• Journal of the Korea Society for Simulation
• /
• v.32 no.4
• /
• pp.19-26
• /
• 2023

The increase in the dropout rate of college students nationwide has a serious negative impact on universities and society as well as individual students. In order to proactive identify students at risk of dropout, this study built a decision tree, random forest, logistic regression, and deep learning-based dropout prediction model using academic data that can be easily obtained from each university's academic management system. Their performances were subsequently analyzed and compared. The analysis revealed that while the logistic regression-based prediction model exhibited the highest recall rate, its f-1 value and ROC-AUC (Receiver Operating Characteristic - Area Under the Curve) value were comparatively lower. On the other hand, the random forest-based prediction model demonstrated superior performance across all other metrics except recall value. In addition, in order to assess model performance over distinct prediction periods, we divided these periods into short-term (within one semester), medium-term (within two semesters), and long-term (within three semesters). The results underscored that the long-term prediction yielded the highest predictive efficacy. Through this study, each university is expected to be able to identify students who are expected to be dropped out early, reduce the dropout rate through intensive management, and further contribute to the stabilization of university finances.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.867-874
• /
• 2023

Recently, many problems are occurring in the bee ecosystem due to rapid climate change. The decline in the bee population and changes in the flowering period are having a huge impact on the harvest of bee-keepers. Since it is impossible to continuously observe the beehives in the hive with the naked eye, most people rely on knowledge based on experience about the state of the hive.Therefore, interest is focused on smart beekeeping incorporating IoT technology. In particular, with regard to swarming, which is one of the most important parts of beekeeping, we know empirically that the swarming time can be determined by the sound of the queen bee, but there is no way to systematically analyze this with data.You may think that it can be done by simply recording the sound of the queen bee and analyzing it, but it does not solve various problems such as various noise issues around the hive and the inability to continuously record.In this study, we developed a system that records queen bee sounds in a real-time cloud system and analyzes sound patterns.After receiving real-time analog sound from the hive through multiple channels and converting it to digital, a sound pattern that was continuously output in the queen bee sound frequency band was discovered. By accessing the cloud system, you can monitor sounds around the hive, temperature/humidity inside the hive, weight, and internal movement data.The system developed in this study made it possible to analyze the sound patterns of the queen bee and learn about the situation inside the hive. Through this, it will be possible to predict the swarming period of bees or provide information to control the swarming period.

• Journal of Navigation and Port Research
• /
• v.46 no.6
• /
• pp.483-490
• /
• 2022

Floating LiDAR is a system that provides a new paradigm for wind condition observation, which is essential when creating an offshore wind farm. As it can save time and money, minimize environmental impact, and even reduce backlash from local communities, it is emerging as the industry standard. However, the design and verification of a stable platform is very important, as disturbance factors caused by fluctuations of the buoy affect the reliability of observation data. In Korea, due to the nation's late entry into the technology, a number of foreign equipment manufacturers are dominating the domestic market. The west coast of Korea is a shallow sea environment with a very large tidal difference, so strong currents repeatedly appear depending on the region, and waves of strong energy that differ by season are formed. This paper conducted a study examining buoys suitable for LiDAR operation in the waters of Korea, which have such complex environmental characteristics. In this paper, we will introduce examples of optimized design and verification of ship-type buoys, which were applied first, and derive important concepts that will serve as the basis for the development of various platforms in the future.

• Journal of Korea Port Economic Association
• /
• v.39 no.2
• /
• pp.41-57
• /
• 2023

The drybulk shipping market has high freight rate volatility in the chartering market and various and complex factors affecting the market. In the unstable economic situation caused by the COVID-19 pandemic in 2020, the BDI plunged due to a decrease in trade volume, but turned from the end of 2020 and maintained a booming period until the end of 2022. The main reason for the market change is the decrease in the available fleet that can actually be operated for cargo transport due to port congestion by the COVID-19 pandemic, regardless of the fleet and trade volume volatility that have affected the drybulk shipping market in the past. A decrease in the actual usable fleet due to vessel waiting at port by congestion led to freight increase, and the freight increase in charting market led to an increase in second-hand ship and new-building ship price in long-term equilibrium relationship. In the past, the drybulk shipping market was determined by the volatility of fleet and trade volume. but, in the future, available fleet volume volatility by pandemics, environmental regulations and climate will be the important factors affecting BDI. To response to the IMO carbon emission reduction in 2023, it is expected that ship speed will be slowed down and more ships are expected to be needed to transport the same trade volume. This slowdown is expected to have an impact on drybulk shipping market, such as a increase in freight and second-hand ship and new-building ship price due to a decrease in available fleet volume.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.395-413
• /
• 2023

This research studied the effect of customer experience characteristics in offline home appliance stores on perceived value and revisit intention. Among the offline distribution of home appliances with more than 100 stores nationwide, two home appliance retailers (HiMart, E-Land), three hypermarkets (E-Mart, Homeplus, Lotte Hi-Mart), and two home appliance stores (LG Best Shop, Samsung Digital Plaza) were selected, and a survey was conducted on men and women in their 20s or older in Seoul, Gyeonggi, and Incheon who had visited and purchased the home appliance store within the last 6 months. As a result of the survey, a statistical analysis was conducted on a total of 330 samples using the PLS (Partial Least Squares) structural equation model and SPSS statistical package. Through this study, the following research results can be obtained. First, educational experience, deviant experience, and aesthetic experience had a positive (+) effect on the functional value. However, entertainment experience did not affect functional value. Second, educational experience, deviant experience, and aesthetic experience all had a positive (+) effect on emotional value. Third, both functional and sensory values had a positive (+) effect on the revisit intention. Fourth, it was confirmed that brand loyalty had no moderating effect between functional value and sensory value revisit intention. The results of this study show the structural relationship between customer experience characteristics, perceived value (functional value, sensory value), and revisit intention. This result provides guidelines on what activities home appliance offline stores should do at a time when online channels threaten the survival of offline channels.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.309-323
• /
• 2023

As the role of online reviews has become increasingly crucial, numerous studies have been conducted to utilize helpful reviews. Helpful reviews, perceived by customers, have been verified in various research studies to be influenced by factors such as ratings, review length, review content, and so on. The determination of a review's helpfulness is generally based on the number of 'helpful' votes from consumers, with more 'helpful' votes considered to have a more significant impact on consumers' purchasing decisions. However, recently written reviews that have not been exposed to many customers may have relatively few 'helpful' votes and may lack 'helpful' votes altogether due to a lack of participation. Therefore, rather than relying on the number of 'helpful' votes to assess the helpfulness of reviews, we aim to classify them based on review content. In addition, the text of the review emerges as the most influential factor in review helpfulness. This study employs text mining techniques, including topic modeling and sentiment analysis, to analyze the diverse impacts of content and emotions embedded in the review text. In this study, we propose a review helpfulness prediction model based on review content, utilizing movie reviews from IMDb, a global movie information site. We construct a review helpfulness prediction model by using an explainable Graph Neural Network (GNN), while addressing the interpretability limitations of the machine learning model. The explainable graph neural network is expected to provide more reliable information about helpful or non-helpful reviews as it can identify connections between reviews.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.4
• /
• pp.80-96
• /
• 2023

The expansion of human activities and road development has led to the loss and fragmentation of ecological spaces, which is a negative factor for biodiversity. In particular, urban areas where land use and land cover have rapidly changed into urbanization zones are regions where ecological spaces are lost and isolated, making it difficult for wildlife to inhabit. Furthermore, the loss and fragmentation of ecological spaces due to urbanization can have a negative impact on ecosystem services. Therefore, to enhance biodiversity and ecosystem services in urban and national land, it is necessary to establish a practical ecological axis that reflects the current status of the city. Thus, this study analyzed the connectivity of ecological spaces and forest axis that can be used for spatial planning related to urban ecological axis of local governments in Daegu and Gyeongsangbuk-do. The ecological connectivity was analyzed by dividing the Daegu-Gyeongbuk region into 31 local government units, distinguishing between forests and natural areas using land cover data. Subsequently, the study area was divided into 20,483 hexagonal grids of 1 square kilometer each, and the restoration effects for ecological fragmentation within 100 meters were spatially clustered to visualize priority restoration areas. The forest axis was derived by considering regional conditions such as land cover, building area, slope, and others to connect 1,534 forests of 100 hectares or more. The research results are expected to be used as fundamental data for spatial planning, goal setting, and the selection of restoration areas for improving ecological connectivity.

• Journal of Marine Bioscience and Biotechnology
• /
• v.15 no.2
• /
• pp.82-89
• /
• 2023

Microalgae, as photosynthetic organisms, possess the ability to produce a diverse array of bioactive compounds. This study focused on the transformant Chlamydomonas reinhardtii dZL and subjected it to cultivation under varying light intensities (60, 120, 180, and 240 µmol/m²/s). Our aim was to assess the impact of light intensity on both microalgal biomass and carotenoid production. The cultivation took place in 80 mL bubble column photobioreactors, specifically the Multi-cultivator. Notably, the culture exposed to 240 µmol/m²/s exhibited the most rapid cell growth, surpassing even the cell concentration achieved at 180 µmol/m²/s by day 8. A detailed analysis of the specific irradiance rate over time unequivocally revealed a sharp decline in growth rates when the rate fell below 2 × 10^-10 µmol/cell/s. Although the culture with 60 µmol/m²/s yielded the highest carotenoid content (1.2% of dry weight), the culture exposed to 240 µmol/m²/s recorded the highest carotenoid concentration at 8.9 mg/L owing to its higher biomass. Our findings reveal the critical importance of maintaining a specific irradiance rate above 2 × 10^-10 µmol/cell/s to enhance biomass and carotenoid productivity. This study lays the groundwork for defining optimal light intensity conditions applicable to mass culture systems, with the objective of augmenting C. reinhardtii biomass and optimizing carotenoid productivity.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.6
• /
• pp.663-671
• /
• 2023

This research experimentally evaluated the recyclability of four varieties of lignocellulosic fly ash(FA), a by-product from three power plants employing lignocellulosic biomass(Bio-SRF, wood pellets) as a fuel source. Comprehensive analyses were conducted on FA, encompassing both physical parameters (particle shape, size distribution, fineness, and density) and chemical properties(chemical composition and heavy metal content). Mortar test specimens, with FA mixing ratios ranging from 5 to 20%, were produced in compliance with KS L 5405 standards, and their flow and compressive strength were subsequently measured. The test results indicated that the four types of FA exhibited particle sizes approximately between 20~30㎛, densities around 2.3~2.5g/cm³, and a fineness range of 2,600~4,900cm²/g. The FA comprised approximately 50~90% of components such as SiO₂, Al₂O₃, Fe₂O₃, and CaO, displaying characteristics akin to type-II and type-III FA of KS L 5405 standards, albeit with differences in chlorine and SiO₂ content. From the mortar tests, it was observed that the compressive strength of the mortar ranged between 34~47MPa when the pellet combustion FA was mixed in proportions of 5~20%. FA, produced exclusively from the combustion of 100% lignocellulosic fuel, is assessed to possess high recyclability potential as a substitute for conventional admixtures.

• Journal of the Korean Institute of Gas
• /
• v.27 no.4
• /
• pp.43-49
• /
• 2023

Hydrofluoric acid is a less acidic substance than hydrochloric acid, nitric acid, and sulfuric acid, but it is one of the most dangerous substances for humans. In recent years, it has become an indispensable substance in industries such as chemical plants and the semiconductor industry, and although it is a threat to the human body, its use is increasing for various purposes, and the amount of use is constantly increasing due to the expansion and development of the industry. The dangers of hydrogen fluoride have been highlighted since the 2012 accident, which led to a more than fivefold increase in management standards for handling facilities. Hydrogen fluoride converts to hydrofluoric acid when exposed to the air, which can be fatal to humans. This study simulates the effects of a release of a toxic substance in the workplace, even though a protection layer has been provided to minimize the damage caused by the released toxic substance, and recommend ways to control the risk to workers in the event of a release in the workplace.