• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.320-320
• /
• 2023

강우 데이터는 수문기상, 환경, 농업, 자연재해, 그리고 수자원 시스템 분야에서 가장 필수적인 기본 요소 중 하나이다. 또한 강우 데이터는 수문학적 분석에서 활용되는 필수 입력 자료 중 하나로 관측 데이터의 품질에 따라 수문 모형을 이용한 모의 결과물의 정확도가 결정된다고 할 수 있다. 따라서, 강우 관측소별로 강우 데이터의 품질을 어떻게 관리하느냐에 따라 수문 모형의 활용 범위 및 수자원 관리의 효율성이 결정될 수 있다. 강우의 시공간적 변동성은 수 많은 인자들과 직간접적으로 연계되어 있기 때문에 미계측 강우 자료에 대해 직접 관측이 아닌 수치 모형을 이용하여 강우의 발생과 강우량을 산정하는 것은 매우 복잡한 과제 중 하나이다. 현재 국내에서 운용되고 있는 강우 관측소의 경우에도 미계측 된 강우 데이터가 존재함으로써 강우 데이터의 활용에 제한이 생기는 경우가 있다. 따라서, 이러한 미계측 데이터의 추정 및 보완은 보다 효과적인 수재해 방지, 수자원 관리를 위한 필수 과제 중 하나이다. 일반적으로, 미계측 강우를 산정하기 위해서 Kriging, Thiessen, 등우선법, 그리고 역거리 관측법 등 다양한 수문학적 방법들이 적용되고 있다. 이러한 방법들은 산악효과나 강우 관측소의 분포 상태 등을 고려하지 못하기 때문에 측정하는 지역에 따라 강우 추정 오차가 커질 수 있다는 한계가 있다. 최근에는 데이터 관측 시스템과 빅데이터 기술의 발전과 활용 가능한 데이터의 양이 증가함에 따라 머신러닝을 활용한 사례가 증가하고 있다. 머신러닝은 데이터 사이의 관계를 기반으로 분류, 회귀, 그리고 예측 문제에 주로 사용되는 기법 중 하나이다. 따라서, 본 연구에서는 광주광역시 지역에 위치한 주요 강우 관측 지점들을 대상으로 미계측 된 시강우 데이터를 추정 및 복원하고자 한다. 여기서 데이터 추정 기술이란 미계측 강우의 발생 유무 및 강우량을 추정할 수 있는 기술을 의미한다. 이를 위해 대표적인 머신러닝 알고리즘인 인공신경망(Artificial Neural Network) 및 랜덤포레스트(Random Forest)를 적용하였다.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.3
• /
• pp.57-67
• /
• 2018

The ensemble is a unified approach used for getting better performance by using multiple algorithms in machine learning. In this paper, we introduce boosting and bagging, which have been widely used in ensemble techniques, and design a method using support vector regression, radial basis function network, Gaussian process, and multilayer perceptron. In addition, our experiment was performed by adding a recurrent neural network and MOHID numerical model. The drifter data used for our experimental verification consist of 683 observations in seven regions. The performance of our ensemble technique is verified by comparison with four algorithms each. As verification, mean absolute error was adapted. The presented methods are based on ensemble models using bagging, boosting, and machine learning. The error rate was calculated by assigning the equal weight value and different weight value to each unit model in ensemble. The ensemble model using machine learning showed 61.7% improvement compared to the average of four machine learning technique.

• Korean Journal of Environmental Agriculture
• /
• v.8 no.1
• /
• pp.37-46
• /
• 1989

A 2-dimensional pollutant transport phenomenon in shallow reservoirs was analyzed by using a finite element method. The Galerkin's weighted residual method, based on linear interpolation, was used and a triangle was adopted as an element. The two dimensional Stock's equation and the advection-diffusion equation integrated over depth were used as governing equations. Also the Newton-Raphson method was introduced to solve the non-linear terms of the equation. The results calculated by the model are in good agreement with the analytical solution for a simplified channel where a known solution is avaiable. An actual application of the model is attempted for Sapkyo Lake with a consideration of the influx of the Sapkyo Chun, the Muhan Chun and kogkyo Chun. Further refined research is needed to evaluate the water quality in the other reservoirs.

• Communications for Statistical Applications and Methods
• /
• v.15 no.1
• /
• pp.125-136
• /
• 2008

In many practical engineering design problems, the form of objective functions is not given explicitly in terms of design variables. Given the value of design variables, under this circumstance, the value of objective functions is obtained by real/computational experiments such as structural analysis, fluid mechanic analysis, thermodynamic analysis, and so on. These experiments are, in general, considerably expensive. In order to make the number of these experiments as few as possible, optimization is performed in parallel with predicting the form of objective functions. Response Surface Methods (RSM) are well known along this approach. This paper suggests to apply Support Vector Machines (SVM) for predicting the objective functions. One of most important tasks in this approach is to allocate sample data moderately in order to make the number of experiments as small as possible. It will be shown that the information of support vector can be used effectively to this aim. The effectiveness of our suggested method will be shown through numerical example which is well known in design of engineering.

• Journal of Korea Water Resources Association
• /
• v.36 no.6
• /
• pp.961-969
• /
• 2003

Formulation of quasi-dynamic wetness index was derived to predict the spatial and temporal distribution of the soil moisture. The algorithm of dynamic wetness index was developed through introducing the convolution integral with the rainfall input. The spatial and temporal behaviors of the wetness index of the Sulmachun Watershed was calculated using the digital elevation model(DEM) and the rainfall data for two years. The spatial distribution of the dynamic wetness index shows most dispersive feature of flow generation among the three assumptions of steady, quasi-dynamic and dynamic. The statistical distribution of the quasi-dynamic wetness index and the dynamic wetness index approximate to the steady state wetness index as the time step is increased. The dynamic wetness index shows mixed distribution of the normalized probability density function.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.3
• /
• pp.295-302
• /
• 2014

An internal gear pump is required to improve the flow rate and noise. Furthermore, such pumps are durable and small in size. In this study, equations of the rotor shape with multiple profiles (ellipse 1-involute-ellipse 2) were derived, and relevant performance parameters (pressure angle, irregularity, and specific sliding) of the internal gear pump to noise were predicted and compared. Rotor profiles and performance parameters were obtained by a prediction algorithm for theoretical analysis, and the effects between the design parameters and the performance parameters were analyzed. Based on the analysis results of the effects, an optimal design of the rotor profile was proposed, and a noise test of the prototype was performed to evaluate the reliability of the design.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.3 no.3
• /
• pp.21-32
• /
• 1999

A ground motion resulting from the destructive earthquakes can subject reinforced concrete members to very large forces. The reinforced concrete shear walls are designed as earthquake-resistant members of building structure in order to prevent severe damage due to the ground motions. The current research activities on seismic behavior of reinforced concrete member under ground motions have been limited to the shaking table test or equivalent static cyclic test and the obtained results have been summarized and proposed for the seismic design retrofit of structural columns or shear walls. The present study predicted the seismic response and failure behavior of reinforced concrete shear wall subjected to base acceleration using the finite element method. A decrease in strength and stiffness, yielding of reinforcing bar, and repetition of crack closing and opening due to seismic load with cyclic nature are accompanied by the crack which is necessarily expected to take place in concrete member. In this study the nonlinear material models for concrete and reinforcing bar based on biaxial stress field and algorithm of dynamic analysis were combined to construct the analytical program using the finite element method. The analytical seismic response and failure behaviors of reinforced concrete shear wall subjected to several base accelerations were compared with reliable experimental result.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.41 no.10
• /
• pp.905-913
• /
• 2017

In this work, a method of size optimization is proposed to maximize the natural frequency of a rod that consists of a hidden shape in one part and an exposed shape in the other. The frequency response function of a rod composed of two parts is predicted by using the frequency response functions of each of the parts instead of the shapes of the parts. The mass and stiffness matrices of the rod are obtained by using the mass and stiffness matrices of the equivalent vibration systems, which are obtained by applying the experimental modal analysis method to the frequency response functions of the parts. Through several numerical examples, the frequency response function obtained by using the proposed method is compared with that of a rod to validate the prediction method based on equivalent vibration systems. A size optimization problem is formulated for maximizing the first natural frequency of a combined rod, which is replaced with an equivalent vibration system, and a rod structure is optimized by using an optimization algorithm.

• Journal of Broadcast Engineering
• /
• v.22 no.3
• /
• pp.375-380
• /
• 2017

This paper has proposed a single image based fog degree quantification method by measuring both transmission and local contrast. The proposed method estimates the foggy expected regions from transmission, and then assesses the size of regions of which transmission values are foggy expected ones and the range of local contrast value on such regions. Compared with fog degree gauged by the scattering coefficient measurement sensor, the proposed method quantifies the fog degree with more than 95% accuracy for images containing various objects and environments. We also developed a technique that measures the local contrast values in process of measuring transmission values. So, the proposed method does not increase complexity compared to the existing transmission method.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.33 no.4
• /
• pp.1-6
• /
• 2005

The ability to predict radar return from flying vehicles becomes a critical technology issue in the development of stealth configurations. Toward developing a CEM code based on Maxwell's equations for analysis of RCS reduction schemes, an explicit upwind scheme suitable for multidisciplinary design is presented. The DFFT algorithm is utilized to convert the time-domain field values to the frequency-domain. A Green's function based on near field-to-far field transformation is also employed to calculate the bistatic RCS. To verify the numerical calculation the two-dimensional field around a perfectly conducting cylinder is considered. Finally results are obtained for the scattering electromagnetic field around an airfoil in order to illustrate the feasibility of applying CFD based methods to CEM.