• Nuclear Engineering and Technology
• /
• v.54 no.4
• /
• pp.1431-1438
• /
• 2022

In this study, natural radioactivity concentrations and dosimetric values of fly ash samples were evaluated for the landfill area of the coal-fired power plant (CFPP) complex at Binh Thuan, Vietnam. The average activity concentrations of ²³⁸U, ²²⁶Ra, ²³²Th and ⁴⁰K were 93, 77, 92 and 938 Bq kg^-1, respectively. The average results for radon dose, indoor external, internal, and total effective dose equivalent (TEDE) were 5.27, 1.22, 0.16, and 6.65 mSv y^-1, respectively. The average emanation fraction for fly ash were 0.028. The excess lifetime cancer risks (ELCR) were recorded as 20.30×10^-3, 4.26×10^-3, 0.62×10^-3, and 25.61×10^-3 for radon, indoor, outdoor exposures, and total ELCR, respectively. The results indicated that the cover of shielding materials above the landfill area significantly decreased the gamma radiation from the ash and slag in the ascending order: Zeolite < PVC < Soil < Concrete. Total dose of all radionuclides in the landfill site reached its peak at 19.8 years. The obtained data are useful for evaluation of radiation safety when fly ash is used for building material as well as the radiation risk and the overload of the landfill area from operation of these plants for population and workers.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.111-126
• /
• 2022

Land use and land cover (LULC) mapping is an important factor in geospatial analysis. Although highly precise ground-based LULC monitoring is possible, it is time consuming and costly. Conversely, because the synthetic aperture radar (SAR) sensor is an all-weather sensor with high resolution, it could replace field-based LULC monitoring systems with low cost and less time requirement. Thus, LULC is one of the major areas in SAR applications. We developed a LULC model using only KOMPSAT-5 single co-polarized data and digital elevation model (DEM) data. Twelve HH-polarized images and 18 VV-polarized images were collected, and two HH-polarized images and four VV-polarized images were selected for the model testing. To train the LULC model, we applied the conditional generative adversarial network (cGAN) method. We used U-Net combined with the residual unit (ResUNet) model to generate the cGAN method. When analyzing the training history at 1732 epochs, the ResUNet model showed a maximum overall accuracy (OA) of 93.89 and a Kappa coefficient of 0.91. The model exhibited high performance in the test datasets with an OA greater than 90. The model accurately distinguished water body areas and showed lower accuracy in wetlands than in the other LULC types. The effect of the DEM on the accuracy of LULC was analyzed. When assessing the accuracy with respect to the incidence angle, owing to the radar shadow caused by the side-looking system of the SAR sensor, the OA tended to decrease as the incidence angle increased. This study is the first to use only KOMPSAT-5 single co-polarized data and deep learning methods to demonstrate the possibility of high-performance LULC monitoring. This study contributes to Earth surface monitoring and the development of deep learning approaches using the KOMPSAT-5 data.

• Nuclear Engineering and Technology
• /
• v.53 no.3
• /
• pp.763-775
• /
• 2021

The thermal hydraulic performances of Steam Generator (SG) under both steady and transient operation conditions are of great importance for the safety and economy in nuclear power plants. In this paper, based on our self-developed SG thermal hydraulic analysis code STAF (Steam-generator Thermalhydraulic Analysis code based on Fluent), an improved new version STAF-CT (fully Coupling and Transient) is developed and introduced. Compared with original STAF, the new version code STAF-CT has two main functional improvements including "Transient" and "Fully Three Dimensional Coupling" features. In STAF-CT, a three dimensional energy transferring module is established which can achieve energy exchange computing function at the corresponding position between two sides of SG. The STAF-CT is validated against the international benchmark experiment data and the results show great agreement. Then the U-shaped SG in AP1000 nuclear power plant is modeled and simulated using STAF-CT. The results show that three dimensional flow fields in the primary side make significant effect on the energy source distribution between two sides. The development of code STAF-CT in this paper can provide an effective method for further SG high fidelity research in the nuclear reactor system.

• Nuclear Engineering and Technology
• /
• v.52 no.12
• /
• pp.2733-2742
• /
• 2020

This paper presents an assessment of applicability of the multigroup cross sections generated with Monte Carlo tools to the fast reactor analysis based on transport calculations. 33-group cross section sets were generated for simple one- (1-D) and two-dimensional (2-D) sodium-cooled fast reactor problems using the SERPENT code and applied to deterministic steady-state and depletion calculations. Relative to the reference continuous-energy SERPENT results, with the transport corrected P₀ scattering cross section, the k-eff value was overestimated by 506 and 588 pcm for 1-D and 2-D problems, respectively, since anisotropic scattering is important in fast reactors. When the scattering order was increased to P₅, the 1-D and 2-D problem errors were increased to 577 and 643 pcm, respectively. A sensitivity and uncertainty analysis with the PERSENT code indicated that these large k-eff errors cannot be attributed to the statistical uncertainties of cross sections and they are likely due to the approximate anisotropic scattering matrices determined by scalar flux weighting. The anisotropic scattering cross sections were alternatively generated using the MC²-3 code and merged with the SERPENT cross sections. The mixed cross section set consistently reduced the errors in k-eff, assembly powers, and nuclide densities. For example, in the 2-D calculation with P3 scattering order, the k-eff error was reduced from 634 pcm to -223 pcm. The maximum error in assembly power was reduced from 2.8% to 0.8% and the RMS error was reduced from 1.4% to 0.4%. The maximum error in the nuclide densities at the end of 12-month depletion that occurred in ²³⁷Np was reduced from 3.4% to 1.5%. The errors of the other nuclides are also reduced consistently, for example, from 1.1% to 0.1% for ²³⁵U, from 2.2% to 0.7% for ²³⁸Pu, and from 1.6% to 0.2% for ²⁴¹Pu. These results indicate that the scalar flux weighted anisotropic scattering cross sections of SERPENT may not be adequate for application to fast reactors where anisotropic scattering is important.

• Journal of Biomedical Engineering Research
• /
• v.43 no.6
• /
• pp.434-440
• /
• 2022

Liver transplantation is a critical used treatment method for patients with end-stage liver disease. The number of cases of living donor liver transplantation is increasing due to the imbalance in needs and supplies for brain-dead organ donation. As a result, the importance of the accuracy of the donor's suitability evaluation is also increasing rapidly. To measure the donor's liver volume accurately is the most important, that is absolutely necessary for the recipient's postoperative progress and the donor's safety. Therefore, we propose liver segmentation in abdominal CT images from pre-operation, POD 7, and POD 63 with a two-dimensional U-Net. In addition, we introduce an algorithm to measure the volume of the segmented liver and measure the hepatectomy rate and regeneration rate of pre-operation, POD 7, and POD 63. The performance for the learning model shows the best results in the images from pre-operation. Each dataset from pre-operation, POD 7, and POD 63 has the DSC of 94.55 ± 9.24%, 88.40 ± 18.01%, and 90.64 ± 14.35%. The mean of the measured liver volumes by trained model are 1423.44 ± 270.17 ml in pre-operation, 842.99 ± 190.95 ml in POD 7, and 1048.32 ± 201.02 ml in POD 63. The donor's hepatectomy rate is an average of 39.68 ± 13.06%, and the regeneration rate in POD 63 is an average of 14.78 ± 14.07%.

• Nuclear Engineering and Technology
• /
• v.54 no.3
• /
• pp.1062-1070
• /
• 2022

In the present communication, pure and stable α-Bismuth Oxide (Bi₂O₃) nanoparticles (NPs) were synthesized by low temperature solution combustion method using urea as a fuel and calcined at 500℃. The synthesized sample was characterized by using powder X-ray Diffraction (PXRD), Scanning Electron Microscopy (SEM), Energy dispersive X-ray analysis (EDAX), Transmission Electron Microscopy (TEM), Fourier Transform Infrared Spectroscopy (FTIR) and UV-Visible absorption spectroscopy. The PXRD pattern confirms the formation of mono-clinic, stable and low temperature phase α-Bi₂O₃. The direct optical energy band gap was estimated by using Wood and Tauc's relation which was found to be 2.81 eV. The characterized sample was studied for X-ray/gamma ray shielding properties in the energy range 0.081-1.332 MeV using NaI (Tl) detector and multi channel analyzer (MCA). The measured shielding parameters agrees well with the theory, whereas, slight deviation up to 20% is observed below 356 keV. This deviation is mainly due to the influence of atomic size of the target medium. Furthermore an accurate theory is necessary to explain the interaction of X-ray/gamma ray with the NPs.The present work opens new window to use this facile, economical, efficient, low temperature method to synthesize nanomaterials for X-ray/gamma ray shielding purpose.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.395-409
• /
• 2022

The purpose of this study is to evaluate the classification performance and applicability when land cover datasets constructed for AI training are cross validation to other areas. For study areas, Gyeongsang-do and Jeolla-do in South Korea were selected as cross validation areas, and training datasets were obtained from AI-Hub. The obtained datasets were applied to the U-Net algorithm, a semantic segmentation algorithm, for each region, and the accuracy was evaluated by applying them to the same and other test areas. There was a difference of about 13-15% in overall classification accuracy between the same and other areas. For rice field, fields and buildings, higher accuracy was shown in the Jeolla-do test areas. For roads, higher accuracy was shown in the Gyeongsang-do test areas. In terms of the difference in accuracy by weight, the result of applying the weights of Gyeongsang-do showed high accuracy for forests, while that of applying the weights of Jeolla-do showed high accuracy for dry fields. The result of land cover classification, it was found that there is a difference in classification performance of existing datasets depending on area. When constructing land cover map for AI training, it is expected that higher quality datasets can be constructed by reflecting the characteristics of various areas. This study is highly scalable from two perspectives. First, it is to apply satellite images to AI study and to the field of land cover. Second, it is expanded based on satellite images and it is possible to use a large scale area and difficult to access.

• Journal of Broadcast Engineering
• /
• v.28 no.1
• /
• pp.132-140
• /
• 2023

In this paper, we propose a method for performance enhancement of speech declipping using clipping detector. Clipping occurs when the input speech level exceeds the dynamic range of microphone, and it significantly degrades the speech quality. Recently, many methods for high-performance speech declipping based on machine learning have been developed. However, they often deteriorate the speech signal because of degradation in signal reconstruction process when the degree of clipping is not high. To solve this problem, we propose a new approach that combines the declipping network and clipping detector, which enables a selective declipping operation depending on the clipping level and provides high-quality speech in all clipping levels. We measured the declipping performance using various metrics and confirmed that the proposed method improves the average performance over all clipping levels, compared with the conventional methods, and greatly improves the performance when the clipping distortion is small.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.2-2
• /
• 2023

기후변화가 가속화로 인해 수재해의 빈도와 강도 예측이 어려워짐에 따라 실시간 홍수 모니터링에 대한 수요가 증가하고 있다. 합성개구레이다는 광원과 날씨에 무관하게 촬영이 가능하여 수재해 발생시에도 영상을 확보할 수 있다. 합성개구레이다를 활용한 수체 탐지 알고리즘 개발이 활발히 연구되어 왔고, 딥러닝의 발달로 CNN을 활용하여 높은 정확도로 수체 탐지가 기능해졌다. 하지만, CNN 기반 수체 탐지 모델은 훈련시 높은 정량적 정확성 지표를 달성하여도 추론 후 정성적 평가시 경계와 소하천에 대한 탐지 정확성이 떨어진다. 홍수 모니터링에서 특히 중요한 정보인 경계와 좁은 하천에 대해서 정확성이 떨어짐에 따라 실생활 적용이 어렵다. 이에 경계를 강화한 적대적 학습 기반의 수체 탐지 모델을 개발하여 더 세밀하고 정확하게 탐지하고자 한다. 적대적 학습은 생성적 적대 신경망(GAN)의 두 개의 모델인 생성자와 판별자가 서로 관여하며 더 높은 정확도를 달성할 수 있도록 학습이다. 이러한 적대적 학습 개념을 수체 탐지 모델에 처음으로 도입하여, 생성자는 실제 라벨 데이터와 유사하게 수체 경계와 소하천까지 탐지하고자 학습한다. 반면 판별자는 경계 거리 변환 맵과 합성개구레이다 영상을 기반으로 라벨데이터와 수체 탐지 결과를 구분한다. 경계가 강화될 수 있도록, 면적과 경계를 모두 고려할 수 있는 손실함수 조합을 구성하였다. 제안 모델이 경계와 소하천을 정확히 탐지하는지 판단하기 위해, 정량적 지표로 F1-score를 사용하였으며, 육안 판독을 통해 정성적 평가도 진행하였다. 기존 U-Net 모델이 탐지하지 못하던 영역에 대해 제안한 경계 강화 적대적 수체 탐지 모델이 수체의 세밀한 부분까지 탐지할 수 있음을 증명하였다.