI is a valuable index for evaluating the prognosis of community-acquired pneumonia.