• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1183-1193
• /
• 2021

Low flow affects various fields such as river water supply management and planning, and irrigation water. A sufficient period of flow data is required to calculate the Flow Duration Curve. However, in order to calculate the Flow Duration Curve, it is essential to secure flow data for more than 30 years. However, in the case of rivers below the national river unit, there is no long-term flow data or there are observed data missing for a certain period in the middle, so there is a limit to calculating the Flow Duration Curve for each river. In the past, statistical-based methods such as Multiple Regression Analysis and ARIMA models were used to predict sulfur in the unmeasured watershed, but recently, the demand for machine learning and deep learning models is increasing. Therefore, in this study, we present the DNN technique, which is a machine learning technique that fits the latest paradigm. The DNN technique is a method that compensates for the shortcomings of the ANN technique, such as difficult to find optimal parameter values in the learning process and slow learning time. Therefore, in this study, the Flow Duration Curve applicable to the unmeasured watershed is calculated using the DNN model. First, the factors affecting the Flow Duration Curve were collected and statistically significant variables were selected through multicollinearity analysis between the factors, and input data were built into the machine learning model. The effectiveness of machine learning techniques was reviewed through statistical verification.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4D
• /
• pp.635-647
• /
• 2006

Korean construction companies first advanced to the international markets in 1960's and so far have brought more than 4,900 projects which account for 193 billion dollars approximately. With the large increase of national employment and income being followed by the achievement, Korea's construction industry has made an enormous contribution to the improvement of domestic economy for the last 40 years. However, recently the increased risk in international markets as well as the sharpening competition with foreign companies promising in terms of advanced technologies and low labor cost have been driving Korean construction away from the market shares. According to ENR (Engineering News Record, 1994~2003), it is revealed that 15.1% of top 225 global contractors are suffering from loss in international construction markets. This phenomenon is largely due to the highly uncertain characteristics of international projects, which are inherently exposed to various and complicated risky situations. Furthermore, especially for Korean construction companies, it is often the case that the failure in an international construction project cannot be offset by even a sufficient number of successful domestic achievements. Therefore, not only the selective screening among the nominated projects which have strong possibility of collapse but the systematic strategies for controlling potential risk factors are also considered indispensable in international construction portfolio management. The purpose of this study is to first analyze the causal relationships of the profit-influencing variables and the project success, and develop the profitability forecasting model in international construction projects.

• Korean Journal of Soil Science and Fertilizer
• /
• v.42 no.6
• /
• pp.430-438
• /
• 2009

An attempt was made to establish the suitability classes of lands for the cultivation of ginseng(Panax ginseng C. A. Meyer). For this study, the relationships between various soil characteristics and ginseng yields were investigated on altogether 450 ginseng fields (150 sites in paddy and 300 sites in upland), across Kangwon, Kyunggi, Chungbug, Chungnam, Jonbug and Kyungbug Provinces, where ginseng is widely cultivated. In the paddy fields, most influential properties of soil on the ginseng yields was found to be the drainage class. Texture of surface soil and available soil depths affected the ginseng yields to some extents. However, the topography, slope, and the gravel content were found not to affect the ginseng yields. In the uplands, the texture of surface soil was most influential and the topography, slope, and occurrence depth of hard-pan were least influential on the performance of the crop. Making use of multiple regression, by SAS, the contribution of soil morphological and physical properties such as, topography, surface soil texture, drainage class, slope, available soil depth, gravel content, and appearance depth of hard-pan, for the suitability of land for ginseng cultivation was analyzed. Based on the results of above analysis, adding up all of the suitability indices, land suitability classes for ginseng cultivation were proposed. On top of this, taking the weather conditions into consideration, suitability of land for ginseng cultivation was established in paddy field and in uplands. As an example, maps showing the distribution of suitable land for ginseng cultivation were drawn, adopting the land suitability classes obtained through current study, soil map, climate map, and GIS information, for Eumsung County, Chungbug Province. Making use of the information on the land suitability for ginseng cultivation obtained from current study, the suitability of lands currently under cultivation of ginseng was investigated. The results indicate that 74.0% of them in paddy field and 88.3% in upland are "highly suitable" and "suitable".

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.2
• /
• pp.125-135
• /
• 2012

The FE model for shot peening often assume that shots impact vertically on the engineering parts to generate compressive residual stresses. However, the shots obliquely impact on the surface in actual peening. In this work, we propose a 3D finite element (FE) model for evaluation of residual stress under angled shot peening. Using the FE model for angled multi-impact, we examine the effects of factors such as impact angle, impact pattern and the number of shots. Plastic deformation of shot is also considered. To validate the model, we then compare the FE solution with experimental result by X-ray diffraction (XRD). The proposed model will be a base of 3D multi-impact FE model with diverse impact angles.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.127-134
• /
• 2007

There are many researches about the intelligent stock trading systems with the help of the advance of the artificial intelligence such as machine learning techniques, Though the establishment of the reasonable trading policy plays an important role in the performance of the trading systems most researches focused on the improvement of the predictability. Also some previous works, which treated the trading policy, treated the simplified versions dependent on the predictors in less systematic ways. In this paper, we propose the integrated multiple simulation' as a method of optimizing trading performance of stock trading systems. The propose method is adopted in the NXShell a development environment for neural network based stock trading systems. Under the proposed integrated multiple simulation', we simulate the multiple tradings for all combinations of the neural network's outputs and the trading policy parameters, evaluate the learning performance according to the various metrics and establish the optimal policy for a given prediction module based on the resulting performance. In the experiment, we present the trading policy comparison results using the stock value data from the KOSPI and KOSDAQ.

• Journal of the Korean GEO-environmental Society
• /
• v.3 no.4
• /
• pp.11-17
• /
• 2002

The purpose of this study is the prediction of pollutant loads into Seomjin river watershed using neural networks model. The pollutant loads into river watershed depend upon the water quantity of inflow from the upstream as well as the water quality of the inflow into the river. For the estimation of pollutants into river, a neural networks model which has the features of multi-layered structure and parallel multi-connections is used. The used water quality parameters are BOD, COD and SS into Seomjin river. The results of calibration are satisfactory, and proved the availability of a proposed neural networks model to estimate short-term water quality pollutants into river system.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.359-359
• /
• 2011

기존 수자원계획에 있어서 수문량 예측은 매우 제한적으로 활용되고 있는 실정으로서 최근 기후변화 및 이상기후로 기인하는 기상학적 불확실성 증가에 대해서 효과적으로 대응 하기가 어렵다. 본 연구에서는 기상인자를 활용한 수문변량 예측기법을 개발하고자 하며 국내에 수문자료가 충분한 지역에 대해서 모형의 적합성과 타당성을 평가하고자 한다. 대부분의 수문변량은 해수면온도, 해수면기압, 바람장 등 Large Scale의 기상학적 특성과 연관성을 가지고 있으며 선행시간을 가지고 수문순환에 영향을 주고 있다. 수문변량과 기상학적 변량사이에는 일반적으로 비선형 관계를 가지고 있는 것으로 알려지고 있으며 이러한 비선형 관계를 효과적으로 예측하기 위해서 본 연구에서는 비선형 예측모형을 개발 하고자 한다. 최근 비선형 예측모형에서 불확실성을 고려한 모형에 대한 연구가 활발히 진행되고 있으며 특히, 다중 모형을 사용한 Ensemble 개념의 예측모형 도입이 이루어지고 있다. 본 연구에서는 국내 다목적댐 유입량 및 강수량에 대해서 최적 기상변량을 도출하고 이를 활용한 비선형 Ensemble 예측모형을 개발하였다. 일반적인 선형 회귀분석 모형에 비해 기상현상과 수문현상에 비선형성을 효과적으로 재현할 수 있는 장점을 확인할 수 있었으며 이와 더불어 예측결과에 대한 불확실성을 제공함으로서 신뢰성 있는 수자원 계획을 위한 기초자료로서 활용이 가능할 것으로 판단된다.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.5 no.1
• /
• pp.11-18
• /
• 2002

Directional breaking waves are generated by the component wave focusing both in direction and frequency based on constant wave steepness and constant wave amplitude spectrum models. The generated breaking waves are classified in the incipient, single and multi breaking waves. The characteristics of directional breaking waves are investigated in terms of surface profile parameters of wave crest steepness and asymmetry. The evolution of breaking wave characteristics is analyzed in a view of focusing efficiency. It shows that the front steepness and vertical asymmetry play an important role in breaking process, while the crest rear steepness and horizontal asymmetry are nearly constant during the process. The superposition of directional components greatly enhances the focusing efficiency and it suggests that characteristics of directional breaking waves may significantly different from uni-directional ones.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.215-215
• /
• 2023

누수는 상수도시스템 내에서 발생할 수 있는 대표적인 비정상상황 중 하나이다. 누수는 발생 직후부터 경제적으로 직접적인 영향을 미치는 것과 함께 토사 내에서 유입되는 이물질 등으로 수질적인 문제 또한 발생할 수 있다. 이와 같은 이유로 누수는 발생에 대한 신속한 인지가 요구되며 이에 따른 신속한 복구가 필요하다. 하지만 기존의 데이터 기반 누수 탐사방법은 일반적으로 누수의 유무만을 인지하기 때문에 발생한 누수에 대한 규모의 정량적인 평가가 어려우며 이는 현재의 누수탐사 방법이 누수의 규모에 따른 복구 우선순위를 고려하기에는 부적절한 방법이라는 것을 의미한다. 따라서, 본 연구에서는 다중 누수시나리오 대해 누수 여부뿐만 아니라 누수 규모, 위치 등을 식별할 수 있는 수리해석 모델 기반 누수탐사 기법을 개발하였고, 이 기법을 활용하여 정량적인 누수량을 식별하여 누수 규모에 따른 누수복구 우선순위를 선정하는 프레임워크를 개발하였다. 이때, 누수복구 우선순위 선정 시 수리학적, 경제적, 사회적 인자 등을 고려하였으며, 각 인자 별 가중치를 통해 최종 복구 우선순위를 선정하였다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.4
• /
• pp.587-593
• /
• 2018

The current road traffic noise prediction programs of Korea, which are widely used, are based upon foreign prediction model. Thus, it is necessary to verify foreign prediction models to find out whether they are suitable for the domestic road traffic environment. In addition, an analysis and an in-depth study on the main factors should be conducted in advance as the influence factors on the occurrence of traffic noise vary for each prediction model. Therefore, this study examined the influence factors and the existing prediction models used to forecast road traffic noise. Also, analyzed their relationship with the factors influencing the noise generated by driving vehicles through multiple regression analysis using a prediction model, taking into consideration of the traffic environment and the road geometric structure. In addition, this study will apply experimental values to the existing road traffic noise prediction model (NIER, RLS-90) and the deducted road traffic noise prediction model. As a result, the order of the absolute value sum of the errors are NIER, RLS-90, model value. Through comparison and verification, developed models are to be analyzed for providing basic research results for future study on road traffic noise prediction modeling.