• Journal of Wetlands Research
• /
• v.21 no.spc
• /
• pp.61-68
• /
• 2019

Recently, climate indices represented by quantifying atmospheric-ocean circulation patterns have been widely used to predict hydrologic variables for considering long-term climate variability. Hydrologic forecasting models based on artificial neural networks have been developed to provide accurate and stable forecasting performance. Forecasts of hydrologic variables considering climate variability can be effectively used for long-term management of water resources and environmental preservation. Therefore, identifying significant indicators for hydrologic variables and applying forecasting models still remains as a challenge. In this study, we selected representative climate indices that have significant relationships with dam inflow time series in the Han-River basin, South Korea for applying the dam inflow forecasting model. For this purpose, the ensemble empirical mode decomposition(EEMD) method was used to identify a significance between dam inflow and climate indices and an artificial neural network(ANN) ensemble model was applied to overcome the limitation of a single ANN model. As a result, the forecasting performances showed that the mean correlation coefficient of the five dams in the training period is 0.88, and the test period is 0.68. It can be expected to come out various applications using the relationship between hydrologic variables and climate variability in South Korea.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.603-610
• /
• 2021

In this paper, we extract the user's power consumption patterns, and model the optimal consumption patterns by applying the user's environment and emotion. Based on the comparative analysis of these two patterns, we present an efficient power consumption method through changes in the user's power consumption behavior. To extract significant consumption patterns, vector standardization and binary data transformation methods are used, and learning about the ensemble's ensemble with k-means clustering is applied, and applying the support factor according to the value of k. The optimal power consumption pattern model is generated by applying forced and emotion-based control based on the learning results for ensemble aggregates with relatively low average consumption. Through experiments, we validate that it can be applied to a variety of windows through the number or size adjustment of clusters to enable forced and emotion-based control according to the user's intentions by identifying the correlation between the number of clusters and the consistency ratios.

• Journal of the Korean Geographical Society
• /
• v.49 no.5
• /
• pp.675-689
• /
• 2014

This study applied Ensemble Empirical Mode Decomposition(EEMD), a new methodology to define the timing of spring onset over the Republic of Korea and to examine its spatio-temporal change. Also this study identified the relationship between spring onet timing and some atmospheric variations, and figured out synoptic factors which affect the timing of spring onset. The averaged spring onset timing for the period of 1974-2011 was 11th, March in Republic of Korea. In general, the spring onset timing was later with higher latitude and altitude regions, and it was later in inland regions than in costal ones. The correlation analysis has been carried out to find out the factors which affect spring onset timing, and global annual mean temperature, Arctic Oscillation(AO), Siberian High had a significant correlation with spring onset timing. The multiple regression analysis was conducted with three indices which were related to spring onset timing, and the model explained 64.7%. As a result of multiple regression analysis, the effect of annual mean temperature was the greatest and that of AO was the second. To find out synoptic factors affecting spring onset timing, the synoptic analysis has been carried out. As a result the intensity of meridional circulation represented as the major factor affect spring onset timing.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.274-274
• /
• 2023

기후변화의 영향으로 겨울철 적설의 양상이 과거와는 많이 달라진 것으로 보인다. 따라서 미래의 적설이 어떤 확률로 발생할 것인지도 과거에 비해 많이 달라질 것으로 예상된다. 하지만 어떤 정도로 달라질 것인지는 정확하게 알 수가 없다. 본 연구에서는 이를 합리적으로 추정하기 위해 일본에서 수행한 대규모 기후 앙상블 모의실험 결과로 생성된 d4PDF(Data for Policy Decision Making for Future Change) 자료 중 적설과 기온 자료를 이용하여 일 최심적설심을 모의하고 연최대치계열을 작성하여 과거의 최심적설심 연최대치분포와 비교하여 분위사상법을 통해 모형의 오차를 보정한 후 미래 지구평균온도 상승 시의 기후모의 결과에 적용함으로써 지구평균온도 상승 정도에 따라 우리나라의 적설양상과 확률적설심이 어떻게 변화할 것인지 추정해 보았다. 연구의 결과는 미래 적설과 관련된 설계와 방재 목적에 참고적으로 활용될 수 있을 것이다.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.251-259
• /
• 2024

Fine particulate matter, especially PM2.5 with a diameter of less than 2.5 micrometers, poses significant health and economic risks. This study focuses on the Seoul region of South Korea, aiming to analyze PM2.5 data and trends from 2017 to 2022 and develop a mid-term prediction model for PM2.5 concentrations. Utilizing collected and produced air quality and weather data, reanalysis data, and numerical model prediction data, this research proposes an ensemble evaluation method capable of adapting to trend changes. The ensemble method proposed in this study demonstrated superior performance in predicting PM2.5 concentrations, outperforming existing models by an average F1 Score of approximately 42.16% in 2019, 58.92% in 2021, and 34.79% in 2022 for future 3 to 6-day predictions. The model maintains performance under changing environmental conditions, offering stable predictions and presenting a mid-term prediction model that extends beyond the capabilities of existing deep learning-based short-term PM2.5 forecasts.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.2
• /
• pp.15-25
• /
• 2024

For effective analysis of animal ecosystems, technology that can automatically identify the current status of animal habitats is crucial. Specifically, animal sound classification, which identifies species based on their sounds, is gaining great attention where video-based discrimination is impractical. Traditional studies have relied on a single deep learning model to classify animal sounds. However, sounds collected in outdoor settings often include substantial background noise, complicating the task for a single model. In addition, data imbalance among species may lead to biased model training. To address these challenges, in this paper, we propose an animal sound classification scheme that combines predictions from multiple models using Focal Loss, which adjusts penalties based on class data volume. Experiments on public datasets have demonstrated that our scheme can improve recall by up to 22.6% compared to an average of single models.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.12
• /
• pp.565-572
• /
• 2017

Traditional method for time series analysis, autoregressive integrated moving average (ARIMA) allows to mine significant patterns from the past observations using autocorrelation and to forecast future sequences. However, Korean baseball games do not have regular intervals to analyze relationship among the past attendance observations. To address this issue, we propose artificial neural network (ANN) based attendance prediction model using various measures including performance, team characteristics and social influences. We optimized ANNs using grid search to construct optimal model for regression problem. The evaluation shows that the optimal and ensemble model outperform the baseline model, linear regression model.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.15 no.1
• /
• pp.262-273
• /
• 1991

In the present study, the steady, incompressible, isothermal, developing flow in a 90.deg. rectangular cross sectional strongly curved duct with aspect ratio 1:1.5 and Reynolds number of 9.4*10$^{4}$ has been investigated. Measurements of components of mean velocities, pressures, and corresponding components of the Reynolds stress tensor are obtained with a hot-wire anemometer and pitot tube. In general, flow in a curved duct is characterized by the secondary vortices which are driven mainly by centrifugal force-radial pressure gradient imbalance, and the stress field stabilizing effects near the convex wall and destablizing effects close to the concave wall. It was found that the secondary mean velocities attain values up to 39% of the bulk velocity and are largely responsible for the convections of Reynolds stress in the cross stream plane. Therefor upstream of the bend the Reynolds stress are low. Corresponding to the small boundary layer thickness. At successive planes, large values of Reynolds stress were observed near the concave surface and the side wall.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.401-404
• /
• 2022

한국 문학이 세계로 뻗어나감에 따라 해외 시장에서 자리를 잡는 것이 중요해진 시점이다. 본 연구에서는 2016 년도부터 2020 년도까지 최근 5 년간 해외 출간된 도서들 중에서 굿셀러로 분류되는 누적 5 천부 이상 판매 여부를 예측하고자 했다. 굿셀러로 분류되는 도서는 전체 번역 도서 중 적은 비율을 차지하여 데이터 불균형이 발생하였으며, 본 연구에서는 SMOTE 기법과 앙상블 알고리즘을 적용하여 데이터 불균형 문제를 해결하였다. 그 결과, 데이터 클래스 비율이 1:1 에 가까울수록 성능 개선 효과가 나타났으며 LightGBM 모델이 99.83%의 AUC 값을 얻어 다른 앙상블 알고리즘에 비해 가장 좋은 예측 성능을 보임을 검증하였다. 또한 누적 5 천부 이상 판매 여부 예측에 있어 큰 영향을 미치는 변수로는 작가가 가장 중요한 요인으로 나타났으며 출간 국가, 그리고 평점 평균, 평점 참여자 수 같은 온라인 요인도 판매 예측에 유의미한 변수로 나타난 것을 확인할 수 있었다.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.153-166
• /
• 2021

A main goal of pharmacogenomics studies is to predict individual's drug responsiveness based on high dimensional genetic variables. Due to a large number of variables, feature selection is required in order to reduce the number of variables. The selected features are used to construct a predictive model using machine learning algorithms. In the present study, we applied several hybrid feature selection methods such as combinations of logistic regression, ReliefF, TurF, random forest, and LASSO to a next generation sequencing data set of 400 epilepsy patients. We then applied the selected features to machine learning methods including random forest, gradient boosting, and support vector machine as well as a stacking ensemble method. Our results showed that the stacking model with a hybrid feature selection of random forest and ReliefF performs better than with other combinations of approaches. Based on a 5-fold cross validation partition, the mean test accuracy value of the best model was 0.727 and the mean test AUC value of the best model was 0.761. It also appeared that the stacking models outperform than single machine learning predictive models when using the same selected features.