• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.1
• /
• pp.79-89
• /
• 2022

Soil moisture is significantly related to crop growth and plays an important role in irrigation management. To predict soil moisture, various process-based model has been developed and used in the world. Various models (Land surface model) may have different performance depending on the model parameters and structures that causes the different model output for the same modeling condition. In this study, the three land surface models (Noah Land Surface Model, Soil Water Atmosphere Plant, Community Land Model) were used to compare the model performance (soil moisture prediction) and develop the multi-model simulation. At first, the genetic algorithm was used to estimate the optimal soil parameters for each model, and the parameters were used to predict soil moisture in the study area. Then, we used the multi-model approach based on Bayesian model averaging (BMA). The results derived from this approach showed a better match to the measurements than the results from the original single land surface model. In addition, identifying the strengths and weaknesses of the single model and utilizing multi-model methods can help to increase the accuracy of soil moisture prediction.

• Journal of ILASS-Korea
• /
• v.27 no.2
• /
• pp.57-65
• /
• 2022

The purpose of this study is to use machine learning to build a model capable of predicting the flash boiling spray characteristics. In this study, the flash boiling spray was visualized using Shadowgraph visualization technology, and then the spray image was processed with MATLAB to obtain quantitative data of spray characteristics. The experimental conditions were used as input, and the spray characteristics were used as output to train the machine learning model. For the machine learning model, the XGB (extreme gradient boosting) algorithm was used. Finally, the performance of machine learning model was evaluated using R² and RMSE (root mean square error). In order to have enough data to train the machine learning model, this study used 12 injectors with different design parameters, and set various fuel temperatures and ambient pressures, resulting in about 12,000 data. By comparing the performance of the model with different amounts of training data, it was found that the number of training data must reach at least 7,000 before the model can show optimal performance. The model showed different prediction performances for different spray characteristics. Compared with the upstream spray angle and the downstream spray angle, the model had the best prediction performance for the spray tip penetration. In addition, the prediction performance of the model showed a relatively poor trend in the initial stage of injection and the final stage of injection. The model performance is expired to be further enhanced by optimizing the hyper-parameters input into the model.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.1-13
• /
• 2021

In this study, a time series analysis technique was applied to calibrate and predict traffic data for various purposes, such as planning, design, maintenance, and research. Existing algorithms have limitations in application to data such as traffic data because they show strong periodicity and seasonality or irregular data. To overcome and supplement these limitations, we applied the SARIMA model, an analytical technique that combines the autocorrelation model, the Seasonal Auto Regressive(SAR), and the seasonal Moving Average(SMA). According to the analysis, traffic volume prediction using the SARIMA(4,1,3)(4,0,3) 12 model, which is the optimal parameter combination, showed excellent performance of 85% on average. In addition to traffic data, this study is considered to be of great value in that it can contribute significantly to traffic correction and forecast improvement in the event of missing traffic data, and is also applicable to a variety of time series data recently collected.

• The Korean Journal of Applied Statistics
• /
• v.35 no.5
• /
• pp.593-601
• /
• 2022

We call "fruad" the cases that are not frequently occurring but cause significant losses. Fraud detection is commonly encountered in various applications, including wafer production in the semiconductor industry. It is not trivial to directly extend the standard binary classification methods to the fraud detection context because the misclassification cost is much higher than the normal class. In this article, we propose the functional fraud detection support vector machine (F²DSVM) that extends the fraud detection support vector machine (FDSVM) to handle functional covariates. The proposed method seeks a classifier for a function predictor that achieves optimal performance while achieving the desired sensitivity level. F²DSVM, like the conventional SVM, has piece-wise linear solution paths, allowing us to develop an efficient algorithm to recover entire solution paths, resulting in significantly improved computational efficiency. Finally, we apply the proposed F²DSVM to the defective wafer detection problem and assess its potential applicability.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.2
• /
• pp.379-384
• /
• 2022

In a wireless sensor network, a large number of sensor nodes are deployed in an environment where direct access is difficult. It is difficult to supply power, such as replacing the battery or recharging it. It is very important to use the energy with the sensor node. Therefore, an important consideration to increase the lifetime of the network is to minimize the energy consumption of each sensor node. If the energy of the wireless sensor node is exhausted and discharged, it cannot function as a sensor node. Therefore, it is a method proposed in various protocols to minimize the energy consumption of nodes and maintain the network for a long time. We consider the center point and residual energy of the cluster, and the plot point and K-means (WSN suggests optimal clustering). We want to evaluate the performance of the KOCED protocol. We compare protocols to which the K-means algorithm, one of the latest machine learning methods, is applied, and present performance evaluation factors.

• Earthquakes and Structures
• /
• v.23 no.1
• /
• pp.35-57
• /
• 2022

This article presents a computationally efficient framework for multi-objective seismic design optimization of steel moment-resisting frame (MRF) structures based on the nonlinear dynamic analysis procedure. This framework employs the uniform damage distribution philosophy to minimize the weight (initial cost) of the structure at different levels of damage. The preliminary framework was recently proposed by the authors based on the single excitation and the nonlinear static (pushover) analysis procedure, in which the effects of record-to-record variability as well as higher-order vibration modes were neglected. The present study investigates the reliability of the previous framework by extending the proposed algorithm using the nonlinear dynamic design procedure (optimization under multiple ground motions). Three benchmark structures, including 4-, 8-, and 12-story steel MRFs, representing the behavior of low-, mid-, and high-rise buildings, are utilized to evaluate the proposed framework. The total weight of the structure and the maximum inter-story drift ratio (IDRmax) resulting from the average response of the structure to a set of seven ground motion records are considered as two conflicting objectives for the optimization problem and are simultaneously minimized. The results of this study indicate that the optimization under several ground motions leads to almost similar outcomes in terms of optimization objectives to those are obtained from optimization under pushover analysis. However, investigation of optimal designs under a suite of 22 earthquake records reveals that the damage distribution in buildings designed by the nonlinear dynamic-based procedure is closer to the uniform distribution (desired target during the optimization process) compared to those designed according to the pushover procedure.

• Journal of Korean Society of Disaster and Security
• /
• v.15 no.2
• /
• pp.45-56
• /
• 2022

The countermeasure for the shortage of water during dry season and drought period has not been considered with return flowrate in detail. In this study, the outflow of STP was predicted through a data-based machine learning model, LSTM. As the first step, outflow, inflow, precipitation and water elevation were utilized as input data, and the distribution of variance was additionally considered to improve the accuracy of the prediction. When considering the variability of the outflow data, the residual between the observed value and the distribution was assumed to be in the form of a complex trigonometric function and presented in the form of the optimal distribution of the outflow along with the theoretical probability distribution. It was apparently found that the degree of error was reduced when compared to the case not considering where the variance distribution. Therefore, it is expected that the outflow prediction model constructed in this study can be used as basic data for establishing an efficient river management system as more accurate prediction is possible.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.2
• /
• pp.1-6
• /
• 2023

The purpose of this study is to research and develop so that users who are gradually progressing in the popularization of smartphones and the calculation of agricultural quality can use more active and flexible applications than existing application fields. People use event management applications to remember what they need to do, and maps applications to get to their appointments on time. You will need to build a glue-delivered application that leverages the Maps API to be able to recommend the glove's path for events so that the user can use the application temporarily. By comparing and analyzing currently used calendar, map, and schedule applications, several Open Maps APIs were compared to supplement the weaknesses and develop applications that converge the strengths. The results of application development by applying the optimal algorithm for recommending traffic routes according to time and place for the schedule registered by the user are described.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.314-314
• /
• 2023

Extreme climate events can have a large impact on human life by hampering social, environmental, and economic development. Global circulation models (GCMs) are the widely used numerical models to understand the anticipated future climate change. However, different GCMs can project different future climates due to structural differences, varying initial boundary conditions and assumptions about the physical phenomena. The multi-model ensemble (MME) approach can improve the uncertainties associated with the different GCM outcomes. In this study, a comprehensive rating metric was used to select the best-performing GCMs out of 11 CMIP5 and 13 CMIP6 GCMs, according to their skills in terms of four temporal and five spatial performance indices, in replicating the 21 extreme climate indices during the baseline (1975-2017) in South Korea. The MME data were derived by averaging the simulations from all selected GCMs and three top-ranked GCMs. The random forest (RF) algorithm was also used to derive the MME data from the three top-ranked GCMs. The RF-derived MME data of the three top-ranked GCMs showed the highest performance in simulating the baseline extreme climate which was subsequently used to project the future extreme climate indices under both the representative concentration pathway (RCP) and the socioeconomic concentration pathway scenarios (SSP). The extreme cold and warming indices had declining and increasing trends, respectively, and most extreme precipitation indices had increasing trends over the period 2031-2100. Compared to all scenarios, RCP8.5 showed drastic changes in future extreme climate indices. The coasts in the east, south and west had stronger warming than the rest of the country, while mountain areas in the north experienced more extreme cold. While extreme cold climatology gradually declined from north to south, extreme warming climatology continuously grew from coastal to inland and northern mountainous regions. The results showed that the socially, environmentally and agriculturally important regions of South Korea were at increased risk of facing the detrimental impacts of extreme climatology.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.497-497
• /
• 2023

정수장에서 소독 및 여과 처리가 완료된 깨끗한 물은 배급수시설로 전달되나, 실제로 관의 노후화, 갑작스러운 유향 변동, 특정 구역의 관 내 정체 시간에 따른 Water Age 상승 등 여러 요인으로 인해 실제 수용가에는 안전하지 않은 용수가 공급될 가능성이 있으며, 이에 따라 적절한 위치에서 지속적인 감시를 통한 조기 발견 및 조치가 필요하다. 상수도 시설기준(2010)에 배수시설의 주요 지점 혹은 관 말단 등 필요에 따라 적절한 위치에 수질 계측기를 설치할 수 있도록 제시되어 있으나, 계측기 설치 위치나 개수에 대한 기준이 모호한 실정이다. 모든 구역에 수질계측기를 설치하여 감시하는 것이 이상적이지만, 현실적으로는 지자체 환경 및 경제적인 한계가 있어 주요 위치에 설치하는 것이 바람직하다. 본 연구에서는 대표적인 수리해석 모형인 EPANET을 사용하여 대상 관망의 노후도, 유속, 유향변동 등의 영향인자를 바탕으로 수질사고가 발생할 확률이 높은 관을 위험관으로 선정하고, 선정된 위험관을 대상으로 최단 경로와 Cost를 산출할 수 있는 Floyd Warshall Algorithm을 이용하여 각 Node(수용가)간 물이 이동할 때의 최소 도달시간과 경로를 파악하였다. 또한, 시간 서비스 수준(Level of T hour Serivice)의 개념을 도입하여 위험관으로부터 특정시간 이내에 흐름이 도달하는 Node를 파악한 뒤, 그 중 가장 많은 피해를 발생시킬 수 있는 위험관을 수질계측위치 지점으로 선정하였다. 제시된 수질사고 발생위험이 높은 위험관을 대상으로 수질계측 위치를 선정하는 방법이 전체 관망 네트워크를 대상으로 수질계측 위치를 판단하는 방법보다 결과 신뢰도 측면에서 더욱 효과적이고 효율적인 방법으로 사료된다.