• 대한토목학회논문집
• /
• 제28권5B호
• /
• pp.485-493
• /
• 2008

한반도 영역을 대상으로 RDAPS모형의 수치예보자료, AWS의 관측강수, 상층기상관측(upper-air sounding)의 관측자료를 이용하여 권역별 강수발생확률을 예측할 수 있는 인공신경망 모형을 제시하였다. 사용된 자료의 기간은 2001년 7, 8월과 2002년 6월로 홍수기를 대상으로 하였다. 500/750/1000 hPa에서의 지위고도, 500-1000 hPa에서의 층후(thickness), 500 hPa에서의 X와 Y방향 바람성분, 750 hPa에서의 X와 Y방향 바람성분, 표면풍속, 500/750 hPa/표면에서의 온도, 평균해면기압, 3시간 누적 강수, AWS관측소에서 관측된 RDAPS모형 실행전의 6시간과 12시간동안의 누적강수, 가강수량, 상대습도등을 신경망의 예측인자로 사용하였다. 신경망의 구조는 3층 MLP(Multi Layer Perceptron)로 구성하여 역전파알고리즘(Back-propagation)을 학습방법으로 사용하였다. 신경망예측결과 한반도전체에 대한 예측성과의 개선은 H가 6.8%상승하였고, 특히 TS와 POD는 각각 99.2%와 148.1% 상승함으로서 강수예측에 대한 신경망모형이 효과적인 도구가 될 수 있음을 확인하였다. KSS 역시 92.8% 개선됨으로서 RDAPS 예측에 비하여 뚜렷이 개선된 결과를 보여주고 있다.

• 대한간호학회지
• /
• 제35권2호
• /
• pp.239-251
• /
• 2005

Purpose: This study was designed to construct a structural model for explaining mental health status in middle - aged women. Methods: The data was collected by self - reported questionnaires from 206 middle - aged women in Seoul. Data analysis was done with the SAS pc program for descriptive statistics and a PC - LISREL Program for finding the best fit model which assumes causal relationships among variables. Results: The overall fit of the hypothetical model to the data was good, but paths and variables of the model were modified by considering theoretical implications and statistical significances of parameter estimates. Thus it was modified by excluding 3 paths, The modified model showed was good fit to the data($x^2=177.55$, p=.00), GFI=0.908, AGFI=0.860, RMR=0.013, NFI=0.972, NNFI=0.982). Perceived stress, anger expression method, and self -esteem were found to have direct effects on mental health status in middle - aged women. These predictive variables of mental health status explained $66.6\%$ of the model. Conclusion: Programs to enhance mental health status in middle - aged women should include stress management skill, anger expression skill, and self -esteem enhancement skills to be effective.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2018년도 학술발표회
• /
• pp.150-150
• /
• 2018

The Numerical Weather Prediction (NWP) models provide information for weather forecasts. The highly nonlinear and complex interactions in the atmosphere are simplified in meteorological models through approximations and parameterization. Therefore, the simplifications may lead to biases and errors in model results. Although the models have improved over time, the biased outputs of these models are still a matter of concern in meteorological and hydrological studies. Thus, bias removal is an essential step prior to using outputs of atmospheric models. The main idea of statistical bias correction methods is to develop a statistical relationship between modeled and observed variables over the same historical period. The Model Output Statistics (MOS) would be desirable to better match the real time forecast data with observation records. Statistical post-processing methods relate model outputs to the observed values at the sites of interest. In this study three methods are used to remove the possible biases of the real-time outputs of the Weather Research and Forecast (WRF) model in Imjin basin (North and South Korea). The post-processing techniques include the Linear Regression (LR), Linear Scaling (LS) and Power Scaling (PS) methods. The MOS techniques used in this study include three main steps: preprocessing of the historical data in training set, development of the equations, and application of the equations for the validation set. The expected results show the accuracy improvement of the real-time forecast data before and after bias correction. The comparison of the different methods will clarify the best method for the purpose of the forecast skill enhancement in a real-time case study.

• 한국게임학회 논문지
• /
• 제22권1호
• /
• pp.33-42
• /
• 2022

온라인 게임에서 다른 플레이어와의 상호작용은 플레이어의 만족도에 영향을 미친다. 따라서, 비슷한 수준의 플레이어를 매치시켜 원활한 상호작용을 도모하는 것은 플레이어의 게임 경험을 위해 중요하다. 그러나, 게임의 최종승패로만 플레이어의 평가점수를 증감시키는 현재의 평가 방식으로는 신규 및 복귀 플레이어의 원활한 매칭이 불가능하다. 본 연구에서는 스타크래프트II의 리플레이를 활용하여 매치메이킹 개선을 위한 기계학습 활용방안을 제시한다. 매치메이킹의 기준이 되는 플레이어의 MMR 점수를 예측하는 기계학습 모델을 생성하고 성능을 평가하였다. 모델의 오차는 리그 평균 MMR 점수 범위의 40.4% 수준으로, 제안된 방식을 통해서 플레이어를 실력과 근접한 리그에 즉시 배치할 수 있음을 확인하였다. 또한, 결과에 대한 플레이어의 수용도를 높일 수 있도록 예측의 근거를 도출하는 방안도 제시되었다.

• 한국콘텐츠학회논문지
• /
• 제16권11호
• /
• pp.399-408
• /
• 2016

본 연구는 청소년들의 집단따돌림 유형에 따른 협동 및 공감기술과 학교생활적응도 간의 차이를 분석하기 위해 수행되었다. 이를 위해 수도권에 소재한 중 고등학교에서 213명의 청소년(중: 106명, 고: 107명)을 대상으로 설문조사하였다. 자료의 분석은 집단따돌림 유형을 분류하기 위해 2단계 군집분석을 사용하였고, 집단에 따른 예측변수의 설명은 다항로지스틱 회귀분석을 통해 분석하였다. 분석결과, 첫째, 집단따돌림 가해 및 피해경험은 협동 및 공감기술과 부적 상관이 있었으며, 학교생활적응도와도 부적 상관을 보였다. 둘째, 집단따돌림 가해군과 피해군은 협동기술의 부족과 관련되며, 가 피해군은 공감기술의 부족과 관계가 있었다. 셋째, 학교생활적응도에 협동과 공감기술은 유의한 예측변수로 나타났다. 이러한 연구결과를 고려할 때, 청소년들의 협동과 공감기술은 집단따돌림의 가해 및 피해경험을 줄이고, 학교생활적응에 긍정적 영향을 미치는 것으로 나타나 청소년들의 사회적 기술 훈련 프로그램의 필요성을 확인하고 시사점에 대해 논의하였다.

• 천문학회지
• /
• 제52권6호
• /
• pp.217-225
• /
• 2019

We apply a modified Convolutional Neural Network (CNN) model in conjunction with transfer learning to predict whether an active region (AR) would produce a ≥C-class or ≥M-class flare within the next 24 hours. We collect line-of-sight magnetogram samples of ARs provided by the SHARP from May 2010 to September 2018, which is a new data product from the HMI onboard the SDO. Based on these AR samples, we adopt the approach of shuffle-and-split cross-validation (CV) to build a database that includes 10 separate data sets. Each of the 10 data sets is segregated by NOAA AR number into a training and a testing data set. After training, validating, and testing our model, we compare the results with previous studies using predictive performance metrics, with a focus on the true skill statistic (TSS). The main results from this study are summarized as follows. First, to the best of our knowledge, this is the first time that the CNN model with transfer learning is used in solar physics to make binary class predictions for both ≥C-class and ≥M-class flares, without manually engineered features extracted from the observational data. Second, our model achieves relatively high scores of TSS = 0.640±0.075 and TSS = 0.526±0.052 for ≥M-class prediction and ≥C-class prediction, respectively, which is comparable to that of previous models. Third, our model also obtains quite good scores in five other metrics for both ≥C-class and ≥M-class flare prediction. Our results demonstrate that our modified CNN model with transfer learning is an effective method for flare forecasting with reasonable prediction performance.

• 대기
• /
• 제16권4호
• /
• pp.303-318
• /
• 2006

A parameterization of gravity wave drag induced by cumulus convection (GWDC) proposed by Chun and Baik is implemented in the KMA operational global NWP model (GDAPS), and effects of the GWDC on the forecast for July 2005 by GDAPS are investigated. The forecast result is compared with NCEP final analyses data (FNL) and model's own analysis data. Cloud-top gravity wave stresses are concentrated in the tropical region, and the resultant forcing by the GWDC is strong in the tropical upper troposphere and lower stratosphere. Nevertheless, the effect of the GWDC is strong in the mid- to high latitudes of Southern Hemisphere and high latitudes of Northern Hemisphere. By examining the effect of the GWDC on the amplitude of the geopotential height perturbation with zonal wavenumbers 1-3, it is found that impact of the GWDC is extended to the high latitudes through the change of planetary wave activity, which is maximum in the winter hemisphere. The GWDC reduces the amplitude of zonal wavenumber 1 but increases wavenumber 2 in the winter hemisphere. This change alleviates model biases in the zonal wind not only in the lower stratosphere where the GWDC is imposed, but also in the whole troposphere, especially in the mid- to high latitudes of Southern Hemisphere. By examining root mean square error, it is found that the GWDC parameterization improves GDAPS forecast skill in the Southern Hemisphere before 7 days and partially in the Northern Hemisphere after about 5 days.

• 대기
• /
• 제24권1호
• /
• pp.1-15
• /
• 2014

This study compared ensemble mean and probability forecasts of snow depth amount associated with winter storm over South Korea on 28 December 2012 at five operational forecast centers (CMA, ECMWF, NCEP, KMA, and UMKO). And cause of difference in predicted snow depth at each Ensemble Prediction System (EPS) was investigated by using THe Observing system Research and Predictability EXperiment (THORPEX) Interactive Grand Global Ensemble (TIGGE) data. This snowfall event occurred due to low pressure passing through South Sea of Korea. Amount of 6 hr accumulated snow depth was more than 10 cm over southern region of South Korea In this case study, ECMWF showed best prediction skill for the spatio-temporal distribution of snow depth. At first, ECMWF EPS has been consistently enhancing the indications present in ensemble mean snow depth forecasts from 7-day lead time. Secondly, its ensemble probabilities in excess of 2~5 cm/6 hour have been coincided with observation frequencies. And this snowfall case could be predicted from 5-day lead time by using 10-day lag ensemble mean 6 hr accumulated snow depth distribution. In addition, the cause of good performances at ECMWF EPS in predicted snow depth amounts was due to outstanding prediction ability of forming inversion layer with below $0^{\circ}C$ temperature in low level (below 850 hPa) according to $35^{\circ}N$ at 1-day lead time.

• 대기
• /
• 제25권4호
• /
• pp.669-683
• /
• 2015

In this study, we investigated the prediction skills of four multiple linear regression methods for monthly air temperature over South Korea. We used simulation results from four regional climate models (RegCM4, SNURCM, WRF, and YSURSM) driven by two boundary conditions (NCEP/DOE Reanalysis 2 and ERA-Interim). We selected 15 years (1989~2003) as the training period and the last 5 years (2004~2008) as validation period. The four regression methods used in this study are as follows: 1) Homogeneous Multiple linear Regression (HMR), 2) Homogeneous Multiple linear Regression constraining the regression coefficients to be nonnegative (HMR+), 3) non-homogeneous multiple linear regression (EMOS; Ensemble Model Output Statistics), 4) EMOS with positive coefficients (EMOS+). It is same method as the third method except for constraining the coefficients to be nonnegative. The four regression methods showed similar prediction skills for the monthly air temperature over South Korea. However, the prediction skills of regression methods which don't constrain regression coefficients to be nonnegative are clearly impacted by the existence of outliers. Among the four multiple linear regression methods, HMR+ and EMOS+ methods showed the best skill during the validation period. HMR+ and EMOS+ methods showed a very similar performance in terms of the MAE and RMSE. Therefore, we recommend the HMR+ as the best method because of ease of development and applications.

• 농업과학연구
• /
• 제47권3호
• /
• pp.471-483
• /
• 2020

Flood prediction is an important issue to prevent damages by flood inundation caused by increasing high-intensity rainfall with climate change. In recent years, machine learning algorithms have been receiving attention in many scientific fields including hydrology, water resources, natural hazards, etc. The performance of a machine learning algorithm was investigated to predict the water elevation of a river in this study. The aim of this study was to develop a new method for securing a large enough lead time for flood defenses by predicting river water elevation using the a long- short-term memory (LSTM) technique. The water elevation data at the Oisong gauging station were selected to evaluate its applicability. The test data were the water elevation data measured by K-water from 15 February 2013 to 26 August 2018, approximately 5 years 6 months, at 1 hour intervals. To investigate the predictability of the data in terms of the data characteristics and the lead time of the prediction data, the data were divided into the same interval data (group-A) and time average data (group-B) set. Next, the predictability was evaluated by constructing a total of 36 cases. Based on the results, group-A had a more stable water elevation prediction skill compared to group-B with a lead time from 1 to 6 h. Thus, the LSTM technique using only measured water elevation data can be used for securing the appropriate lead time for flood defense in a river.