• Journal of Korea Water Resources Association
• /
• v.55 no.7
• /
• pp.545-556
• /
• 2022

It is recommended to use long-term hydrometeorological data for more than the service life of the hydraulic structures and water resource planning. For the purpose of expanding rainfall data, stochastic simulation models, such as Modified Bartlett-Lewis Rectangular Pulse (BLRP) and Neyman-Scott Rectangular Pulse (NSRP) models, have been widely used. The optimal parameters of the model can be estimated by repeatedly comparing the statistical moments defined through a combination of parameters of the probability distribution in the optimization context. However, parameter estimation using relatively small observed rainfall statistics corresponds to an ill-posed problem, leading to an increase in uncertainty in the parameter estimation process. In addition, as shown in previous studies, extreme values are underestimated because objective functions are typically defined by the first and second statistical moments (i.e., mean and variance). In this regard, this study estimated the parameters of the NSRP model using the objective function with the third moment and compared it with the existing approach based on the first and second moments in terms of estimation of extreme rainfall. It was found that the first and second moments did not show a significant difference depending on whether or not the skewness was considered in the objective function. However, the proposed model showed significantly improved performance in terms of estimation of design rainfalls.

• Nuclear Engineering and Technology
• /
• v.52 no.7
• /
• pp.1429-1435
• /
• 2020

Applying an accurate parametric prediction model to identify abnormal or false pressurizer water levels (PWLs) is critical to the safe operation of marine pressurized water reactors (PWRs). Recently, deep-learning-based models have proved to be a powerful feature extractor to perform high-accuracy prediction. However, the effectiveness of models still suffers from two issues in PWL prediction: the correlations shifting over time between PWL and other feature parameters, and the example imbalance between fluctuation examples (minority) and stable examples (majority). To address these problems, we propose a cost-sensitive mechanism to facilitate the model to learn the feature representation of later examples and fluctuation examples. By weighting the standard mean square error loss with a cost-sensitive factor, we develop a Cost-Sensitive Long Short-Term Memory (CSLSTM) model to predict the PWL of PWRs. The overall performance of the CSLSTM is assessed by a variety of evaluation metrics with the experimental data collected from a marine PWR simulator. The comparisons with the Long Short-Term Memory (LSTM) model and the Support Vector Regression (SVR) model demonstrate the effectiveness of the CSLSTM.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.58 no.4
• /
• pp.9-19
• /
• 2016

The objective of this study was to evaluate the applicability of SWAT (Soil and Water Assessment Tool) model for runoff estimation in the Nam river dam watershed. Input data for the SWAT model were established using spatial data (land use, soil, digital elevation map) and weather data. The SWAT model was calibrated and validated using observed runoff data from 2003 to 2014 for three stations (Sancheong, Shinan, Changchon) within the study watershed. The $R^2$ (Determination Coefficient), RMSE (Root Mean Square Error), NSE (Nash-Sutcliffe efficiency coefficient), and RMAE (Relative Mean Absolute Error) were used to evaluate the model performance. Parameters for runoff calibration were selected based on user's manual and references and trial and error method was applied for parameter calibration. Calibration results showed that annual mean runoff were within ${\pm}5%$ error compared to observed. $R^2$ were ranged 0.64 ~ 0.75, RMSE were 2.51 ~ 4.97 mm/day, NSE were 0.48 ~ 0.65, and RMAE were 0.34 ~ 0.63 mm/day for daily runoff, respectively. The runoff comparison for three stations showed that annual runoff was higher in Changchon especially summer and winter seasons. The flow exceedance graph showed that Sancheong and Shinan stations were similar while Changchon was higher in entire fraction.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.2 no.3
• /
• pp.343-352
• /
• 1998

The use of DGPS enhances standalone GPS accuracy and removes common errors from two or more receivers viewing the same satellites. The design of DGPS system contains a precise reference point which is able to compute the common errors to update the pseudo range of users receivers. It should take a great time and cost to provide precise and sufficient accuracy of the reference point. That is, it is natural to measure the parameters from satellites with specific survey instrument system, and then obtain that by post processing. The purpose of the study is to examine the bounds of accuracy which resulted from RTCM correction data transmitted from a simply designed DGPS system. In the paper, We design and evaluate the DGPS system based m the surveyed reference point, and Sub-optimal no by a Standalone GPS as well. As a result of the study, it is shown that the designed system may be applied to the specific marine activity in civilian and military.

• Earthquakes and Structures
• /
• v.26 no.4
• /
• pp.311-326
• /
• 2024

Transmission tower structures are particularly susceptible to damage and even collapse under strong seismic ground motions. Conventional seismic analyses of transmission towers are usually performed by considering only ground motion uncertainty while ignoring structural uncertainty; consequently, the performance evaluation and failure prediction may be inaccurate. In this context, the present study numerically investigates the seismic responses and failure mechanism of transmission towers by considering multiple sources of uncertainty. To this end, an existing transmission tower is chosen, and the corresponding three-dimensional finite element model is created in ABAQUS software. Sensitivity analysis is carried out to identify the relative importance of the uncertain parameters in the seismic responses of transmission towers. The numerical results indicate that the impacts of the structural damping ratio, elastic modulus and yield strength on the seismic responses of the transmission tower are relatively large. Subsequently, a set of 20 uncertainty models are established based on random samples of various parameter combinations generated by the Latin hypercube sampling (LHS) method. An uncertainty analysis is performed for these uncertainty models to clarify the impacts of uncertain structural factors on the seismic responses and failure mechanism (ultimate bearing capacity and failure path). The numerical results show that structural uncertainty has a significant influence on the seismic responses and failure mechanism of transmission towers; different possible failure paths exist for the uncertainty models, whereas only one exists for the deterministic model, and the ultimate bearing capacity of transmission towers is more sensitive to the variation in material parameters than that in geometrical parameters. This research is expected to provide an in-depth understanding of the influence of structural uncertainty on the seismic demand assessment of transmission towers.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.18 no.8
• /
• pp.997-1004
• /
• 2007

High resolution synthetic aperture radar image could be sensitive to the various parameters of the payload, platform, and ground system. In this paper, a parameter based SAR simulator is presented for two-dimensional image formation and image quality analysis. Functional modules are implemented by Matalb code and GUI for the flexibility and expandability. Main function of this simulator includes the SAR input signal generation, range-doppler algorithm(RDA) based SAR image formation, and the SAR image quality analysis which is relevant to the SAR system design parameters. This simulator can effectively be used for the SAR image quality performance evaluation, which can be applicable to the airborne as well as spaceborne SAR system design and analysis.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.6
• /
• pp.79-88
• /
• 2011

In this paper, We propose real-time sound editing and playback systems which is based on Augmented Reality. The proposed system are composed with music maker which is based on AR maker and music board. By using music marker's contents, the proposed system selects the kinds of musical instruments and pre-defined midi track and by calculating the relative location of music marker on 2-dimensional plane, we set the spatial relative parameter in midi track. For performance evaluation, we check the jitter value of in various resolutions by using CAM which supports $1600{\pm}1200$ as the maximum resolution. As a result, when we set the configuration value of CAM as $860{\pm}600$ pixels and process two frames per minute, the success ratio of recognizing music markers and jitter values are accegnable. It can be utilized in the fields of alternative cmacine which is based on music and also be utilized in the educational aspects because child or elderly who don't know enough musical theory can easily handle it.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.3
• /
• pp.297-308
• /
• 2023

Displacement of structures is the most important parameter for safety and performance assessment and is measured to use for diagnosis and maintenance of bridges. Usually LVDT, Laser and GNSS are used for displacement measurement but these measurement instruments have problems in terms of field condition and cost. Therefore, in this study, displacements were evaluated using rotational angle measured by inclinometers and the proposed algorithm was experimentally verified. As the result, vertical displacements of cable supported bridges with traffic and temperature load were properly evaluated through the proposed algorithm. Therefore it is considered that the proposed algorithm can be used for displacement measurement by vehicle load test and long term displacement monitoring.

• Journal of the Korean Society for Railway
• /
• v.11 no.1
• /
• pp.54-60
• /
• 2008

In the trackbed design using elastic multilayer model, the stress-dependent resilient modulus $(E_R)$ is an important input parameter, that is, reflects substructure performance under repeated traffic loading. However, the evaluation method for resilient modulus using repeated loading triaxial test is not fully developed for practical purpose, because of costly equipment and the significantly fluctuated values depending on the testing equipment and laboratory personnel. The this study, the paper will present an indirect method to estimate the resilient modulus using dynamic properties. The resilient modulus of crushed stone, which is the typical material of sub-ballast, was calculated with the measured dynamic properties and the range of stress level of the sub-ballast, and approximated with the power model combined with bulk and deviatoric stresses. The resilient modulus of coarse grained material decreases with increasing deviatoric stress at a confining pressure, and increases with increasing bulk stress. Sandy soil (SM classified from Unified Soil Classification System) of subgrade was also evaluated and best fitted with the power model of deviatoric stress only.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1773-1793
• /
• 2023

Automated machine learning, often referred to as "AutoML," is the process of automating the time-consuming and iterative procedures that are associated with the building of machine learning models. There have been significant contributions in this area across a number of different stages of accomplishing a data-mining task, including model selection, hyper-parameter optimization, and preprocessing method selection. Among them, preprocessing method selection is a relatively new and fast growing research area. The current work is focused on the recommendation of preprocessing methods, i.e., feature subset selection (FSS) algorithms. One limitation in the existing studies regarding FSS algorithm recommendation is the use of a single learner for meta-modeling, which restricts its capabilities in the metamodeling. Moreover, the meta-modeling in the existing studies is typically based on a single group of data characterization measures (DCMs). Nonetheless, there are a number of complementary DCM groups, and their combination will allow them to leverage their diversity, resulting in improved meta-modeling. This study aims to address these limitations by proposing an architecture for preprocess method selection that uses ensemble learning for meta-modeling, namely AutoFE-Sel. To evaluate the proposed method, we performed an extensive experimental evaluation involving 8 FSS algorithms, 3 groups of DCMs, and 125 datasets. Results show that the proposed method achieves better performance compared to three baseline methods. The proposed architecture can also be easily extended to other preprocessing method selections, e.g., noise-filter selection and imbalance handling method selection.