• The Mathematical Education
• /
• v.26 no.2
• /
• pp.55-61
• /
• 1988

이 논문에서는 CS-Semistratifiable 공간보다 더 일반화된 공간 Cn-Semistratifiable을 정의 하며 그에 따른 여러가지 성질들을 조사하였다. 위상 공간(X, $\tau$)에 대하여 $\alpha$$\times$$\tau$에서 X의 폐집합족으로의 함수 S가 존재하여 다음 조건들을 만족할 때 공간X는 Cn-Semistratifiable over $\alpha$라 정의한다. a) 임의의 개집합 U에 대하여 U=U{S($\beta$, U) : $\beta$<$\alpha$} b) U, V가 X의 개집합이고 U⊂CV이면 모든 $\beta$<$\alpha$에 대하여 S($\beta$, V)⊂S($\beta$, V)이다. c) 만약 ${\gamma}$<$\beta$<$\alpha$ 이라면 임의의 개집합 U에 대하여 S(${\gamma}$, U)⊂S($\beta$, U)이다. d) X의 수렴하는 net $X_{\beta}$$\longrightarrow$X와 X를 품는 임의의 개집합 U에 대하여 적당한 $\beta$<$\alpha$가 존재하여 X$\in$S($\beta$. U)이고 { $X_{\beta}$}는 S($\beta$, U)안에 eventual하게 들어간다. 위의 정의에 의하여 다음과 같은 성질들이 증명되었다. 1 . Strstifiable over $\alpha$$\longrightarrow$cn-semistratifiable over$\longrightarrow$semistratifiable over $\alpha$ 2, 어떤 공간이 cn-Semistratifiable over $\alpha$이기 위한 필요충분 조건은 그것이 linearly cushioned cn-pairnet를 갖는 것이다. 3. cn-semistratifiable over $\alpha$의 부분공간 역시 cn-semistratifiabie over $\alpha$ 하다. 4. on-semistratifiable over $\alpha$의 유한개의 적공간 역시 cn-semistratifiabie over $\alpha$한다. 5. 폐 cn-semistratifiable over $\alpha$ 부분공간들의 합공간 역시 on-semistrbtifiable over $\alpha$ 하다. 6. 폐연속 net-cevering 함수에 의하여 cn-semistratifiable over $\alpha$ 성질이 보존된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1778-1797
• /
• 2021

Document image binarization is an important pre-processing step in document analysis and archiving. The state-of-the-art models for document image binarization are variants of encoder-decoder architectures, such as FCN (fully convolutional network) and U-Net. Despite their success, they still suffer from three limitations: (1) reduced feature map resolution due to consecutive strided pooling or convolutions, (2) multiple scales of target objects, and (3) reduced localization accuracy due to the built-in invariance of deep convolutional neural networks (DCNNs). To overcome these three challenges, we propose an improved semantic segmentation model, referred to as DP-LinkNet, which adopts the D-LinkNet architecture as its backbone, with the proposed hybrid dilated convolution (HDC) and spatial pyramid pooling (SPP) modules between the encoder and the decoder. Extensive experiments are conducted on recent document image binarization competition (DIBCO) and handwritten document image binarization competition (H-DIBCO) benchmark datasets. Results show that our proposed DP-LinkNet outperforms other state-of-the-art techniques by a large margin. Our implementation and the pre-trained models are available at https://github.com/beargolden/DP-LinkNet.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.21-29
• /
• 2024

Reducing the radiation dose during CT scanning can lower the risk of radiation exposure, but not only does the image resolution significantly deteriorate, but the effectiveness of diagnosis is reduced due to the generation of noise. Therefore, noise removal from CT images is a very important and essential processing process in the image restoration. Until now, there are limitations in removing only the noise by separating the noise and the original signal in the image area. In this paper, we aim to effectively remove noise from CT images using the wavelet transform-based GAN model, that is, the WT-GAN model in the frequency domain. The GAN model used here generates images with noise removed through a U-Net structured generator and a PatchGAN structured discriminator. To evaluate the performance of the WT-GAN model proposed in this paper, experiments were conducted on CT images damaged by various noises, namely Gaussian noise, Poisson noise, and speckle noise. As a result of the performance experiment, the WT-GAN model is better than the traditional filter, that is, the BM3D filter, as well as the existing deep learning models, such as DnCNN, CDAE model, and U-Net GAN model, in qualitative and quantitative measures, that is, PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index Measure) showed excellent results.

• Geophysics and Geophysical Exploration
• /
• v.25 no.2
• /
• pp.59-70
• /
• 2022

Recent studies demonstrate that machine learning has expanded in the field of seismic interpretation. Many convolutional neural networks have been developed for seismic sequence identification, which is important for seismic interpretation. However, expense and time limitations indicate that there is insufficient data available to provide a sufficient dataset to train supervised machine learning programs to identify seismic sequences. In this study, patch division and data augmentation are applied to mitigate this lack of data. Furthermore, to obtain spatial information that could be lost during patch division, an artificial channel is added to the original data to indicate depth. Seismic sequence identification is performed using a U-Net network and the Netherlands F3 block dataset from the dGB Open Seismic Repository, which offers datasets for machine learning, and the predicted results are evaluated. The results show that patch-based U-Net seismic sequence identification is improved by data augmentation and the addition of an artificial channel.

• Nuclear Engineering and Technology
• /
• v.53 no.2
• /
• pp.611-617
• /
• 2021

The mechanical properties of α-Na₃(U_0.84(2),Na_0.16(2))O₄ have been researched using the first-principles calculations combined with the quasi-harmonic Debye model. The obtained lattice parameters agree well with the published experimental data. The results of elastic constants indicate that α-Na₃(U_0.84(2),Na_0.16(2))O₄ is mechanically stable. The polycrystalline moduli are predicted. The results show that the α-Na₃(U_0.84(2),Na_0.16(2))O₄ exhibits brittleness and possesses obvious elastic anisotropy. The hardness shows that it can be considered a "soft material". Furthermore, the Debye temperature θ_D and the minimum thermal conductivity k_min are also discussed, respectively. Finally, the thermal expansion coefficient α, isobaric heat capacity C_P and isochoric heat capacity C_V are evaluated through the quasi-harmonic Debye model.

• Nuclear Engineering and Technology
• /
• v.51 no.6
• /
• pp.1638-1649
• /
• 2019

Top soil samples across the state of Kuwait numering ninety were collected and analysed using gamma-ray spectrometry, to evaluate the elemental concentration of $^{238}U$, $^{232}Th$ and $^{40}K$ and their depletion/enrichment. Results of elemental concentration ranges from 0.48 to 2.61 mg/kg, 0.87-5.23 mg/kg, and 0.24-2.23%, with a mean values of 1.39 mg/kg, 3.47 mg/kg, and 1.18%, for the $^{238}U$, $^{232}Th$ and $^{40}K$, respectively. Further analysis was conducted amongst the five identified soil types, i.e. Aquisalids (S1), Calcigypsids (S2), Petrocalcids (S3), Petrogypsids (S4), and torripsamment (S5). The highest radioactivity concentrations from both uranium and thorium were recorded in the S2 (Calcigypsids) soil, with a value of 1.71 (mg/kg) and 4.45 (mg/kg), respectively. Minimum and maximum values of $^{40}K$ are 1.1(%) and 1.27(%) and is prevalent in Aquisalids (S1) and Petrocalcids (S3) soil types, respectively. Ratios of elemental concentration for $^{232}Th/^{238}U$, $^{40}K/^{238}U$, $^{40}K/^{232}Th$ across the soil types are 2.53, 0.09 and 0.03, with a correlation coefficient of 0.92, 0.34, and 0.38, respectively. A progressively higher $^{232}Th/^{238}U$ ratio is observed moving south-wards, indicating lower $^{238}U$ content in soils from the south relative to the northern part. Overall results indicate Kuwait to be relatively an area with low level of natural radioactivity.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.1-7
• /
• 2023

An artificial intelligence (AI) method based on image deep learning is proposed to predict the entire displacement shape of a structure using the feature of partial displacements. The performance of the method was investigated through a structural test of a steel frame. An image-to-image regression (I2IR) training method was developed based on the U-Net layer for image recognition. In the I2IR method, the U-Net is modified to generate images of entire displacement shapes when images of partial displacement shapes of structures are input to the AI network. Furthermore, the training of displacements combined with the location feature was developed so that nodal displacement values with corresponding nodal coordinates could be used in AI training. The proposed training methods can consider correlations between nodal displacements in 3D space, and the accuracy of displacement predictions is improved compared with artificial neural network training methods. Displacements of the steel frame were predicted during the structural tests using the proposed methods and compared with 3D scanning data of displacement shapes. The results show that the proposed AI prediction properly follows the measured displacements using 3D scanning.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2004.05a
• /
• pp.39-43
• /
• 2004

A research shows that a new category of software, Collaborative Product Commerce (CPC), is now emerging, allowing discrete manufacturers to once again distinguish themselves on their products and innovations. CPC permits discrete manufacturers to significantly improve the core processes around the management functions associated with the complete product life cycle that are the basis of their existence. As a way to develop computing tools of CPC to support a design process of product, a web-based design supporting system was constructed in the paper. The system consists of C-Product system and Net Meeting Communication system to improve communications between designers and persons for verification of design. The product data files of C-Product system were designed by Pro/Engineer and converted to 3D Viewer format for being used in the web browser. Also, Net Meeting Communication system and Database were developed using ASP and Microsoft SQL 2000 Server to share diverse files that can be utilized to design on the web in real time.

• Nuclear Engineering and Technology
• /
• v.41 no.2
• /
• pp.187-198
• /
• 2009

In this paper, three power ramp tests performed on high burn-up Re-crystallized Zircaloy2 - UO2 BWR fuel rods (56 to 63 MWd/kgU) within the SCIP project are simulated with METEOR and ALCYONE 3D. Two of the ramp tests are of staircase type up to Linear Heat Rates of 420 and 520 W/cm and with long holding periods. Failure of the 420 W/cm fuel rod was observed after 40 minutes. The third ramp test consisted of a more standard ramp test with a constant power rate of 80 W/cm/min up to 410 W/cm with a short holding time. The tests were first simulated with the METEOR 1D fuel rod code, which gave accurate results in terms of profilometry and fission gas releases. The behaviour of a fuel pellet fragment and of the cladding piece on top of it was then investigated with ALCYONE 3D. The size and the main characteristics of the ridges after base irradiation and power ramp testing were recovered. Finally, the failure criteria validated for PWR conditions and fuel rods with low-to-medium burn-ups were used to analyze the failure probability of the KKL rodlets during ramp testing.

• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.5
• /
• pp.303-313
• /
• 2021

Recently, quality control of the Liquefied Natural Gas Carrier (LNGC) cargo hold and block-erection interference areas using 3D scanners have been performed, focusing on large shipyards and the international association of classification societies. In this study, as a part of the research on LNGC cargo hold quality management advancement, a study on deep-learning-based scaffolding system 3D point cloud object detection and post-processing were conducted using a LNGC cargo hold 3D point cloud. The scaffolding system point cloud object detection is based on the PointNet deep learning architecture that detects objects using point clouds, achieving 70% prediction accuracy. In addition, the possibility of improving the accuracy of object detection through parameter adjustment is confirmed, and the standard of Intersection over Union (IoU), an index for determining whether the object is the same, is achieved. To avoid the manual post-processing work, the object detection architecture allows automatic task performance and can achieve stable prediction accuracy through supplementation and improvement of learning data. In the future, an improved study will be conducted on not only the flat surface of the LNGC cargo hold but also complex systems such as curved surfaces, and the results are expected to be applicable in process progress automation rate monitoring and ship quality control.