• Journal of Korea Water Resources Association
• /
• v.51 no.11
• /
• pp.1021-1029
• /
• 2018

A primary objective of this study is to develop a drought forecasting technique based on groundwater which can be exploit for water supply under drought stress. For this purpose, we explored the lagged relationships between regionalized SGI (standardized groundwater level index) and SPI (standardized precipitation index) in view of the drought propagation. A regional prediction model was constructed using a NARX (nonlinear autoregressive exogenous) artificial neural network model which can effectively capture nonlinear relationships with the lagged independent variable. During the training phase, model performance in terms of correlation coefficient was found to be satisfactory with the correlation coefficient over 0.7. Moreover, the model performance was described by root mean squared error (RMSE). It can be concluded that the proposed approach is able to provide a reliable SGI forecasts along with rainfall forecasts provided by the Korea Meteorological Administration.

• Journal of Wetlands Research
• /
• v.14 no.2
• /
• pp.243-254
• /
• 2012

Recently, the use of radar rainfall data that can help tracking of the development and movement of rainfall's spatial distribution is drawing much attention in hydrology. The reliability of existing radar rainfall compared to gauge rainfall data on the ground has not yet been confirmed and so we have difficulties to apply the radar rainfall in hydrology. The radar rainfall for the applications in hydrology are adjusted merging method derived from gage. This study uses the Mean-Field Bias (MFB) and Statistical Objective Analysis (SOA) as correction methods to create adjusted grid-based radar rainfall data which can represent the temporal and spatial distribution of rainfall. This study used a storm event occurred in August 2010 for the adjustment of radar rainfall. In addition, the grid-based distributed rainfall-runoff model (Vflo), which enables more detailed examinations of spatial flux changes in the basin rather than the lumped hydrological models, has been applied to Gamcheon river basin which is a tributary of Nakdong River located in south-eastern part of the Korean peninsular and the basin area is $1005km^2$. The simulated runoff was compared with the observed runoff in an attempt to evaluate the usability of radar rainfall data and the reliability of the correction methods. The error range of peak discharge using each correction method was within 20 percent and the efficiency of the model was between 60 and 80 percent. In particular, the SOA method showed better results than MFB method. Therefore, the SOA method could be used for the adjustment of grid-based radar rainfall and the adjusted radar rainfall can be used as an input data of rainfall-runoff models.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.6
• /
• pp.1873-1879
• /
• 2014

There are various methodologies to forecast the travel time using real-time data but the K-nearest neighborhood (KNN) method in general is regarded as the most one in forecasting when there are enough historical data. The objective of this study is to evaluate applicability of KNN method. In this study, real-time and historical data of toll collection system (TCS) traffic flow and the dedicated short range communication (DSRC) link travel time, and the historical path travel time data are used as input data for KNN approach. The proposed method investigates the path travel time which is the nearest to TCS traffic flow and DSRC link travel time from real-time and historical data, then it calculates the predicted path travel time using weight average method. The results show that accuracy increased when weighted value of DSRC link travel time increases. Moreover the trend of forecasted and real travel times are similar. In addition, the error in forecasted travel time could be further reduced when more historical data could be available in the future database.

• Progress in Medical Physics
• /
• v.17 no.1
• /
• pp.17-23
• /
• 2006

In Vivo dosimetry is a method to evaluate the radiotherapy; it is used to find the dosimetric and mechanical errors of radiotherapy unit. In this study, on-line In Vivo dosimetry was enabled by measuring the skin dose with MOSFET detectors attached to patient's skin during treatment. MOSFET dosimeters were found to be reproducible and independent on beam directions. MOSFET detectors were positioned on patient's skin underneath of the dose build-up material which was used to minimize dosimetric error. Delivered dose calculated by the plan verification function embedded in the radiotherapy treatment planning system (RTPs), was compared with measured data point by point. The dependency of MOSFET detector used in this study for energy and dose rate agrees with the specification provided by manufacturer within 2% error. Comparing the measured and the calculated point doses of each patient, discrepancy was within 5%. It was enabled to verify the IMRT by using MOSFET detector. However, skin dosimetry using conventional ion chamber and diode detector is limited to the simple radiotherapy.

• Journal of Intelligence and Information Systems
• /
• v.13 no.2
• /
• pp.55-68
• /
• 2007

DNA sequence alignment algorithms in computational molecular biology have been improved by diverse methods. In this paper, we proposed a DNA sequence alignment algorithm utilizing quality information and a fuzzy inference method utilizing characteristics of DNA sequence fragments and a fuzzy logic system in order to improve conventional DNA sequence alignment methods using DNA sequence quality information. In conventional algorithms, DNA sequence alignment scores were calculated by the global sequence alignment algorithm proposed by Needleman-Wunsch applying quality information of each DNA fragment. However, there may be errors in the process for calculating DNA sequence alignment scores in case of low quality of DNA fragment tips, because overall DNA sequence quality information are used. In the proposed method, exact DNA sequence alignment can be achieved in spite of low quality of DNA fragment tips by improvement of conventional algorithms using quality information. And also, mapping score parameters used to calculate DNA sequence alignment scores, are dynamically adjusted by the fuzzy logic system utilizing lengths of DNA fragments and frequencies of low quality DNA bases in the fragments. From the experiments by applying real genome data of NCBI (National Center for Biotechnology Information), we could see that the proposed method was more efficient than conventional algorithms using quality information in DNA sequence alignment.

• Journal of agriculture & life science
• /
• v.44 no.4
• /
• pp.69-77
• /
• 2010

Fuzzy control is widely used for improving temperature control performance as controlling ventilation in greenhouse because the technique can respond more flexibly to the outside air temperature and wind speed. By pre-studied PID and normal fuzzy control this study was performed to obtain the fundamental data that can be established in better greenhouse ventilation control method. The temperature control error by the simple fuzzy control was $1.2^{\circ}C$. The accumulated operating size of the window and the number of operating were 84% and 13, respectively. These showed equivalent control performance with pre-studied result that control error. The accumulated operating size of the window and the number of operating were 75% and 12, respectively. The proposed fuzzy technique was simple control logic method compared with step and PID control methods, but it showed equivalent performance. Therefore, the proposed simple fuzzy control method could be used in micro controller of small programmable memory size and many applications.

• Journal of the Korean GEO-environmental Society
• /
• v.12 no.11
• /
• pp.71-77
• /
• 2011

Recently, non-destructive stress measurement method using magnetic anisotropy sensor has been applied to the construction site such as steel bridges and steel pipes. In addition, steel rib used in the tunnel construction site was found to be possible to measure the stress by non-destructive method. In this study, steel loading experiments using magnetic anisotropy sensor developed in Japan and strain gauges were conducted to derive stress sensitivity curve for domestic steel SS400. Also, additional steel loading experiments and numerical analysis were performed for evaluation of applicability for non-destructive stress measurement method using magnetic anisotropy sensor. As a result of this study, stress sensitivity curves for domestic steel SS400 were derived using output voltage measured by magnetic anisotropy sensor and average of stress measured by strain gauges depending on the measurement location. And as a result of comparing additional steel loading experiments with the numerical analysis, error level of magnetic anisotropy sensor is around 20MPa. When considering the level of the yield stress(245MPa) of steel, in case of using magnetic anisotropy sensor in order to determine the stress status of steel, it has sufficient accuracy in engineering. Especially, magnetic anisotropy sensor can easily identify the current state of stress which considers residual stress at steel structure that stress measurement sensor is not installed, so we found that magnetic anisotropy sensor can be applied at maintenance of steel structure conveniently.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.1A
• /
• pp.45-52
• /
• 2009

In conventional structural design, deterministic optimization which satisfies codified constraints is performed to ensure safety and maximize economical efficiency. However, uncertainties are inevitable due to the stochastic nature of structural materials and applied loads. Thus, deterministic optimization without considering these uncertainties could lead to unreliable design. Recently, there has been much research in reliability-based design optimization (RBDO) taking into consideration both the reliability and optimization. RBDO involves the evaluation of probabilistic constraint that can be estimated using the RIA (Reliability Index Approach) and the PMA(Performance Measure Approach). It is generally known that PMA is more stable and efficient than RIA. Despite the significant advancement in PMA, RBDO still requires large computation time for large-scale applications. In this paper, A new reliability-based design optimization (RBDO) method is presented to achieve the more stable and efficient algorithm. The idea of the new method is to integrate a response surface method (RSM) with PMA. For the approximation of a limit state equation, the moving least squares (MLS) method is used. Through a mathematical example and ten-bar truss problem, the proposed method shows better convergence and efficiency than other approaches.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.489-498
• /
• 2023

Advancements in hardware performance and computing technology have facilitated the progress of climate prediction models to address climate change. The Korea Meteorological Administration employs the GloSea6 model with supercomputer technology for operational use. Various universities and research institutions utilize the Low-GloSea6 model, a low-resolution coupled model, on small to medium-scale servers for weather research. This paper presents an analysis using Intel VTune Profiler on Low-GloSea6 to facilitate smooth weather research on small to medium-scale servers. The tri_sor_dp_dp function of the atmospheric model, taking 1125.987 seconds of CPU time, is identified as a hotspot. Nonlinear regression models, a machine learning technique, are applied and compared to existing functions conducting numerical operations. The K-Nearest Neighbors regression model exhibits superior performance with MAE of 1.3637e-08 and SMAPE of 123.2707%. Additionally, the Light Gradient Boosting Machine regression model demonstrates the best performance with an RMSE of 2.8453e-08. Therefore, it is confirmed that applying a nonlinear regression model to the tri_sor_dp_dp function during the execution of Low-GloSea6 could be a viable alternative.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.6
• /
• pp.469-484
• /
• 2021

Rock mass classification results have a great influence on construction schedule and budget as well as tunnel stability in tunnel design. A total of 3,526 tunnels have been constructed in Korea and the associated techniques in tunnel design and construction have been continuously developed, however, not many studies have been performed on how to assess rock mass quality and grade more accurately. Thus, numerous cases show big differences in the results according to inspectors' experience and judgement. Hence, this study aims to suggest a more reliable rock mass classification (RMR) model using machine learning algorithms, which is surging in availability, through the analyses based on various rock and rock mass information collected from boring investigations. For this, 11 learning parameters (depth, rock type, RQD, electrical resistivity, UCS, V_p, V_s, Young's modulus, unit weight, Poisson's ratio, RMR) from 13 local tunnel cases were selected, 337 learning data sets as well as 60 test data sets were prepared, and 6 machine learning algorithms (DT, SVM, ANN, PCA & ANN, RF, XGBoost) were tested for various hyperparameters for each algorithm. The results show that the mean absolute errors in RMR value from five algorithms except Decision Tree were less than 8 and a Support Vector Machine model is the best model. The applicability of the model, established through this study, was confirmed and this prediction model can be applied for more reliable rock mass classification when additional various data is continuously cumulated.