• Journal of Korea Water Resources Association
• /
• v.56 no.11
• /
• pp.801-813
• /
• 2023

Recently, as studies about Artificial Neural Network (ANN) are actively progressing, studies for predicting water quality of rivers using ANN are being conducted. However, it is difficult to analyze the operation process inside ANN, because ANN is form of Black-box. Although eXplainable Artificial Intelligence (XAI) is used to analyze the computational process of ANN, research using XAI technology in the field of water resources is insufficient. This study analyzed Multi Layer Perceptron (MLP) to predict Water Temperature (WT), Dissolved Oxygen (DO), hydrogen ion concentration (pH) and Chlorophyll-a (Chl-a) at the Dasan water quality observatory in the Nakdong river using Layer-wise Relevance Propagation (LRP) among XAI technologies. The MLP that learned water quality was analyzed using LRP to select the optimal input data to predict water quality, and the prediction results of the MLP learned using the optimal input data were analyzed. As a result of selecting the optimal input data using LRP, the prediction accuracy of MLP, which learned the input data except daily precipitation in the surrounding area, was the highest. Looking at the analysis of MLP's DO prediction results, it was analyzed that the pH and DO a had large influence at the highest point, and the effect of WT was large at the lowest point.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.729-736
• /
• 2023

Traditionally, Germany, a conservative welfare state, has pursued a male breadwinner model based on gender division of labor. For a long time, Germany tried to address low fertility through economic support centered on cash benefits, but it was not successful. In 2007, the German government began to shift the paradigm of family policy for work-life balance under the slogan of "A mix of time policy, income transfer, and infrastructure." When the issue of low birth rates emerged as a national concern in Germany, there was a growing social sentiment that not only the government but also private companies should contribute to increasing fertility by providing family-friendly personnel policies and working conditions. Private companies have been voluntarily improving family-friendly working conditions beyond legal obligations, aiming to secure personnel and prevent turnover. Germany's fertility rate is currently rising toward the European average level in 2023, which can be attributed to the government's work-life balance policies and the participation of private companies. In terms of improving work-life balance policies in Korea, it has been proposed to change the perception of the need for fathers to participate in child care, to make parental leave compulsory for men, to guarantee employment for women after childbirth, to expand child care facilities, and to revitalize family-friendly policies in companies.

• Journal of the Korean Applied Science and Technology
• /
• v.40 no.5
• /
• pp.1136-1148
• /
• 2023

The purpose of this study was to examine the relationship between leisure passion, self-realization, and psychological well-being for baby boomers who regularly participate in leisure activities, and to provide basic data for baby boomers to participate in leisure sports based on this. This study required the study of baby boomers born between 1995 and 1963 who participated in leisure activities in Seoul and Gyeonggi Province to fill out a questionnaire using the convenient sampling method among non-probability sampling. Frequency analysis, confirmatory factor analysis, reliability analysis, correlation analysis, and structural equation model analysis were conducted through the SPSS 20.0 program to achieve the purpose of the study with a total of 310 data processing analysis. The results of this study are as follows. First, it was found that leisure passion has an effect on self-realization. Second, self-realization is affecting psychological well-being. Third, it was found that leisure passion affects psychological well-being. Therefore, it was found that all paths had a statistically significant effect on the relationship between leisure passion, self-realization, and psychological well-being according to the leisure participation of baby boomers. In addition, leisure passion was found to have an indirect effect on psychological well-being, indicating that it had a mediating effect.

• Korean Journal of Environmental Biology
• /
• v.41 no.3
• /
• pp.204-214
• /
• 2023

This study aimed to conduct a comprehensive assessment of the potential impact of deforestation and forest restoration on carbon storage in North Korea until 2050, employing rigorous analyses of trends of land use change in the past periods and projecting future land use change scenarios. We utilized the CA-Markov model, which can reflect spatial trends in land use changes, and verified the impact of forest restoration strategies on carbon storage by creating land use change scenarios (reforestation and non-reforestation). We employed two distinct periods of land use maps (2000 to 2010 and 2010 to 2020). To verify the overall terrestrial carbon storage in North Korea, our evaluation included estimations of carbon storage for various elements such as above-ground, below-ground, soil, and debris (including litters) for settlement, forest, cultivated, grass, and bare areas. Our results demonstrated that effective forest restoration strategies in North Korea have the potential to increase carbon storage by 4.4% by the year 2050, relative to the carbon storage observed in 2020. In contrast, if deforestation continues without forest restoration efforts, we predict a concerning decrease in carbon storage by 11.5% by the year 2050, compared to the levels in 2020. Our findings underscore the significance of prioritizing and continuing forest restoration efforts to effectively increase carbon storage in North Korea. Furthermore, the implications presented in this study are expected to be used in the formulation and implementation of long-term forest restoration strategies in North Korea, while fostering international cooperation towards this common environmental goal.

• Tunnel and Underground Space
• /
• v.33 no.5
• /
• pp.399-413
• /
• 2023

The present study conducted a numerical modeling of CO₂ injection at the Janggi Basin using the TOUGH-FLAC simulator, and examined the hydro-mechanical stability of the aquifer and the fault. Based on the site investigations and a 3D geological model of the target area, we simulated the injection of 32,850 tons of CO₂ over a 3-year period. The analysis of CO₂ plume with different values of the aquifer permeability revealed that assuming a permeability of 10^-14 m² the CO₂ plume exhibited a radial flow and reached the fault after 2 years and 9 months. Conversely, a higher permeability of 10^-13 m² resulted in predominant westward flow along the reservoir, with negligible impact on the fault. The pressure changes around the injection well remained below 0.6 MPa over the period, and the influence on the hydro-mechanical stability of the reservoir and fault was found to be insignificant.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.113-119
• /
• 2023

Most infrastructure structures were completed during periods of economic growth. The number of infrastructure structures reaching their lifespan is increasing, and the proportion of old structures is gradually increasing. The functions and performance of these structures at the time of design may deteriorate and may even lead to safety accidents. To prevent this repercussion, accurate inspection and appropriate repair are requisite. To this end, demand is increasing for computer vision and deep learning technology to accurately detect even minute cracks. However, deep learning algorithms require a large number of training data. In particular, label images indicating the location of cracks in the image are required. To secure a large number of those label images, a lot of labor and time are consumed. To reduce these costs as well as increase detection accuracy, this study proposed a learning structure based on mean teacher method. This learning structure was trained on a dataset of 900 labeled image dataset and 3000 unlabeled image dataset. The crack detection network model was evaluated on over 300 labeled image dataset, and the detection accuracy recorded a mean intersection over union of 89.23% and an F1 score of 89.12%. Through this experiment, it was confirmed that detection performance was improved compared to supervised learning. It is expected that this proposed method will be used in the future to reduce the cost required to secure label images.

• Journal of Korea Foundry Society
• /
• v.43 no.6
• /
• pp.271-278
• /
• 2023

In the present study, A356 melt degassing experiments were conducted under various impeller rotation speed and inert gas flow rate conditions to determine changes in the melt temperature, composition and density during a degassing treatment. The melt temperature was found to decrease gradually as the degassing time increased, but a clear correlation between the impeller rotation speed or inert gas flow rate and the melt heat loss could not be confirmed. Regardless of the impeller rotation speed or inert gas flow rate, the Mg and Ti contents in the A356 melt scarcely changed, even after degassing for more than 10 minutes, while Sr contents decreased at the maximum degassing rate of 70 ppm. From a quantitative analysis of the degassing rate under each experimental condition based on the hydrogen concentration in the melt derived from the melt density and the degassing model equation, the inert gas flow rate was found to affect the degassing rate rather than the impeller rotation speed under the degassing operation condition employed in the present study.

• Journal of Aerospace System Engineering
• /
• v.18 no.1
• /
• pp.37-45
• /
• 2024

This paper presents a design approach for passive vibration control to reduce vertical vibrations transmitted to the control unit during hovering flight of a quadrotor drone. Ground vibration test simulation based on finite element model was performed for forced vibration analysis of the quadrotor drone. First, modal analysis was performed to evaluate dynamic characteristics. Forced vibration response analysis was then performed to obtain the steady-state response within the operating frequency range under the hovering flight condition. Furthermore, to obtain the vibration reduction effect, a viscous damping tape was applied at positions that could induce vibrations transmitted to the control unit under the same conditions. Such a passive vibration control approach was investigated. Relevant vibration reduction effect was assessed with respect to the application of damping materials and the attachment position.

• Korean Association of Arts Management
• /
• no.50
• /
• pp.213-241
• /
• 2019

Recently, many interests in the economic contribution of performing arts for the city's tourist attractions have been increasing, and the policy projects supporting surtitle for foreign tourists are expanding. Therefore, the purpose of this study is to explore the acceptance process of subtitle systems using the TAM(Technical Acceptance Model) to understand the influential relations of factors affecting the viewing of the performance of subtitling service by foreign tourists. Data for empirical analysis were collected in a survey of foreign tourists who had experienced performance subtitles with smart pads in three languages. The results of this study are as follows. First, the higher the information system quality of the performance subtitles, the higher the perceived usefulness of the subtitles. Second, for Korean performances, the decreasing level of both the performance-based risk and the psychological risk has a positive influence on the viewing intent. But, the decreasing level of the financial risk has a negative influence on the viewing intent. Third, the decreasing level of performance risk has a positive influence on the perceived usefulness, while the decreasing level of psychological risk has a negative influence on the perceived usefulness. Finally, the psychological risk has the moderating effect of the viewing intention, which it has a negative influence on the perceived usefulness.

• Information Systems Review
• /
• v.23 no.1
• /
• pp.69-91
• /
• 2021

Credit Bureaus in Korea commonly use financial transaction information of the past and present time for calculating an individual's credit scores. Compared to other rating factors, the repayment history information accounts for a larger weights on credit scores. Accordingly, despite full redemption of overdue payments, late payment history is reflected negatively for the assessment of credit scores for certain period of the time. An individual with debt delinquency can be classified into two groups; (1) the individuals who have faithfully paid off theirs overdue debts(Normal Repayment), and (2) those who have not and as differences of creditworthiness between these two groups do exist, it needs to grant relatively higher credit scores to the former individuals with normal repayment. This study is designed to analyze the factors of normal repayment of Korean financial debt delinquents based on credit information of personal loan, overdue payments, redemption from Korea Credit Information Services. As a result of the analysis, the number of overdue and the type of personal loan and delinquency were identified as significant variables affecting normal repayment and among applied methodologies, neural network models suggested the highest classification accuracy. The findings of this study are expected to improve the performance of individual credit scoring model by identifying the factors affecting normal repayment of a financial debt delinquent.