• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.229-229
• /
• 2023

강화학습은 에이전트(agent)가 주어진 환경(environment)과의 상호작용을 통해서 상태(state)를 변화시켜가며 최대의 보상(reward)을 얻을 수 있도록 최적의 행동(action)을 학습하는 기계학습법을 의미한다. 최근 알파고와 같은 게임뿐만 아니라 자율주행 자동차, 로봇 제어 등 다양한 분야에서 널리 사용되고 있다. 상수도관망 분야의 경우에도 펌프 운영, 밸브 운영, 센서 최적 위치 선정 등 여러 문제에 적용되었으나, 설계에 강화학습을 적용한 연구는 없었다. 설계의 경우, 관망의 크기가 커짐에 따라 알고리즘의 탐색 공간의 크기가 증가하여 기존의 최적화 알고리즘을 이용하는 것에는 한계가 존재한다. 따라서 본 연구는 강화학습을 이용하여 상수도관망의 구성요소와 환경요인 간의 복잡한 상호작용을 고려하는 설계 방법론을 제안한다. 모델의 에이전트를 딥 강화학습(Deep Reinforcement Learning)으로 구성하여, 상태 및 행동 공간이 커 발생하는 고차원성 문제를 해결하였다. 또한, 해당 모델의 상태 및 보상으로 절점에서의 압력 및 수요량과 설계비용을 고려하여 적절한 수량과 수압의 용수 공급이 가능한 경제적인 관망을 설계하도록 하였다. 모델의 행동은 실제로 공학자가 설계하듯이 절점마다 하나씩 차례대로 다른 절점과의 연결 여부를 결정하는 것으로, 이를 통해 관망의 레이아웃(layout)과 관경을 결정한다. 본 연구에서 제안한 방법론을 규모가 큰 그리드 네트워크에 적용하여 모델을 검증하였으며, 고려해야 할 변수의 개수가 많음에도 불구하고 목적에 부합하는 관망을 설계할 수 있었다. 모델 학습과정 동안 에피소드의 평균 길이와 보상의 크기 등의 변화를 비교하여, 제안한 모델의 학습 능력을 평가 및 보완하였다. 향후 강화학습 모델을 통해 신뢰성(reliability) 또는 탄력성(resilience)과 같은 시스템의 성능까지 고려한 설계가 가능할 것으로 기대한다.

• Biomolecules & Therapeutics
• /
• v.31 no.5
• /
• pp.573-582
• /
• 2023

Muscle atrophy is characterized by the loss of muscle function. Many efforts are being made to prevent muscle atrophy, and exercise is an important alternative. Methylglyoxal is a well-known causative agent of metabolic diseases and diabetic complications. This study aimed to evaluate whether methylglyoxal induces muscle atrophy and to evaluate the ameliorative effect of moderate-intensity aerobic exercise in a methylglyoxal-induced muscle atrophy animal model. Each mouse was randomly divided into three groups: control, methylglyoxal-treated, and methylglyoxal-treated within aerobic exercise. In the exercise group, each mouse was trained on a treadmill for 2 weeks. On the last day, all groups were evaluated for several atrophic behaviors and skeletal muscles, including the soleus, plantaris, gastrocnemius, and extensor digitorum longus were analyzed. In the exercise group, muscle mass was restored, causing in attenuation of muscle atrophy. The gastrocnemius and extensor digitorum longus muscles showed improved fiber cross-sectional area and reduced myofibrils. Further, they produced regulated atrophy-related proteins (i.e., muscle atrophy F-box, muscle RING-finger protein-1, and myosin heavy chain), indicating that aerobic exercise stimulated their muscle sensitivity to reverse skeletal muscle atrophy. In conclusion, shortness of the gastrocnemius caused by methylglyoxal may induce the dynamic imbalance of skeletal muscle atrophy, thus methylglyoxal may be a key target for treating skeletal muscle atrophy. To this end, aerobic exercise may be a powerful tool for regulating methylglyoxal-induced skeletal muscle atrophy.

• Journal of Korean Association for Spatial Structures
• /
• v.23 no.3
• /
• pp.87-94
• /
• 2023

Chloride is one of the most common threats to reinforced concrete (RC) durability. Alkaline environment of concrete makes a passive layer on the surface of reinforcement bars that prevents the bar from corrosion. However, when the chloride concentration amount at the reinforcement bar reaches a certain level, deterioration of the passive protection layer occurs, causing corrosion and ultimately reducing the structure's safety and durability. Therefore, understanding the chloride diffusion and its prediction are important to evaluate the safety and durability of RC structure. In this study, the chloride diffusion coefficient is predicted by machine learning techniques. Various machine learning techniques such as multiple linear regression, decision tree, random forest, support vector machine, artificial neural networks, extreme gradient boosting annd k-nearest neighbor were used and accuracy of there models were compared. In order to evaluate the accuracy, root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2) were used as prediction performance indices. The k-fold cross-validation procedure was used to estimate the performance of machine learning models when making predictions on data not used during training. Grid search was applied to hyperparameter optimization. It has been shown from numerical simulation that ensemble learning methods such as random forest and extreme gradient boosting successfully predicted the chloride diffusion coefficient and artificial neural networks also provided accurate result.

• Proceedings of the Korean Environmental Sciences Society Conference
• /
• 2020.10a
• /
• pp.221-221
• /
• 2020

Curcumin, a hydrophobic polyphenol derived from turmeric, has been used a food additive and as a herbal medicine for the treatment of various diseases. In the present study, we found the functional role of a nanosphere loaded with curcumin (CN) in the promotion of the motility of human umbilical cord blood derived mesenchymal stem cells (hUCB-MSCs) during the wound closure. We found that the efficacy of hUCB-MSCs migration induced by CN was 1000-fold higher than that of curcumin powder. CN significantly increased the motility of hUCB-MSCs by activating c-Src, which is responsible for the phosphorylation of protein kinase C (PKC) and extracellular signal-regulated kinase (ERK). CN induced the expression levels of α-actinin-1, profilin-1 and filamentous-actin, as regulated by the phosphorylation of nuclear factor-kappa B during its promotion of cell migration. In a mouse skin excisional wound model, we found that transplantation of UCB-MSCs pre-treated with CN enhances wound closure, granulation, and re-epithelialization at mouse skin wound sites. These results indicate that CN is a functional agent that promotes the mobilization of UCB-MSCs for cutaneous wound repair.

• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2022.09a
• /
• pp.92-92
• /
• 2022

Under the COVID-19 pandemic, interest in immune enhancement is increasing. Although the immune-enhancing activity of plants of the genus Hibiscus has been reported, there is no study on the immune-enhancing activity of H. syriacus. Thus, in this study, we investigated the immune-enhancing activity of Hibiscus syriacus leaves (HSL) in mouse macrophages, RAW264.7 cells, and immunosuppressed mice. HSL increased the production of immunostimulatory factors such as nitric oxide (NO), inducible nitric oxide synthase (iNOS), interleukin-1β (IL-1β), and tumor necrosis factor-α (TNF-α) and activated the phagocytosis in RAW264.7 cells. The HSL-mediated production of immunostimulatory factors was dependent on toll-like receptor 4 (TLR4), p38, and c-Jun N-terminal kinase (JNK) in RAW264.7 cells. In the immunosuppressed mouse model, HSL increased the spleen index, the levels of the cytokines, and the numbers of lymphocytes, neutrophils, and monocytes. Taken together, HSL may be considered to have immune-enhancing activity and be expected to be used as a potential immune-enhancing agent.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.6
• /
• pp.1001-1020
• /
• 2023

As massive increase in remote work since COVID-19, the boundaries between the inside and outside of corporate networks have become blurred. As a result, traditional perimeter security has stagnated business productivity and made it difficult to manage risks such as information leakage. The zero trust architecture model has emerged, but it is difficult to apply to IT environments composed of various companies. Therefore, using the remote work system configuration as an example, we presented a configuration and methodology that can apply zero trust models even in various network environments such as on-premise, cloud, and network separation. Through this, we aim to contribute to the creation of a safe and convenient cyber environment by providing guidance to companies that want to apply zero trust architecture, an intelligent system that actively responds to cyber threats.

• Smart Media Journal
• /
• v.12 no.9
• /
• pp.124-133
• /
• 2023

Currently, Korea shares culture, economy, and society together as a member of the international community along with rapid economic growth. In particular, in the 2000s, the construction of local cultural performance halls has been promoted through efforts and methods for the development of local culture. As a result, many local governments built medium-sized or larger performance halls, and achieved both quantitative and qualitative effects by satisfying citizens and attracting visitors. However, this study aims to analyze the safety of the space used by many visitors at the same time and whether an effective evacuation plan is applied to frequent disasters and disaster situations in recent years.

• Journal of the Korean Society of Food Culture
• /
• v.39 no.1
• /
• pp.74-81
• /
• 2024

Ulcerative colitis (UC) is a chronic inflammatory intestinal disease characterized by an imbalance in immune function and the overexpression of inflammatory cytokines and mediators. Vitamin B2, also known as riboflavin (Libof), is an essential water-soluble vitamin with numerous beneficial properties, including antioxidant, anti-aging, anti-inflammatory, anti-nociceptive, and anti-cancer effects. In this study, we aimed to investigate the protective effects of Libof on dextran sulfate sodium (DSS)-induced experimental colitis. The C57BL/6 mice were used as the in vivo model of chronic colitis to investigate the anti-inflammatory effects of Libof. RAW 264.7 cells were used for the in vitro investigation of the molecular mechanisms underlying these effects. In vivo, Libof alleviated the DSS-induced disease activity index (DAI), colon length shortening, and colonic pathological damage. In vitro, Libof inhibited lipopolysaccharide (LPS)-induced tumor necrosis factor (TNF)-alpha and interleukin (IL)-6 production in RAW 264.7 cells. Moreover, Libof inhibited LPS-induced nitric oxide (NO) production and inducible nitric oxide synthase (iNOS) expression in RAW 264.7 cells. In conclusion, these findings indicate that Libof shows potential as an agent for the treatment of UC.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.131-139
• /
• 2024

Crew Transfer Vessels (CTVs) are primarily used for the maintenance of offshore wind farms. Despite being manually operated by professional captains and crew, collisions with other ships and marine structures still occur. To prevent this, the introduction of autonomous navigation systems to CTVs is necessary. In this study, research on the obstacle avoidance system of the autonomous navigation system for CTVs was conducted. In particular, research on obstacle avoidance simulation for CTVs using deep reinforcement learning was carried out, taking into account the currents and wind loads in offshore wind farms. For this purpose, 3 degrees of freedom ship maneuvering modeling for CTVs considering the currents and wind loads in offshore wind farms was performed, and a simulation environment for offshore wind farms was implemented to train and test the deep reinforcement learning agent. Specifically, this study conducted research on obstacle avoidance maneuvers using MATD3 within deep reinforcement learning, and as a result, it was confirmed that the model, which underwent training over 10,000 episodes, could successfully avoid both static and moving obstacles. This confirms the conclusion that the application of the methods proposed in this study can successfully facilitate obstacle avoidance for autonomous navigation CTVs within offshore wind farms.

• Journal of Web Engineering
• /
• v.14 no.10
• /
• pp.2164-2174
• /
• 2022

Obesity treatment efficiency can be increased by targeting both central and peripheral pathways. In a previous study, we identified two natural compounds (hispidulin and p-synephrine) that affect adipocyte differentiation. We tested whether obesity treatment efficiency may be improved by adding an appetite-controlling agent to the treatment in the present study. Alkaloids, such as p-octopamine, are adrenergic agonists and are thus used as dietary supplements to achieve weight loss. Here, we assessed anti-obesity effects of a mixture of p-synephrine, p-octopamine HCl, and hispidulin (SOH) on murine preadipocyte cells and on mice receiving a high-fat diet (HFD). SOH showed stronger inhibition of the formation of red-stained lipid droplets than co-treatment with hispidulin and p-synephrine. Moreover, SOH reduced the expression of adipogenic marker proteins, including CCAAT/enhancer-binding protein alpha, CCAAT/enhancer-binding protein beta, and peroxisome proliferator-activated receptor gamma. In the HFD-induced obesity model, body weight and dietary intake were lower in mice treated with SOH than in the controls. Additionally, liver weight and the levels of alanine aminotransferase and total cholesterol were lower in SOH-treated mice than in the controls. In conclusion, our results suggest that consumption of SOH may be a potential alternative strategy to counteract obesity.