• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.12
• /
• pp.320-330
• /
• 2020

Fire is difficult to achieve good performance in image detection using deep learning because of its high irregularity. In particular, there is little data on fire detection in underground utility facilities, which have poor light conditions and many objects similar to fire. These make fire detection challenging and cause low performance of deep learning models. Therefore, this study proposed a fire detection model using deep learning and estimated the performance of the model. The proposed model was designed using a combination of a basic convolutional neural network, Inception block of GoogleNet, and Skip connection of ResNet to optimize the deep learning model for fire detection under underground utility facilities. In addition, a training technique for the model was proposed. To examine the effectiveness of the method, the trained model was applied to fire images, which included fire and non-fire (which can be misunderstood as a fire) objects under the underground facilities or similar conditions, and results were analyzed. Metrics, such as precision and recall from deep learning models of other studies, were compared with those of the proposed model to estimate the model performance qualitatively. The results showed that the proposed model has high precision and recall for fire detection under low light intensity and both low erroneous and missing detection capabilities for things similar to fire.

• Journal of Korea Water Resources Association
• /
• v.55 no.7
• /
• pp.545-556
• /
• 2022

It is recommended to use long-term hydrometeorological data for more than the service life of the hydraulic structures and water resource planning. For the purpose of expanding rainfall data, stochastic simulation models, such as Modified Bartlett-Lewis Rectangular Pulse (BLRP) and Neyman-Scott Rectangular Pulse (NSRP) models, have been widely used. The optimal parameters of the model can be estimated by repeatedly comparing the statistical moments defined through a combination of parameters of the probability distribution in the optimization context. However, parameter estimation using relatively small observed rainfall statistics corresponds to an ill-posed problem, leading to an increase in uncertainty in the parameter estimation process. In addition, as shown in previous studies, extreme values are underestimated because objective functions are typically defined by the first and second statistical moments (i.e., mean and variance). In this regard, this study estimated the parameters of the NSRP model using the objective function with the third moment and compared it with the existing approach based on the first and second moments in terms of estimation of extreme rainfall. It was found that the first and second moments did not show a significant difference depending on whether or not the skewness was considered in the objective function. However, the proposed model showed significantly improved performance in terms of estimation of design rainfalls.

• Journal of Mushroom
• /
• v.20 no.3
• /
• pp.178-182
• /
• 2022

Despite the long history of mushroom use, studies examining the genetic function of mushrooms and the development of new varieties via bio-molecular methods are significantly lacking compared to those examining other organisms. However, owing to recent developments, attempts have been made to use a novel gene-editing technique involving CRISPR/Cas9 technology and genetic scissors in mushroom studies. In particular, research is actively being conducted to utilize ribonucleoprotein particles (RNPs) that can be genetically edited with high efficiency without foreign gene insertion for ease of selection. However, RNPs are too large for Cas9 protein to pass through the cell membrane of the protoplasmic reticulum. Furthermore, guide RNA is unstable and can be easily decomposed, which remarkably affects gene editing efficiency. In this study, nanoparticles were used to mitigate the shortcomings of RNP-based gene editing techniques and to obtain transformants stably. We used Lentinula edodes (shiitake mushroom) Sanjo705-13 monokaryon strain, which has been successfully used in previous genome editing experiments. To identify a suitable osmotic buffer for the isolation of protoplast, 0.6 M and 1.2 M sucrose, mannitol, sorbitol, and KCl were treated, respectively. In addition, with various nanoparticle-forming materials, experiments were conducted to confirm genome editing efficiency via the formation of nanoparticles with calcium phosphate (CaP), which can be bound to Cas9 protein without any additional amino acid modification. RNPs/NP complex was successfully formed and protected nuclease activity with nucleotide sequence specificity.

• Economic Analysis
• /
• v.27 no.4
• /
• pp.1-42
• /
• 2021

The outlook for Korea's consumer price inflation rate has a profound impact not only on the Bank of Korea's operation of the inflation target system but also on the overall economy, including the bond market and private consumption and investment. This study presents the prediction results of consumer price inflation in Korea for the next three years. To this end, first, model selection is performed based on the out-of-sample predictive power of autoregressive distributed lag (ADL) models, AR models, small-scale vector autoregressive (VAR) models, and large-scale VAR models. Since there are many potential predictors of inflation, a Bayesian variable selection technique was introduced for 12 macro variables, and a precise tuning process was performed to improve predictive power. In the case of the VAR model, the Minnesota prior distribution was applied to solve the dimensional curse problem. Looking at the results of long-term and short-term out-of-sample predictions for the last five years, the ADL model was generally superior to other competing models in both point and distribution prediction. As a result of forecasting through the combination of predictions from the above models, the inflation rate is expected to maintain the current level of around 2% until the second half of 2022, and is expected to drop to around 1% from the first half of 2023.

• Korean Chemical Engineering Research
• /
• v.61 no.1
• /
• pp.123-141
• /
• 2023

A sufficient amount of data with quality is needed for training artificial neural networks (ANNs). However, developing ANN models with a small amount of data often appears in engineering fields. This paper presented an ANN model to improve prediction performance of the ammonia emission amount with 83 data. The ammonia emission rate included eleven inputs and two outputs (maximum ammonia loss, N_max and time to reach half of N_max, K_m). Categorical input variables were transformed into multi-dimensional equal-distance variables, and 13 data were added into 66 training data using a generative adversarial network. Hyperparameters (number of layers, number of neurons, and activation function) of ANN were optimized using Gaussian process. Using 17 test data, the previous ANN model (Lim et al., 2007) showed the mean absolute error (MAE) of K_m and N_max to 0.0668 and 0.1860, respectively. The present ANN outperformed the previous model, reducing MAE by 38% and 56%.

• Korean Journal of Microbiology
• /
• v.40 no.2
• /
• pp.147-153
• /
• 2004

Protein modification by N-acetyl-${\beta}$-D-glucosamine (O-G1cNAc) on the hydroxyl groups of Ser or Thr ubiq-uitously occurs in eukaryotic cells and is involved in many cellular phenomena. The level of O-G1cNAc-mod-ified protein is regulated by OGT and O-GlcNAcase enzymes. We have tried to produce recombinant O-GlcNAcase in E. coli as an effort to establish in vitro screening system for modulators of O-GlcNAcase. The culture conditions for improvement of O-GlcNAcase productivity, were as follows: induction temperature, $30^{\circ}C$; the concentration of L-arabinose, 0.02% and induction time, 5 hr. Under these culture conditions, E. coli cells containing O-GlcNAcase gene had no enzyme activity until up to 3 hr culture. However, O-GlcNAcase activity dramatically increased from 3 to 5 hr culture. It almost maintained the same level after 5 hr culture. Western blot analysis verified the amount of expressed O-GlcNAcase increased with culture time, being con-sistent with activity data. The optimal reaction condition determined in this study was as follows: protein quan-tity, $5{\mu}g$; reaction time, 30 min; reaction temperature, $45^{\circ}C$; substrate concentration, 2 mM; reaction pH, 6.5. Methanol had little effect on O-GlcNAcase activity and 90% of activity were retained at 10%. Only 15% resid-ual activity were detected at 5% of chloroform.

• Journal of the Korean Society of Radiology
• /
• v.18 no.2
• /
• pp.127-133
• /
• 2024

The elbow joint is made up of three different bones. X-rays or other radiological exams are commonly used to diagnose elbow injuries or disorders caused by physical activity and external forces. Previous research on the elbow joint reported a new examination method that meets the imaging evaluation criteria in the tilt position by Z-axis elevation of the forearm. Therefore, this study aims to design an optimized instrument and develop an aid applicable to other upper extremity exams. After completing the 2D drawing and 3D modeling design, the final design divided into four parts was fabricated with a 3D printer using ABS plastic and assembled. The developed examination aid consists of a four-stage Z-axis elevation tilt angle function (0°, 5°, 10°, and 15°) and can rotate and fixate 360° in 1-degree increments. It was designed to withstand a maximum equivalent stress of 56.107 Pa and a displacement of 1.6548e-5 mm through structural analysis to address loading issues caused by cumulative frequency of use and physical utilization. In addition to X-ray exams of the elbow joint, the developed aid can be used for shoulder function tests by rotating the humerus and also be applied to MRI and CT exams as it is made of non-metallic materials. It will contribute to the accuracy and efficiency of medical imaging diagnosis through clinical applications of various devices and medical imaging exams in the future.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.199-207
• /
• 2024

Today, AI image creation technology is being expanded and utilized across industries. Accordingly, various AI image creation programs optimized for the fashion industry are being developed and commercialized. In this study, we compared and analyzed the visual characteristics of fashion images created by AI image creation programs such as Playground, Midjourney, and The New Black to identify the characteristics of each program and point out areas where each program can be used and problems. The results are as follows: First, while Playground and Midjourney intuitively applied the contents of the command to create images that were different from actual fashion trends, Dannew Black created images that were relatively similar to fashion trends. Second, while Playground separates or combines images corresponding to the command content, Midjourny tends to create new images by adding and fusing various details. Third, in Playground, colors not included in the command appear randomly, and in The New Black, colors not included in the command appear coordinated, and Midjourney generates the color specified in the command relatively accurately. In conclusion, Midjourney can be used when seeking inspiration for developing unique and creative fashion designs, and The New Black can be helpful in referencing fashion trends or fashion styling. On the other hand, playgrounds can be somewhat confusing when it comes to color creation, so this is something to be careful about. It is expected that AI image creation tools can be used more efficiently in fashion design development.

• Journal of Chest Surgery
• /
• v.41 no.5
• /
• pp.550-562
• /
• 2008

Background: We attempted to reproduce a previously reported method that is known to be effective for decellularization, and we sought to find the optimal condition for decellularization by introducing some modifications to this method. Material and Method: Porcine semilunar valves, arterial walls and pericardium were processed for decellularization with using a variety of combinations and concentrations of decellularizing agents under different conditions of temperature, osmolarity and incubation time. The degree of decellularization and the preservation of the extracellular matrix were evaluated by staining with hematoxylin and eosin and with alpha-Gal and DAPI in some of the decellularized tissues. Result: Decellularization was achieved in the specimens that were treated with sodium deoxycholate, sodium dodesyl sulfate, Triton X-100 and sodium dodesyl sulfate with Triton X-100 as single-step methods, and this was also achieved in the specimens that were treated with hypotonic solution ${\rightarrow}$ Triton X-100 ${\rightarrow}$ sodium dodesyl sulfate, sodium deoxycholate ${\rightarrow}$ hypotonic solution ${\rightarrow}$ sodium dodesyl sulfate, and hypotonic solution sodium dodesyl sulfate as multi-step methods. Conclusion: Considering the number and the amount of the chemicals that were used, the incubation time and the degree of damage to the extracellular matrix, a single-step method with sodium dodesyl sulfate and Triton X-100 and a multi-step method with hypotonic solution followed by sodium dodesyl sulfate were both relatively optimal methods for decellularization in this study.

• Journal of Bio-Environment Control
• /
• v.25 no.4
• /
• pp.225-231
• /
• 2016

Glasshouse heating package technologies to improve energy usage efficiency in winter were developed. Heating package was composed of the ground water source heat pump with heating capacity of 105kW, the aluminum multi-layer thermal curtain with six layers of different materials and the root zone local heater with XL pipes of ${\phi}20mm$. Venlo type glasshouse($461m^2$) with the heating package was compared with the same type and area control glasshouse with the light oil boiler, the usual non-woven fabric thermal curtain with respect to the glasshouse inside temperature, relative humidity, crop growth, and heating energy consumption. The results of test in paprika cultivation glasshouses showed that the air temperature inside glasshouse with aluminum multi-layer thermal curtain was maintained $2.2^{\circ}C$ higher than that of control glasshouse in un-heating night time and the temperature in bed with root zone local heating was $4.7^{\circ}C$ higher than that in bed without local heating. Average heating coefficient of performance(COP) of the ground water source heat pump used in paprika cultivation was 3.7 and the glasshouse inside temperature was maintained at $21^{\circ}C$ of heating set up temperature. The heating energy consumptions per 10a were measured at 14,071L of light oil and 364kWh of electric power for the control glasshouse and 35,082kWh for the glasshouse applied heating package. As results, the heating cost of the glasshouse applied heating package was 87 percent lower than that of control glasshouse. The growths of paprika in glasshouses of control and applied heating package did not show any significant difference.