• Korean Journal of Radiology
• /
• v.22 no.11
• /
• pp.1850-1857
• /
• 2021

Objective: The purpose of this study was to assess whether a deep learning (DL) algorithm could enable simultaneous noise reduction and edge sharpening in low-dose lumbar spine CT. Materials and Methods: This retrospective study included 52 patients (26 male and 26 female; median age, 60.5 years) who had undergone CT-guided lumbar bone biopsy between October 2015 and April 2020. Initial 100-mAs survey images and 50-mAs intraprocedural images were reconstructed by filtered back projection. Denoising was performed using a vendor-agnostic DL model (ClariCT.AI^TM, ClariPI) for the 50-mAS images, and the 50-mAs, denoised 50-mAs, and 100-mAs CT images were compared. Noise, signal-to-noise ratio (SNR), and edge rise distance (ERD) for image sharpness were measured. The data were summarized as the mean ± standard deviation for these parameters. Two musculoskeletal radiologists assessed the visibility of the normal anatomical structures. Results: Noise was lower in the denoised 50-mAs images (36.38 ± 7.03 Hounsfield unit [HU]) than the 50-mAs (93.33 ± 25.36 HU) and 100-mAs (63.33 ± 16.09 HU) images (p < 0.001). The SNRs for the images in descending order were as follows: denoised 50-mAs (1.46 ± 0.54), 100-mAs (0.99 ± 0.34), and 50-mAs (0.58 ± 0.18) images (p < 0.001). The denoised 50-mAs images had better edge sharpness than the 100-mAs images at the vertebral body (ERD; 0.94 ± 0.2 mm vs. 1.05 ± 0.24 mm, p = 0.036) and the psoas (ERD; 0.42 ± 0.09 mm vs. 0.50 ± 0.12 mm, p = 0.002). The denoised 50-mAs images significantly improved the visualization of the normal anatomical structures (p < 0.001). Conclusion: DL-based reconstruction may enable simultaneous noise reduction and improvement in image quality with the preservation of edge sharpness on low-dose lumbar spine CT. Investigations on further radiation dose reduction and the clinical applicability of this technique are warranted.

• Korean Journal of Radiology
• /
• v.22 no.6
• /
• pp.983-993
• /
• 2021

Objective: To investigate the image quality of ultralow-dose CT (ULDCT) of the chest reconstructed using a cycle-consistent generative adversarial network (CycleGAN)-based deep learning method in the evaluation of pulmonary tuberculosis. Materials and Methods: Between June 2019 and November 2019, 103 patients (mean age, 40.8 ± 13.6 years; 61 men and 42 women) with pulmonary tuberculosis were prospectively enrolled to undergo standard-dose CT (120 kVp with automated exposure control), followed immediately by ULDCT (80 kVp and 10 mAs). The images of the two successive scans were used to train the CycleGAN framework for image-to-image translation. The denoising efficacy of the CycleGAN algorithm was compared with that of hybrid and model-based iterative reconstruction. Repeated-measures analysis of variance and Wilcoxon signed-rank test were performed to compare the objective measurements and the subjective image quality scores, respectively. Results: With the optimized CycleGAN denoising model, using the ULDCT images as input, the peak signal-to-noise ratio and structural similarity index improved by 2.0 dB and 0.21, respectively. The CycleGAN-generated denoised ULDCT images typically provided satisfactory image quality for optimal visibility of anatomic structures and pathological findings, with a lower level of image noise (mean ± standard deviation [SD], 19.5 ± 3.0 Hounsfield unit [HU]) than that of the hybrid (66.3 ± 10.5 HU, p < 0.001) and a similar noise level to model-based iterative reconstruction (19.6 ± 2.6 HU, p > 0.908). The CycleGAN-generated images showed the highest contrast-to-noise ratios for the pulmonary lesions, followed by the model-based and hybrid iterative reconstruction. The mean effective radiation dose of ULDCT was 0.12 mSv with a mean 93.9% reduction compared to standard-dose CT. Conclusion: The optimized CycleGAN technique may allow the synthesis of diagnostically acceptable images from ULDCT of the chest for the evaluation of pulmonary tuberculosis.

• Journal of Intelligence and Information Systems
• /
• v.16 no.1
• /
• pp.93-116
• /
• 2010

Ensemble approach is applied to the detection modeling of illegal cash accommodation (ICA) that is the well-known type of fraudulent usages of credit cards in far east nations and has not been addressed in the academic literatures. The performance of fraud detection model (FDM) suffers from the imbalanced data problem, which can be remedied to some extent using an ensemble of many classifiers. It is generally accepted that ensembles of classifiers produce better accuracy than a single classifier provided there is diversity in the ensemble. Furthermore, recent researches reveal that it may be better to ensemble some selected classifiers instead of all of the classifiers at hand. For the effective detection of ICA, we adopt ensemble size reduction technique that prunes the ensemble of all classifiers using accuracy and diversity measures. The diversity in ensemble manifests itself as disagreement or ambiguity among members. Data imbalance intrinsic to FDM affects our approach for ICA detection in two ways. First, we suggest the training procedure with over-sampling methods to obtain diverse training data sets. Second, we use some variants of accuracy and diversity measures that focus on fraud class. We also dynamically calculate the diversity measure-Forward Addition and Backward Elimination. In our experiments, Neural Networks, Decision Trees and Logit Regressions are the base models as the ensemble members and the performance of homogeneous ensembles are compared with that of heterogeneous ensembles. The experimental results show that the reduced size ensemble is as accurate on average over the data-sets tested as the non-pruned version, which provides benefits in terms of its application efficiency and reduced complexity of the ensemble.

• Resources Recycling
• /
• v.15 no.4 s.72
• /
• pp.44-51
• /
• 2006

Most electric arc furnace dust (EAFD) treatment processes to recover zinc from EAFD employ carbon as a reducing agent for the zinc oxide in the EAFD. In the present work, the reduction reaction of zinc oxide with carbon in the present of iron oxide was kinetically studied. The experiments were carried out at temperatures between 1173 K and 1373 K under nitrogen atmosphere using a weight-loss technique. From the experimental results, it was concluded that adding the proper amount of iron oxide to the reactant accelerates the reaction rate of zinc oxide with carbon. This is because iron oxide in the reduction reaction of zinc oxide with carbon promotes the carbon gasification reaction. The spherical shrinking core model for a surface chemical reaction control was found to be useful in describing kinetics of the reaction over the entire temperature range. The reaction has an activation energy of 53 kcal/mol (224 kJ/mol) for ZnO-C reaction system, an activation energy of 42 kcal/mol (175 kJ/mol) for $ZnO-Fe_{2}O_{3}-C$ reaction system, and an activation energy of 44 kcal/mol (184 kJ/mol) for ZnO-mill scale-C reaction system.

• Magazine of the Korea Concrete Institute
• /
• v.11 no.2
• /
• pp.95-103
• /
• 1999

The reduction phenomena of concrete compressive strength with the size of specimens have been extensively investigated, but till now the adequate analysis technique is not fixed. The existing research results show that the bigger the member size, the smaller the strength. This means the nonlinear fracture mechanics theory is needed in order to analyze the fracture behaviors of concrete and the size effect. There is a few model equations that is to predict the size effect of compressive strength of standard and non-standard cylindrical specimen. However, theses equations did not considered the difference of fracturing mechanism which depends on the strength level. In this paper, model equations to predict compressive strength of concrete considering the size effect and strength level are suggested. The size effect model suggested in this paper shows good prediction compared with the existing test data of various concrete size and strength level.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.9 no.3
• /
• pp.299-307
• /
• 2007

In this study, a new concept for simulating a physical damage of tunnel shotcrete lining due to a long-term chemical deterioration has been proposed. It is known that the damage takes place mainly by internal cracks, reduction of stiffness and strength, which results mainly from volume expansion of the lining and corrosion of cement materials, respectively. This damage mechanism of shotcrete lining appears similar in most kinds of chemical reactions in tunnels. Therefore, the mechanical deterioration mechanism induced by a series of chemical reactions was generalized in this study and mathematically formulated in the framework of thermodynamics. The numerical model was implemented to a 3D finite element code, which can be used to simulate behaviour of tunnel structures undergoing external loads as well as chemical deterioration in time. A number of illustrative examples were given to show a feasibility of the model in tunnel designs.

• Journal of information and communication convergence engineering
• /
• v.10 no.1
• /
• pp.61-65
• /
• 2012

Many public organizations have been adopting and operating various servers. These servers run on Windows, Unix, and Linux operating systems that generally use less than 10% of their capacity. For migrating a public organization to cloud computing, we must first virtualize the server environment. This article proposes a strategy for server virtualization that the National IT Industry Promotion Agency (NIPA) has done and describes the effects of a public organization migrating to cloud computing. The NIPA Computer Center planned an effective virtualization migration on various servers. This project of virtualization migration was conducted with the existing policy of separate x86 servers and Unix servers. There are three popular approaches to server virtualization: a virtual machine model, a paravirtual machine model, and virtualization at the operating system layer. We selected a VMware solution that uses the virtual machine model. We selected servers for virtualization in the following manner. Servers were chosen that had the highest rate of service usage and CPU usage and had been operating for five years or more. However, we excluded servers that require 80% or greater rates of CPU usage. After adopting the server virtualization technique, we consolidated 32 servers into 3 servers. Virtualization is a technology that can provide benefits in these areas: server consolidation and optimization, infrastructure cost reduction and improved operational flexibility, and implementation of a dual computing environment.

• Advances in concrete construction
• /
• v.9 no.4
• /
• pp.355-365
• /
• 2020

The influence of temperature on the material of concrete filled columns (CFCs) under axial loading has been quantitatively studied in this research. CFCs have many various advantages and disadvantages. One of the important inefficiency of classic CFCs design is the practical lack of hooped compression under the operational loads because of the fewer variables of Poisson's rate of concrete compared to steel. This is the reason why the holder tends to break away from the concrete core in elastic stage. It is also suggested to produce concrete filled steel tube columns with an initial compressed concrete core to surpass their design. Elevated temperatures have essentially reduced the strengths of steel tubes and the final capacity of CFCs exposed to fire. Thus, the computation of bearing capacity of concrete filled steel tube columns is studied here. Sometimes, the structures of concrete could be exposed to the high temperatures during altered times, accordingly, outcomes have shown a decrement in compressive-strength, then an increase with the reduction of this content. In addition, the moisture content at the minimal strength is declined with temperature rising. According to Finite Element (FE), the column performance assessment is carried out according to the axial load carrying capacities and the improvement of ductility and strength because of limitations. Self-stress could significantly develop the ultimate stiffness and capacity of concrete columns. In addition, the design equations for the ultimate capacity of concrete columns have been offered and the predictions satisfactorily agree with the numerical results. The proposed based model (FE model of PEC column) 65% aligns with the concrete exposed to high temperature. Therefore, computed solutions have represented a better perception of structural and thermal responses of CFC in fire.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2006.11a
• /
• pp.467-470
• /
• 2006

The earth volume which is the basis of all the construction has gone through great development so far with the use of construction machine; however, systematic studies on the related area is in need since the appropriate compound engineering method of earth volume equipments which is a key factor for shortening the project duration and cost reduction is not systematically established and it is dependent on experience. Reasonable mechanical earth volume should take into consideration of performance and characteristics of the equipment, the kind of project, scale and conditions in advance. Also, the optimum compound engineering should be planned by selecting several available scales of equipment. In this study, the earth volume estimate model is established for optimum compound engineering of earth volume equipment for mechanized earth volume equipment loading and moving stage among many stages of earth volume task using system dynamics technique. The optimum compound engineering model of the earth volume equipment produced as a result of this is expected to make reasonable decisions in the shortest time in selecting earth volume facility.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.53 no.1
• /
• pp.37-45
• /
• 2011

Mandae watershed in Gangwon province has been known as one of soil erosion hot spot watersheds within Hanggang basin. Thus numerous efforts have been made to reduce soil erosion and pollutant loads into receiving watershed. However, proper best management practices have not been suggested because no monitoring flow and water quality data were available. Thus, modeling technique could not be utilized to evaluate water quality issue properly at Mandae watershed to develop and implement the best management practices. In this study, the SWAT model was applied to the Mandae watershed, Gangwon province to evaluate the SWAT prediction ability and water quality improvement with vegetated filter strip (VFS) in this study. The Nash-Sutcliffe model efficiency (NSE) and Coefficient of determination ($R^2$) values for flow simulation were 0.715 and 0.802, respectively, and the NSE and $R^2$ values were 0.903 and 0.920 for T-P simulation indicating the SWAT can be used to simulate flow and T-P with acceptable accuracies. The SWAT model, calibrated for flow and T-P, was used to evaluate water quality improvement with the VFS in agricultural fields. It was found that approximately 56.19 % of T-P could be reduced with vegetated filter strip of 5 m at the edge of agricultural fields within the watershed (34.86 % reduction with VFS of 1m, 48.29 % with VFS of 3 m). As shown in this study, the T-P, which plays key roles in eutrophication in the waterbodies, can be reduced with proper installation of the VFS.