• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.6A
• /
• pp.581-590
• /
• 2010

This study introduces a layered sectional analysis for a PSC girder with a vaiable cross section and curved tendons. To consider the shear equilibrium at a concrete layer with curved tendons, the shear stress distribution has been computed at each section. In addition, to improve the convergence to the solution, a system identification technique is newly adopted in the solution process for strain computation. To examine the feasibility of the proposed approach, a static load test has been conducted for a full scale PSC girder with variable cross section. The prediction shows a good agreement with experiment. It is seen that a uniform cross section has the same moment capacity with a variable cross section while the variable cross section has more shear capacity than the uniform cross section. It is also noted that the maximum displacement of a variable cross section is a little smaller than a uniform cross section.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.507-519
• /
• 2023

Multi-temporal optical images have been utilized for time-series monitoring of croplands. However, the presence of clouds imposes limitations on image availability, often requiring a cloud removal procedure. This study assesses the applicability of various machine learning algorithms for effective cloud removal in optical imagery. We conducted comparative experiments by focusing on two key variables that significantly influence the predictive performance of machine learning algorithms: (1) land-cover types of training data and (2) temporal variability of land-cover types. Three machine learning algorithms, including Gaussian process regression (GPR), support vector machine (SVM), and random forest (RF), were employed for the experiments using simulated cloudy images in paddy fields of Gunsan. GPR and SVM exhibited superior prediction accuracy when the training data had the same land-cover types as the cloud region, and GPR showed the best stability with respect to sampling fluctuations. In addition, RF was the least affected by the land-cover types and temporal variations of training data. These results indicate that GPR is recommended when the land-cover type and spectral characteristics of the training data are the same as those of the cloud region. On the other hand, RF should be applied when it is difficult to obtain training data with the same land-cover types as the cloud region. Therefore, the land-cover types in cloud areas should be taken into account for extracting informative training data along with selecting the optimal machine learning algorithm.

• Journal of Korean Society of Forest Science
• /
• v.112 no.4
• /
• pp.490-501
• /
• 2023

Laboratory column tests were conducted to analyze infiltration and water redistribution processes on the basis of rainfall. To efficiently measure moisture content within soil layers, this research developed a predictive model grounded in a convolutional neural network (CNN), a deep learning technique. The digital images obtained during the column tests were incorporated into the established CNN. The moisture content of each soil layer over time was effectively measured. The measured values were also in relatively good agreement with the moisture content determined using the moisture sensors installed for each soil layer. The use of CNN enabled a comprehensive understanding of continuous moisture distribution within the soil layers, as well as the infiltration process according to soil texture and initial moisture content conditions.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.67-77
• /
• 2023

This study represents an innovative research conducted in the smart farm environment, developing a deep learning-based disease and pest detection model and applying it to the Intelligent Internet of Things (IoT) platform to explore new possibilities in the implementation of digital agricultural environments. The core of the research was the integration of the latest ImageNet models such as Pseudo-Labeling, RegNet, EfficientNet, and preprocessing methods to detect various diseases and pests in complex agricultural environments with high accuracy. To this end, ensemble learning techniques were applied to maximize the accuracy and stability of the model, and the model was evaluated using various performance indicators such as mean Average Precision (mAP), precision, recall, accuracy, and box loss. Additionally, the SHAP framework was utilized to gain a deeper understanding of the model's prediction criteria, making the decision-making process more transparent. This analysis provided significant insights into how the model considers various variables to detect diseases and pests.

• Korea Trade Review
• /
• v.46 no.2
• /
• pp.19-38
• /
• 2021

This study aims to analyze the foreign asset leverage effect on Korean oil & gas companies' foreign profits and to maintain the appropriate foreign asset volume for reducing exchange risk. For a long time, large Korean companies, including oil companies, overheld foreign currency liabilities. For this reason, most large companies have been burdened to hedge exchange risk and this excess limit holding deteriorated total profit and reduced foreign currency asset management efficiency. Our paper proceeds in presenting a three-stage analysis considering diversified exchange risk factors through estimation on transformation of foreign transactions a/c including annual trends of foreign asset and industry specifics. We also supplement incomplete the estimation method through a practical hedging case investigation. Our research parts are differentiated on the analyzing four periods considering period-specifics The FER value of the oil firms ranged from -0.3 to +2.3 over the entire period. The results of the FER Value are volatile and irregular; those results do not represent the industry standard comparative index. The Korean oil firms are over the credit limit without accurate prediction and finance high interest rate funds from foreign-owned banks on the basis on a biased relationship. Since the IMF crisis, liabilities of global firms have decreased. Above all, oil firms need to finance a minimum limit without opportunity losses on the demand forecast and prepare for uncertainty in the market. To reduce exchange risk from the over-the-limit position, we must consider factors that affect the corporate exchange risk on the entire business process, including the contract phase.

• Composites Research
• /
• v.36 no.5
• /
• pp.315-320
• /
• 2023

In the manufacturing process of thermosetting carbon fiber composite materials using an autoclave, the internal temperature changes according to the set temperature cycle. This temperature change causes the resin in the composite material to cure. Heat is generated through the chemical reaction of the resin, which can result in a difference between the temperature inside the autoclave and the temperature of the composite material. Previous research assumed that the temperatures of the composite material and the autoclave were the same and analyzed to predict the residual stress and thermal deformation after manufacturing. However, these stresses and deformations depend on the temperature and degree of cure of the composite material. Therefore, this study verifies a thermal-chemical model analysis technique that takes into account the heat generated by the chemical reaction of the resin to accurately calculate the temperature and degree of cure. Additionally, case studies were conducted for different thicknesses to investigate whether this model exhibits similar trends across varying thicknesses.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.112-118
• /
• 2023

As technology advances, the need for enhanced preparedness against cyber-attacks becomes an increasingly critical problem. Therefore, it is imperative to consider various circumstances and to prepare for cyber-attack strategic technology. This paper proposes a method to solve network security problems by applying reinforcement learning to cyber-security. In general, traditional static cyber-security methods have difficulty effectively responding to modern dynamic attack patterns. To address this, we implement cyber-attack scenarios such as 'Tiny Alpha' and 'Small Alpha' and evaluate the performance of various reinforcement learning methods using Network Attack Simulator, which is a cyber-attack simulation environment based on the gymnasium (formerly Open AI gym) interface. In addition, we experimented with different RL algorithms such as value-based methods (Q-Learning, Deep-Q-Network, and Double Deep-Q-Network) and policy-based methods (Actor-Critic). As a result, we observed that value-based methods with discrete action spaces consistently outperformed policy-based methods with continuous action spaces, demonstrating a performance difference ranging from a minimum of 20.9% to a maximum of 53.2%. This result shows that the scheme not only suggests opportunities for enhancing cybersecurity strategies, but also indicates potential applications in cyber-security education and system validation across a large number of domains such as military, government, and corporate sectors.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.33 no.6
• /
• pp.276-281
• /
• 2023

With the high design freedom of the additive manufacturing process, there is a growing interest in multi-dimensional lattice structures among researchers, who are studying intricate structural modeling that is challenging to produce using conventional manufacturing processes. In the case of titanium alloy implants for human insertion, a multi-dimensional lattice structure is employed to ensure compatibility with bones, adjusting strength and elastic modulus to levels similar to those of bones. Therefore, securing a database on the mechanical properties based on lattice structure design variables and the development of related simulation techniques are believed to efficiently facilitate the customization of implants. In this study, lattice structures were additively manufactured using Ti-6Al-4V alloy, and the elastic modulus was measured based on design parameters. The results were compared with simulations, and an approach to finite element analysis for accurate prediction of the elastic modulus was proposed.

• Journal of The Korean Astronomical Society
• /
• v.56 no.1
• /
• pp.11-22
• /
• 2023

We report the result of a high-resolution spectroscopic study on seven magnesium (Mg) enhanced stars. The high Mg abundances in these stars imply that they were born in an environment heavily affected by the nucleosynthesis products of massive stars. We measure abundances of 16 elements including Mg and they show various abundance patterns implying their diverse origin. Three of our program stars show a very high Mg to Si ratio ([Mg/Si] ≈ 0.18-0.25), which might be well explained by fall-back supernovae or by supernovae with rapid rotating progenitors having an initial mass higher than about 20 M_⊙. Another three of our program stars have high light to heavy s-process element ratios ([Y/Ba] ≈ 0.30-0.44), which are consistent with the theoretical prediction of the nucleosynthesis in rapidly rotating massive stars with an initial mass of about M = 40 M_⊙. We also report a star having both high Y ([Y/Fe] = 0.2) and Ba ([Ba/Fe] = 0.28) abundance ratios, and it also shows the highest Zn abundance ratio ([Zn/Fe] = 0.27) among our sample, implying the nucleosynthesis by asymmetric supernova explosion induced by very rapid rotation of a massive progenitor having an initial mass between 20 M_⊙ ≲ M ≲ 40 M_⊙. A relative deficiency of odd-number elements, which would be a signature of the pair-instability nucleosynthesis, is not found in our sample.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.103-112
• /
• 2023

Recently, the need to prevent battery fires and accidents has emerged, as the use of lithium-ion batteries has increased. In order to prevent accidents, it is necessary to predict the state of health (SOH) and check the replacement timing of the battery with a lot of degradation. This paper proposes a model for predicting the degradation state of a battery by using four battery degradation indicators: maximum voltage arrival time, current change time, maximum temperature arrival time, and incremental capacity (IC) that can be obtained in the battery charging process, and LSTM using an attention mechanism. The performance of the proposed model was measured using the NASA battery data set, and the predictive performance was improved compared to that of the general LSTM model, especially in the SOH 90-70% section, which is close to the battery replacement cycle.