• Nuclear Engineering and Technology
• /
• v.44 no.4
• /
• pp.355-362
• /
• 2012

The aim of this study was to develop a bundle position-wise linear model (BPLM) to predict Pressure Tube (PT) diametral creep employing the previously measured PT diameters and operating conditions. There are twelve bundles in a fuel channel, and for each bundle a linear model was developed by using the dependent variables, such as the fast neutron fluences and the bundle coolant temperatures. The training data set was selected using the subtractive clustering method. The data of 39 channels that consist of 80 percent of a total of 49 measured channels from Units 2, 3, and 4 of the Wolsung nuclear plant in Korea were used to develop the BPLM. The data from the remaining 10 channels were used to test the developed BPLM. The BPLM was optimized by the maximum likelihood estimation method. The developed BPLM to predict PT diametral creep was verified using the operating data gathered from Units 2, 3, and 4. Two error components for the BPLM, which are the epistemic error and the aleatory error, were generated. The diametral creep prediction and two error components will be used for the generation of the regional overpower trip setpoint at the corresponding effective full power days. The root mean square (RMS) errors were also generated and compared to those from the current prediction method. The RMS errors were found to be less than the previous errors.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.165-165
• /
• 2023

Streamflow prediction is a critical task in water resources management and essential for planning and decision-making purposes. However, the streamflow prediction is challenging due to the complexity and non-linear nature of hydrological processes. The transfer learning is a powerful technique that enables a model to transfer knowledge from a source domain to a target domain, improving model performance with limited data in the target domain. In this study, we apply the transfer learning using the Informer model, which is a state-of-the-art deep learning model for streamflow prediction. The model was trained on a large-scale hydrological dataset in the source basin and then fine-tuned using a smaller dataset available in the target basin to predict the streamflow in the target basin. The results demonstrate that transfer learning using the Informer model significantly outperforms the traditional machine learning models and even other deep learning models for streamflow prediction, especially when the target domain has limited data. Moreover, the results indicate the effectiveness of streamflow prediction when knowledge transfer is used to improve the generalizability of hydrologic models in data-sparse regions.

• The Korean Journal of Applied Statistics
• /
• v.15 no.2
• /
• pp.213-222
• /
• 2002

The 3-hour-interval prediction of ground-level temperature up to +45 hours in Seoul area is performed using dynamic linear models(DLM). Numerical outputs and observations we used as input values of DLM. According to compare DLM forecasts to RDAPS forecasts using RMSE, DLM improve the accuracy of prediction and systematic error of numerical model outputs are eliminated by DLM.

• Journal of the Microelectronics and Packaging Society
• /
• v.20 no.3
• /
• pp.7-10
• /
• 2013

This study presents an approach to predict insulation resistance failure of multilayer ceramic capacitors (MLCCs) using non-linear modeling. A capacitance aging model created by non-linear modeling allowed for the prediction of insulation resistance failure. The MLCC data tested under temperature-humidity-bias testing conditions showed that a change in capacitance, when measured against a capacitance aging model, was able to provide a prediction of insulation resistance failure.

• Communications for Statistical Applications and Methods
• /
• v.4 no.3
• /
• pp.795-805
• /
• 1997

In this paper, we consider a Bayesian forecasting method for the analysis of repeated surveys. It is assumed that the parameters of the superpopulation model at each time follow a stochastic model. We propose Bayesian prediction procedures for the finite population total under dynamic generalized linear models. Some numerical studies are provided to illustrate the behavior of the proposed predictors.

• Journal of radiological science and technology
• /
• v.43 no.6
• /
• pp.503-509
• /
• 2020

This study aims to develop a patient-specific radiation exposure dose prediction model based on anthropometric data that can be easily measurable during CT examination, and to be used as basic data for DRL setting and radiation dose management system in the future. In addition, among the machine learning algorithms, the most suitable model for predicting exposure doses is presented. The data used in this study were chest CT scan data, and a data set was constructed based on the data including the patient's anthropometric data. In the pre-processing and sample selection of the data, out of the total number of samples of 250 samples, only chest CT scans were performed without using a contrast agent, and 110 samples including height and weight variables were extracted. Of the 110 samples extracted, 66% was used as a training set, and the remaining 44% were used as a test set for verification. The exposure dose was predicted through random forest, linear regression analysis, and SVM algorithm using Orange version 3.26.0, an open software as a machine learning algorithm. Results Algorithm model prediction accuracy was R^2 0.840 for random forest, R^2 0.969 for linear regression analysis, and R^2 0.189 for SVM. As a result of verifying the prediction rate of the algorithm model, the random forest is the highest with R^2 0.986 of the random forest, R^2 0.973 of the linear regression analysis, and R^2 of 0.204 of the SVM, indicating that the model has the best predictive power.

• Proceedings of the KWS Conference
• /
• 2006.10a
• /
• pp.271-273
• /
• 2006

This paper focuses on the developed empirical models for the prediction on top-bead width in GMA(Gas Metal Arc) welding process. Three empirical models have been developed: linear, curvilinear and an intelligent model. Regression analysis was employed fur optimization of the coefficients of linear and curvilinear model, while Genetic Algorithm(GA) was utilized to estimate the coefficients of intelligent model. Not only the fitting of these models were checked, but also the prediction on top-bead width was carried out. ANOVA analysis and contour plots were respectively employed to represent main and interaction effects between process parameters on top-bead width.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10b
• /
• pp.1041-1044
• /
• 1988

This paper considers the design problem of adaptive filters based an the state-space models for linear discrete-time stationary stochastic signal processes. The adaptive state estimator consists of both the predictor and the sequential prediction error estimator. The discrete Chandrasakhar filter developed by author is employed as the predictor and the nonlinear least-squares estimator is used as the sequential prediction error estimator. Two models are presented for calculating the parameter sensitivity functions in the adaptive filter. One is the exact model called the linear innovations model and the other is the simplified model obtained by neglecting the sensitivities of the Chandrasekhar X and Y functions with respect to the unknown parameters in the exact model.

• Communications for Statistical Applications and Methods
• /
• v.27 no.4
• /
• pp.445-458
• /
• 2020

The least absolute shrinkage and selection operator (LASSO) is a popular method for a high-dimensional regression model. LASSO has high prediction accuracy; however, it also selects many irrelevant variables. In this paper, we consider the moderately clipped LASSO (MCL) for the high-dimensional generalized linear model which is a hybrid method of the LASSO and minimax concave penalty (MCP). The MCL preserves advantages of the LASSO and MCP since it shows high prediction accuracy and successfully selects relevant variables. We prove that the MCL achieves the oracle property under some regularity conditions, even when the number of parameters is larger than the sample size. An efficient algorithm is also provided. Various numerical studies confirm that the MCL can be a better alternative to other competitors.

• Journal of Korean Institute of Industrial Engineers
• /
• v.40 no.3
• /
• pp.283-290
• /
• 2014

In the flat panel display industry, to meet production target quantities and the deadline of production, the scheduler and dispatching systems are major production management systems which control the order of facility production and the distribution of WIP (Work In Process). Especially the delivery time is a key factor of the dispatching system for the time when a lot can be supplied to the facility. In this paper, we use survival analysis methods to identify main factors of the delivery time and to build the delivery time forecasting model. To select important explanatory variables, the cox proportional hazard model is used to. To make a prediction model, the accelerated failure time (AFT) model was used. Performance comparisons were conducted with two other models, which are the technical statistics model based on transfer history and the linear regression model using same explanatory variables with AFT model. As a result, the mean square error (MSE) criteria, the AFT model decreased by 33.8% compared to the statistics prediction model, decreased by 5.3% compared to the linear regression model. This survival analysis approach is applicable to implementing the delivery time estimator in display manufacturing. And it can contribute to improve the productivity and reliability of production management system.