• Journal of Korea Water Resources Association
• /
• v.56 no.12
• /
• pp.969-980
• /
• 2023

Since the 2000s, ensemble streamflow prediction (ESP) has been actively utilized in South Korea, primarily for hydrological forecasting purposes. Despite its notable success in hydrological forecasting, the original objective of enhancing water resources system management has been relatively overlooked. Consequently, this study aims to demonstrate the utility of ESP in water resources management by creating a simple hypothetical exercise for dam operators and applying it to actual multi-purpose dams in South Korea. The hypothetical exercise showed that even when the means of ESP are identical, different costs can result from varying standard deviations. Subsequently, using sampling stochastic dynamic programming (SSDP) and considering the capacity-inflow ratio (CIR), optimal release patterns were derived for Soyang Dam (CIR = 1.345) and Chungju Dam (CIR = 0.563) based on types W and P. For this analysis, Type W was defined with standard deviation equal to the mean inflow, and Type P with standard deviation ten times of the mean inflow. Simulated operations were conducted from 2020 to 2022 using the derived optimal releases. The results indicate that in the case of Dam Chungju, more aggressive optimal release patterns were derived under types with smaller standard deviations, and the simulated operations demonstrated satisfactory outcomes. Similarly, Soyang Dam exhibited similar results in terms of optimal release, but there was no significant difference in the simulation between types W and P due to its large CIR. Ultimately, this study highlights that even with the same mean values, the standard deviation of ESP impacts optimal release patterns and outcomes in simulation. Additionally, it underscores that systems with smaller CIRs are more sensitive to such uncertainties. Based on these findings, there is potential for improvements in South Korea's current operational practices, which rely solely on single representative values for water resources management.

• The Journal of the Korea Contents Association
• /
• v.19 no.11
• /
• pp.278-287
• /
• 2019

Spatial information extraction is to retrieve static and dynamic aspects in natural language text by explicitly marking spatial elements and their relational words. This paper proposes a deep learning approach for spatial information extraction for Korean language using a two-step bidirectional LSTM-CRF ensemble model. The integrated model of spatial element extraction and spatial relation attribute extraction is proposed too. An experiment with the Korean SpaceBank demonstrates the better efficiency of the proposed deep learning model than that of the previous CRF model, also showing that the proposed ensemble model performed better than the single model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.286-286
• /
• 2016

기후변화를 고려한 위한 미래 수자원 계획은 신뢰성 있는 수문기상인자의 산정을 통한 수자원 영향 평가 결과로 수립되는 것이 중요하다. 본 연구에서는 DHSVM모형과 TOPLATS모형에서 생산된 결과를 가지고 제약조건을 가지는 다중선형회귀 모형을 통하여 2012년-2014년 동안의 한반도 유역에 대한 수문기상인자를 산정하였다(Fig. 1). 다중선형회귀 모형은 하나의 종속변수의 변화를 설명하기 위하여 두 개 이상의 독립변수를 사용하는 모형으로 일반적으로 다중선형회귀 모형의 회귀 계수는 음의 값을 가질 수 있으므로 본 연구의 적용을 위하여 검정지점에 대하여 산정된 음의 회귀계수 값이 그대로 적용될 경우 적합하지 않으므로 회귀 계수에 제약조건을 부여하였다. 제한된 회귀 계수의 범위는 0-1사이를 가진다. 동적 다중선형 모형의 구성은 광릉 GCK, GDK 지점자료를 활용하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.433-438
• /
• 2003

Recently, some studies of a web-based information recommendation technique which provides users with the most necessary information through websites like a web-based shopping mall have been conducted vigorously. In most cases of web information recommendation techniques which rely on a user profile and a specific feedback from users, they require accurate and diverse profile information of users. However, in reality, it is quite difficult to acquire this related information. This paper is aimed to suggest an information prediction technique for a web information service without depending on the users'specific feedback and profile. To achieve this goal, this study is to design and implement a Dynamic Web Information Prediction System which can recommend the most useful and necessary information to users from a large volume of web data by designing and embodying Ensemble Support Vector Machine and hybrid SOM algorithm and eliminating the scarcity problem of web log data.

• Journal of Korea Water Resources Association
• /
• v.39 no.3 s.164
• /
• pp.187-198
• /
• 2006

Korea Water Resources Corporation(KOWACO) has developed the Integrated Real-time Water Management System(IRWMS) that calculates monthly optimal ending target storages by using Sampling Stochastic Dynamic Programming(SSDP) with Ensemble Streamflow Prediction(ESP) running on the $1^{st}$ day of each month. This system, however, has a shortcoming: it cannot reflect the hydrolmeteorologic variations in the middle of the month. To overcome this drawback, in this study updated ESP forecasts three times each month by using the observed precipitation series from the $1^{st}$ day of the month to the forecast day and the historical precipitation ensemble for the remaining days. The improved accuracy and its effect on the reservoir operations were quantified as a result. SSDP/ESP21 that reflects within-a-month hydrolmeteorologic states saves $1\;X\;10^6\;m^3$ in water shortage on average than SSDP/ESP01. In addition, the simulation result demonstrated that the effect of ESP accuracy on the reduction of water shortage became more important when the total runoff was low during the drawdown period.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.4
• /
• pp.579-586
• /
• 2018

Short-term prediction of travel speed has been widely studied using data-driven non-parametric techniques. There is, however, a lack of research on the prediction aimed at urban areas due to their complex dynamics stemming from traffic signals and intersections. The purpose of this study is to develop a hybrid approach combining ensemble empirical mode decomposition (EEMD) and artificial neural network (ANN) for predicting urban travel speed. The EEMD decomposes the time-series data of travel speed into intrinsic mode functions (IMFs) and residue. The decomposed IMFs represent local characteristics of time-scale components and they are predicted using an ANN, respectively. The IMFs can be predicted more accurately than their original travel speed since they mitigate the complexity of the original data such as non-linearity, non-stationarity, and oscillation. The predicted IMFs are summed up to represent the predicted travel speed. To evaluate the proposed method, the travel speed data from the dedicated short range communication (DSRC) in Daegu City are used. Performance evaluations are conducted targeting on the links that are particularly hard to predict. The results show the developed model has the mean absolute error rate of 10.41% in the normal condition and 25.35% in the break down for the 15-min-ahead prediction, respectively, and it outperforms the simple ANN model. The developed model contributes to the provision of the reliable traffic information in urban transportation management systems.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.11
• /
• pp.435-442
• /
• 2018

Outlier detection means to detect data samples that deviate significantly from the distribution of normal data. Most outlier detection methods calculate an outlier score that indicates the extent to which a data sample is out of normal state and determine it to be an outlier when its outlier score is above a given threshold. However, since the range of an outlier score is different for each data and the outliers exist at a smaller ratio than the normal data, it is very difficult to determine the threshold value for an outlier score. Further, in an actual situation, it is not easy to acquire data including a sufficient amount of outliers available for learning. In this paper, we propose a clustering-based outlier detection method by constructing a model representing a normal data region using only normal data and performing binary classification of outliers and normal data for new data samples. Then, by dividing the given normal data into chunks, and constructing a clustering model for each chunk, we expand it to the ensemble method combining the decision by the models and apply it to the streaming data with dynamic changes. Experimental results using real data and artificial data show high performance of the proposed method.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.45-55
• /
• 2021

This paper has proposed an algorithm that detecting for dense small vehicle in large image efficiently. It is consisted of two Ensemble Deep-Learning Network algorithms based on Coarse to Fine method. The system can detect vehicle exactly on selected sub image. In the Coarse step, it can make Voting Space using the result of various Deep-Learning Network individually. To select sub-region, it makes Voting Map by to combine each Voting Space. In the Fine step, the sub-region selected in the Coarse step is transferred to final Deep-Learning Network. The sub-region can be defined by using dynamic windows. In this paper, pre-defined mapping table has used to define dynamic windows for perspective road image. Identity judgment of vehicle moving on each sub-region is determined by closest center point of bottom of the detected vehicle's box information. And it is tracked by vehicle's box information on the continuous images. The proposed algorithm has evaluated for performance of detection and cost in real time using day and night images captured by CCTV on the road.

• Polymer(Korea)
• /
• v.35 no.6
• /
• pp.513-519
• /
• 2011

Molecular simulations via the molecular dynamics method have been carried out to investigate the dynamic collision properties of penetrable-sphere model fluids. The collision frequencies, the mean free paths, the angle distributions of the hard-type reflection and the soft-type penetration, and the effective packing fractions are computed over a wide range of the packing fraction ${\phi}$ and the repulsive energy ${\varepsilon}^*$. The soft-type collisions are dominated for lower repulsive energy systems, while the hardtype collisions for higher repulsive energy systems. Very interestingly, the ratio of the soft-type (or, the hard-type) collision frequency to the total collision frequency is directly related with the Boltzmann factor of acceptance (or rejection) probabilities in the canonical ensemble Monte Carlo calculations. Such dynamic collision properties are shown to be restricted for highly repulsive and dense systems of ${\varepsilon}^*{\geqq}3.0 $and ${\phi}{\geqq}0.7$, indicating the cluster forming structures in the penetrable-sphere model.