• Journal of the Korean Data and Information Science Society
• /
• v.28 no.4
• /
• pp.721-731
• /
• 2017

In this study, principal component analysis methods using Lasso penalty are introduced. There are two popular methods that apply Lasso penalty to principal component analysis. The first method is to find an optimal vector of linear combination as the regression coefficient vector of regressing for each principal component on the original data matrix with Lasso penalty (elastic net penalty in general). The second method is to find an optimal vector of linear combination by minimizing the residual matrix obtained from approximating the original matrix by the singular value decomposition with Lasso penalty. In this study, we have reviewed two methods of principal components using Lasso penalty in detail, and shown that these methods have an advantage especially in applying to data sets that have more variables than cases. Also, these methods are compared in an application to a real data set using R program. More specifically, these methods are applied to the crime data in Ahamad (1967), which has more variables than cases.

• The Korean Journal of Applied Statistics
• /
• v.31 no.3
• /
• pp.367-382
• /
• 2018

Prediction models for a corporate bond rating in existing studies have been developed using various models such as linear regression, ordered logit, and random forest. Financial characteristics help build prediction models that are expected to be contained in the assigning model of the bond rating agencies. However, the ranges of bond ratings in existing studies vary from 5 to 20 and the prediction models were developed with samples in which the target companies and the observation periods are different. Thus, a simple comparison of the prediction accuracies in each study cannot determine the best prediction model. In order to conduct a fair comparison, this study has collected corporate bond ratings and financial characteristics from 2013 to 2017 and applied prediction models to them. In addition, we applied the elastic-net penalty for the linear regression, the ordered logit, and the ordered probit. Our comparison shows that data-driven variable selection using the elastic-net improves prediction accuracy in each corresponding model, and that the random forest is the most appropriate model in terms of prediction accuracy, which obtains 69.6% accuracy of the exact rating prediction on average from the 5-fold cross validation.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2022

In this paper, we propose a vector-based augmentation technique that can generate data required for crack detection and a ConvNet(Convolutional Neural Network) technique that can learn it. Detecting cracks quickly and accurately is an important technology to prevent building collapse and fall accidents in advance. In order to solve this problem with artificial intelligence, it is essential to obtain a large amount of data, but it is difficult to obtain a large amount of crack data because the situation for obtaining an actual crack image is mostly dangerous. This problem of database construction can be alleviated with elastic distortion, which increases the amount of data by applying deformation to a specific artificial part. In this paper, the improved crack pattern results are modeled using ConvNet. Rather than elastic distortion, our method can obtain results similar to the actual crack pattern. By designing the crack data augmentation based on a vector, rather than the pixel unit used in general data augmentation, excellent results can be obtained in terms of the amount of crack change. As a result, in this paper, even though a small number of crack data were used as input, a crack database can be efficiently constructed by generating various crack directions and patterns.

• Nuclear Engineering and Technology
• /
• v.48 no.2
• /
• pp.339-350
• /
• 2016

Based on the resonance integral (RI) tables produced by the NJOY program, the conventional subgroup method usually ignores both the resonance elastic scattering and the resonance interference effects. In this paper, on one hand, to correct the resonance elastic scattering effect, RI tables are regenerated by using the Monte Carlo code, OpenMC, which employs the Doppler broadening rejection correction method for the resonance elastic scattering. On the other hand, a fast resonance interference factor method is proposed to efficiently handle the resonance interference effect. Encouraging conclusions have been indicated by the numerical results. (1) For a hot full power pressurized water reactor fuel pin-cell, an error of about +200 percent mille could be introduced by neglecting the resonance elastic scattering effect. By contrast, the approach employed in this paper can eliminate the error. (2) The fast resonance interference factor method possesses higher precision and higher efficiency than the conventional Bondarenko iteration method. Correspondingly, if the fast resonance interference factor method proposed in this paper is employed, the $k_{inf}$ can be improved by ~100 percent mille with a speedup of about 4.56.

• Nuclear Engineering and Technology
• /
• v.54 no.7
• /
• pp.2550-2563
• /
• 2022

This study performed a precise dynamic finite element time history elastic-plastic seismic analysis considering the welds, which have been not considered in design stage, on the nuclear components subjected to severe seismic loadings such as beyond-design basis earthquakes for sustainable nuclear power plants. First, the dynamic finite element elastic-plastic seismic analysis was performed for a general design practice that does not take into account the welds of the pressurizer surge line system, one of safety class I components in nuclear power plants, and then the reference values for the accumulated equivalent plastic strain, equivalent plastic strain, and von Mises effective stress were set. Second, the dynamic finite element elastic-plastic seismic analyses were performed for the case of considering only the mechanical strength over-mismatch of the welds as well as for the case of considering both the strength over-mismatch and welding residual strain. Third, the effects of the strength over-mismatch and welding residual strain were analyzed by comparing the finite element analysis results with the reference values. As a result of the comparison, it was found that not considering the strength over-mismatch may lead to conservative assessment results, whereas not considering the welding residual strain may be non-conservative.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3229-3240
• /
• 2023

Due to neutron radiation, atomic displacement has a significant effect on material in nuclear reactors. A range of secondary displacement models, including the Kinchin-Pease (K-P), Lindhard, Norgett-Robinson-Torrens (NRT), and athermal recombination-corrected displacement per atom (arc-dpa) have been suggested to calculate the number of displacement per atom (dpa). As neutron elastic interaction is the main cause of displacement damage, the focus of the current study is to calculate the atomic displacement caused by the neutron elastic interaction in order to estimate the exact amount of yield strength in a WWER-1000 reactor pressure vessel. To achieve this purpose, the reactor core is simulated by MCNPX code. In addition, a program is developed to calculate the elastic radiation damage induced by the incident neutron flux (RADIX) based on different models using Fortran programming language. Also, due to non-elastic interaction, the displacement damage is calculated by the HEATR module of the NJOY code. ASME E-693-01 standard, SPECTER, NJOY codes, and other pervious findings have been used to validate RADIX results. The results showed that the RADIX(arc-dpa)/HEATR outputs have appropriate accuracy. The relative error of the calculated dpa resulting from RADIX(arc-dpa)/HEATR is about 8% and 46% less than NJOY code, respectively in the ¼ and ¾ vessel wall.

• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2147-2157
• /
• 2023

The aggregate-forming minerals in concrete undergo volume swelling and microstructure change under neutron irradiation, leading to degradation of physical and mechanical properties of the aggregates and concrete. A comprehensive investigation of volume change and elastic property variation of major aggregate-forming minerals is still lacking, so molecular dynamics simulations have been employed in this paper to improve the understanding of the degradation mechanisms. The results demonstrated that the densities of the selected aggregate-forming minerals of similar atomic structure and chemical composition vary in a similar trend with deposited energy due to the similar amorphization mechanism. The elastic tensors of all silicate minerals are almost isotropic after saturated irradiation, while those of irradiated carbonate minerals remain anisotropic. Moreover, the elastic modulus ratio versus density ratio of irradiated minerals is roughly following the density-modulus scaling relationship. These findings could further provide basis for predicting the volume and elastic properties of irradiated concrete aggregates in nuclear facilities.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.2
• /
• pp.200-207
• /
• 2007

The passive direction finding cross localization method is widely adopted in passive tracking, therefore there will exist masses of false intersection points. Eliminating these false intersection points correctly and quickly is a key technique in passive localization. A new method is proposed for passive locating and tracking multi-jammer target in this paper. It not only solves the difficulty of determining the number of targets when masses of false intersection points existing, but also solves the initialization problem of elastic network. Thus this method solves the problem of multi-jammer target correlation and the elimination of static false intersection points. The method which dynamically establishes multiple hypothesis trajectory trees solves the problem of eliminating the remaining false intersection points. Simulation results show that computational burden of the method is lower, the elastic network can more quickly find all or most of the targets and have a more probability of locking the real targets. This method can eliminate more false intersection points.

• Nuclear Engineering and Technology
• /
• v.54 no.2
• /
• pp.732-740
• /
• 2022

A piping system stress analysis need to be re-performed for structural integrity assessment after reinforcement of a pipe with significant wall thinning. For efficient stress analysis, a one-dimensional beam element for the wall-thinned pipe with reinforcement needs to be developed. To develop the beam element, this work presents analytical equations for elastic stiffness of the wall-thinned pipe with reinforcement are analytically derived for axial tension, bending and torsion. Comparison with finite element (FE) analysis results using detailed three-dimensional solid models for wall-thinned pipe with reinforcement shows good agreement. Implementation of the proposed solutions into commercial FE programs is explained.

• Journal of Korea Multimedia Society
• /
• v.25 no.2
• /
• pp.206-214
• /
• 2022

The way to measure the extent of damage from floods and droughts is to identify changes in the extent of water systems. In order to effectively grasp this at a glance, satellite images are used. KOMPSAT-5 uses Synthetic Aperture Radar (SAR) to capture images regardless of weather conditions such as clouds and rain. In this paper, various deep learning models are applied to perform semantic segmentation of the water system in this SAR image and the performance is compared. The models used are U-net, V-Net, U2-Net, UNet 3+, PSPNet, Deeplab-V3, Deeplab-V3+ and PAN. In addition, performance comparison was performed when the data was augmented by applying elastic deformation to the existing SAR image dataset. As a result, without data augmentation, U-Net was the best with IoU of 97.25% and pixel accuracy of 98.53%. In case of data augmentation, Deeplab-V3 showed IoU of 95.15% and V-Net showed the best pixel accuracy of 96.86%.